{ "schema_version": 1, "generated_at": "2026-07-12T08:54:32.729933+00:00", "source": { "name": "UniProt manual", "repository": "https://github.com/ebi-uniprot/uniprot-manual", "help_url": "https://www.uniprot.org/help", "license": "CC BY 4.0", "commit": { "sha": "029b6f5e7b2141e264cc9fa29bb789d76b7626eb", "date": "2026-06-12T12:50:53Z", "url": "https://github.com/ebi-uniprot/uniprot-manual/commit/029b6f5e7b2141e264cc9fa29bb789d76b7626eb" } }, "document_count": 281, "category_counts": { "manual": 117, "UniProtKB": 87, "help": 73, "faq": 67, "Sequence": 40, "Text_search": 34, "Biocuration": 33, "Technical": 32, "UniParc": 24, "UniRef": 21, "Website": 21, "Family_and_domains": 17, "Cross-references": 16, "Proteomes": 16, "Function": 15, "PTM_processing": 15, "Automatic_annotation": 14, "Programmatic_access": 14, "disease_phenotypes_variants": 13, "About_UniProt": 12, "Download": 11, "Names_and_taxonomy": 11, "Release": 10, "Entry_information": 9, "Keywords": 9, "project": 8, "Taxonomy": 7, "Get_started": 6, "Human": 6, "Controlled_vocabulary": 5, "Interaction": 5, "Publications": 5, "Subcellular_location": 5, "3D_structure": 4, "Expression": 4, "Nomenclature": 4, "Staff": 4, "Ontology": 3, "Protein_existence": 3, "Similar_proteins": 3, "Miscellaneous": 2, "async_download": 1, "Chordata": 1, "file_generation": 1, "Fungi": 1, "Invertebrates": 1, "Outreach": 1, "search": 1, "solr": 1, "statistics": 1, "Viruses": 1 }, "module_counts": { "foundations": 9, "search": 16, "entry": 54, "proteomes": 78, "sequence-tools": 29, "id-mapping": 13, "programmatic": 24, "annotation": 37, "release": 11, "reference": 10 }, "topic_counts": { "Search": 106, "Taxonomy": 93, "API": 82, "Evidence": 79, "Download": 47, "Proteome": 47, "Variant": 47, "PTM": 42, "Structure": 41, "FASTA": 34, "Sequence tools": 17, "ID mapping": 12 }, "modules": [ { "key": "foundations", "label": "UniProt 数据体系", "count": 9 }, { "key": "search", "label": "检索与结果整理", "count": 16 }, { "key": "entry", "label": "UniProtKB 条目解读", "count": 54 }, { "key": "proteomes", "label": "Proteome 与 FASTA", "count": 78 }, { "key": "sequence-tools", "label": "序列与分析工具", "count": 29 }, { "key": "id-mapping", "label": "ID Mapping", "count": 13 }, { "key": "programmatic", "label": "API 与批量获取", "count": 24 }, { "key": "annotation", "label": "注释与证据", "count": 37 }, { "key": "release", "label": "版本、提交与支持", "count": 11 }, { "key": "reference", "label": "术语与数据标准", "count": 10 } ], "documents": [ { "slug": "about", "title": "About UniProt", "type": "help", "categories": [ "About_UniProt", "Staff", "UniProtKB", "UniRef", "UniParc", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "Variant" ], "excerpt": "The mission of UniProt is to provide the scientific community with a comprehensive, high-quality and freely accessible resource of protein sequence and functional information. The Universal Protein Resource (UniProt) is a comprehensive resource for protein sequence and annotation data. The UniProt databases are the UniProt Knowledgebase (UniProtKB), the UniP...", "headings": [ { "level": 1, "title": "Funding" }, { "level": 1, "title": "Past funding" }, { "level": 1, "title": "Data preservation" }, { "level": 1, "title": "Further information" }, { "level": 1, "title": "Logo" }, { "level": 1, "title": "Contact the UniProt consortium members" } ], "word_count": 601, "official_url": "https://www.uniprot.org/help/about", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/about.md", "source_path": "about.md", "sha256": "ed3356cfdcf281b29db4dcb0375b55c51216ba6629a46ddcea2d83b02204cbe8" }, { "slug": "accession_numbers", "title": "Accession", "type": "help", "categories": [ "Entry_information", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [], "excerpt": "This subsection of the 'Entry information' section provides one or more accession number(s). These are stable identifiers and should be used to cite UniProtKB entries. Upon integration into UniProtKB, each entry is assigned a unique accession number, which is called 'Primary (citable) accession number'. UniProtKB accession numbers consist of 6 or 10 alphanum...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 355, "official_url": "https://www.uniprot.org/help/accession_numbers", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/accession_numbers.md", "source_path": "accession_numbers.md", "sha256": "43a0bd505635a266ee5a4817361c708fd6307ef3ac3331eeda38cd2092d4da59" }, { "slug": "act_site", "title": "Active site", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the Function section is used for enzymes and indicates the residues directly involved in catalysis. Example: Q9F6D4 When the exact role of an active site residue is known, this is indicated using a semi-controlled vocabulary in the 'Description' field. The possible roles are: Charge relay system Electrophile Nucleophile Proton donor Proton...", "headings": [], "word_count": 167, "official_url": "https://www.uniprot.org/help/act_site", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/act_site.md", "source_path": "act_site.md", "sha256": "fa9226b028156545e008dbb01962d2f5f7a3a48cdba86c5bb0df8324e00646c9" }, { "slug": "activity_regulation", "title": "Activity regulation", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the Function section describes regulatory mechanisms for enzymes, transporters or microbial transcription factors, and reports the components which regulate (by activation or inhibition) the reaction. Example: P17289 A regulation can be allosteric, performed by natural or synthetic products or may be due to a post-translational modificatio...", "headings": [], "word_count": 106, "official_url": "https://www.uniprot.org/help/activity_regulation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/activity_regulation.md", "source_path": "activity_regulation.md", "sha256": "7155f7be390e291f15161447db6aaf5416d03e658103e96807d9de68330228af" }, { "slug": "advanced_search", "title": "UniProtKB advanced search options", "type": "help", "categories": [ "Website", "Text_search", "Technical", "help" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "Evidence", "Structure", "Variant", "Taxonomy" ], "excerpt": "The advanced search interface allows to browse the different search fields and options within the dropdown menus. There is a search box right at the top when you open the blue dropdown menu that allows you to type a concept name (e.g. \"structure\") and receive some autocompleted suggestions from which you can then select the most suitable one: The table below...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 730, "official_url": "https://www.uniprot.org/help/advanced_search", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/advanced_search.md", "source_path": "advanced_search.md", "sha256": "cb62d70eb44568bca8a1118a88c8516e92b44ac1f4da89e0f782029aa4af9d9d" }, { "slug": "allergenic_properties", "title": "Allergenic properties", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section is used for proteins that cause an allergic reaction in mammals. We usually specify in which species the protein is allergenic. Example: Q06811 There is however an exception for an enzyme that does not cause allergic reaction by itself, but catalyzes a modification responsible for multiple alle...", "headings": [ { "level": 1, "title": "Related document" } ], "word_count": 72, "official_url": "https://www.uniprot.org/help/allergenic_properties", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/allergenic_properties.md", "source_path": "allergenic_properties.md", "sha256": "3d72006f2bb44bda636bc73b0f19c613724dcdad7165bcc626f74b01330b9da0" }, { "slug": "alternative_products", "title": "Alternative products", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Evidence" ], "excerpt": "This subsection of the 'Sequence' section lists the alternative protein sequences (isoforms) that can be generated from the same gene by a single or by the combination of up to four biological events (alternative promoter usage, alternative splicing, alternative initiation and ribosomal frameshifting). Additionally, this section gives relevant information on...", "headings": [ { "level": 1, "title": "1. General information" }, { "level": 1, "title": "2. Isoform-specific information" }, { "level": 2, "title": "Identifier" }, { "level": 2, "title": "Name and synomym(s)" }, { "level": 2, "title": "Description of the sequence differences" }, { "level": 2, "title": "Description of characteristics that differ from the canonical form" }, { "level": 2, "title": "Information in free text can be provided to complement the above items" }, { "level": 1, "title": "Notes" }, { "level": 1, "title": "Related documents" } ], "word_count": 575, "official_url": "https://www.uniprot.org/help/alternative_products", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/alternative_products.md", "source_path": "alternative_products.md", "sha256": "4c0b9ec8c9fb623a2431aa324acb38c953e25649ec81ab06c8a7a43c32416e8d" }, { "slug": "annotation_guidelines", "title": "Annotation guidelines", "type": "help", "categories": [ "Biocuration", "UniProtKB", "Protein_existence", "Names_and_taxonomy", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Evidence", "Structure", "Taxonomy" ], "excerpt": "Standard operating procedure (SOP) for UniProt manual curation This document describes the manual curation procedure used by the UniProt Consortium members. The UniProt manual curation process comprises manual review of results from a range of sequence analysis programs and literature curation of experimental data as well as attribution of all information to...", "headings": [ { "level": 1, "title": "Standard operating procedure (SOP) for UniProt manual curation" }, { "level": 1, "title": "Protein naming guidelines" }, { "level": 1, "title": "Criteria description for protein existence" } ], "word_count": 383, "official_url": "https://www.uniprot.org/help/annotation_guidelines", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/annotation_guidelines.md", "source_path": "annotation_guidelines.md", "sha256": "06d9fc2f9c3e2ce5991b002c72f0bfad73dd854f87ffc9dfb27bd74397690357" }, { "slug": "annotation_score", "title": "Annotation score", "type": "help", "categories": [ "UniProtKB", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Evidence" ], "excerpt": "The annotation score provides a heuristic measure of the annotation content of a UniProtKB entry or proteome. This score cannot be used as a measure of the accuracy of the annotation as we cannot define the 'correct annotation' for any given protein. The annotation score is computed in the following way: Different UniProtKB annotation types (e.g. protein nam...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 384, "official_url": "https://www.uniprot.org/help/annotation_score", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/annotation_score.md", "source_path": "annotation_score.md", "sha256": "064ad9fbe156f2a143561947a4443089fae86d842865878634476d4a9aef2283" }, { "slug": "Antibody_binding_sequences", "title": "Antibody binding sequences", "type": "help", "categories": [ "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "API", "Variant" ], "excerpt": "Regions of a protein sequence that are specifically recognized by Human Protein Atlas antibodies used in protein expression and profiling experiments. Antibodies are generated against Protein Epitope Signature Tag (PrEST) fragments, whose sequences are selected based on the principles of lowest sequence similarity to other human proteins and for properties t...", "headings": [ { "level": 1, "title": "Where can I find this data in UniProt?" } ], "word_count": 191, "official_url": "https://www.uniprot.org/help/Antibody_binding_sequences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Antibody_binding_sequences.md", "source_path": "Antibody_binding_sequences.md", "sha256": "3093328698d31474d65d07a24904b3998450ca900ea41a64145b5b16f35e838f" }, { "slug": "api", "title": "How can I access UniProt resources programmatically?", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Text_search", "Programmatic_access", "Technical", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "API", "ID mapping" ], "excerpt": "UniProt has a number of freely available APIs that allow users to access data in their favourite programming languages. Please see our Programmatic access page for further details of our API services and data endpoints. All resources (individual entries as well as sets of entries retrieved by queries) are accessible through RESTful URLs that can be bookmarke...", "headings": [ { "level": 1, "title": "Examples of the services that can be accessed programmatically" } ], "word_count": 146, "official_url": "https://www.uniprot.org/help/api", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/api.md", "source_path": "api.md", "sha256": "b142a47485361ad58c65f76c6b4d583c0a0e07dc48f8db6c44b7095e16addc4e" }, { "slug": "api_queries", "title": "Programmatic access - Retrieving entries via queries", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Programmatic_access", "Text_search", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "FASTA", "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "You can use any query to define the set of entries that you are interested in. It is perhaps simplest to start with an interactive text search on the website to find the URL for your set, e.g., all reviewed human entries: The data for the website is provided by our REST API. For the above example, the request to retrieve the first batch of data would be: The...", "headings": [ { "level": 1, "title": "Formats" }, { "level": 2, "title": "Format Parameter" }, { "level": 1, "title": "TAB SEPARATED VALUES" }, { "level": 1, "title": "XML" }, { "level": 2, "title": "Accept Header" }, { "level": 1, "title": "TAB SEPARATED VALUES" }, { "level": 1, "title": "XML" }, { "level": 1, "title": "What formats are available?" }, { "level": 2, "title": "List of all formats" }, { "level": 2, "title": "Accept header" }, { "level": 2, "title": "Format Parameter" }, { "level": 1, "title": "Tips" }, { "level": 1, "title": "Python Examples" }, { "level": 2, "title": "1. Use search results immediately within a Python script" }, { "level": 3, "title": "1.1 Small number of results: use stream" }, { "level": 4, "title": "Stream limitations" }, { "level": 4, "title": "Steps" }, { "level": 3, "title": "1.2 Large number of results: use pagination" }, { "level": 4, "title": "Steps" }, { "level": 2, "title": "2. Save search results to disk" }, { "level": 3, "title": "2.1 Small number of results: use stream" }, { "level": 4, "title": "Stream limitations" }, { "level": 4, "title": "Steps" }, { "level": 3, "title": "2.2 Large number of results: use pagination" }, { "level": 4, "title": "Steps" } ], "word_count": 1626, "official_url": "https://www.uniprot.org/help/api_queries", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/api_queries.md", "source_path": "api_queries.md", "sha256": "9f7c08ec54c002280024c185c76996ff3474a6ebcd76c0377566a8c28bf2460e" }, { "slug": "api_retrieve_entries", "title": "Programmatic access - Retrieving individual entries", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Programmatic_access", "help" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "FASTA", "API", "ID mapping", "Taxonomy" ], "excerpt": "The web address for an entry consists of a data set name (e.g. uniprot, uniref, uniparc, taxonomy,...) and the entry's unique identifier, e.g.: https://www.uniprot.org/uniprotkb/P12345 By default, a web page is returned. Depending on the data set, other formats may also be available (click on \"Formats\" on the entry's web page). Here are some examples: https:...", "headings": [ { "level": 1, "title": "Resolving RDF identifiers" }, { "level": 1, "title": "See also" } ], "word_count": 361, "official_url": "https://www.uniprot.org/help/api_retrieve_entries", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/api_retrieve_entries.md", "source_path": "api_retrieve_entries.md", "sha256": "97c9b07489f7abcb5443394ed3487f769632ebf1646b1aac9827457f7e7f51e4" }, { "slug": "arba", "title": "Automatic annotation using ARBA", "type": "help", "categories": [ "UniProtKB", "Automatic_annotation", "help" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "UniProt's Automatic Annotation pipeline enhances the unreviewed records in UniProtKB by enriching them with automatic classification and annotation. The Association-Rule-Based Annotator (ARBA) is one of the contributors to this pipeline. It is a multiclass learning system trained on expertly annotated entries in UniProtKB/Swiss-Prot. ARBA uses rule mining te...", "headings": [ { "level": 1, "title": "ARBA based evidence for UniProtKB annotation (example: Q3TWF3)" }, { "level": 1, "title": "Searching ARBA rules" }, { "level": 1, "title": "Exploring the ARBA rule pages" } ], "word_count": 431, "official_url": "https://www.uniprot.org/help/arba", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/arba.md", "source_path": "arba.md", "sha256": "ecbae20ae5f15d19a0d895f261141a69b95531967ce28bde78d518da30450dec" }, { "slug": "assessing_proteomes", "title": "Assessing proteome completeness and quality", "type": "help", "categories": [ "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Taxonomy" ], "excerpt": "In order to assess quality and completeness of proteomes, we provide two values: Statistical evaluation and classification of the proteome by the Complete Proteome Detector (CPD) algorithm (developed by UniProt) The BUSCO score of the proteome, which was developed to quantify genomic data completeness in terms of expected gene content. Complete Proteome Dete...", "headings": [ { "level": 1, "title": "Complete Proteome Detector (CPD)" }, { "level": 2, "title": "Score definitions" }, { "level": 1, "title": "Benchmarking Universal Single-Copy Orthologs (BUSCO)" } ], "word_count": 593, "official_url": "https://www.uniprot.org/help/assessing_proteomes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/assessing_proteomes.md", "source_path": "assessing_proteomes.md", "sha256": "c237fa3718554c74483ad81c47cc1a9e91c3861cd144dfdaf42e34902d75f3af" }, { "slug": "automatic_annotation", "title": "Automatic annotation", "type": "help", "categories": [ "Automatic_annotation", "Biocuration", "UniProtKB", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence" ], "excerpt": "UniProt's Automatic Annotation pipeline enhances the unreviewed records in UniProtKB by enriching them with automatic classification and annotation. Automatic classification and domain annotation UniProt uses InterPro to classify sequences at superfamily, family and subfamily levels and to predict the occurrence of functional domains and important sites. Int...", "headings": [ { "level": 1, "title": "Automatic classification and domain annotation" }, { "level": 1, "title": "Automatic annotation" } ], "word_count": 212, "official_url": "https://www.uniprot.org/help/automatic_annotation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/automatic_annotation.md", "source_path": "automatic_annotation.md", "sha256": "d209ebe6328269708656d456c27d00882939e463d4f054a1d027e28d9ae61e4b" }, { "slug": "basket", "title": "Saving proteins with the UniProt basket", "type": "help", "categories": [ "Text_search", "UniParc", "UniProtKB", "UniRef", "Website", "Download", "help" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "Download", "ID mapping", "Sequence tools", "Taxonomy" ], "excerpt": "When browsing through different UniProt proteins, you can use the 'basket' to save them, so that you can back to find or analyse them later. The UniProt basket allows you to remember your favorite proteins build your own selection of proteins over time come back to a saved protein later on analyse a subset of your proteins (Align, BLAST, ID mapping, download...", "headings": [ { "level": 1, "title": "Adding proteins to your basket" }, { "level": 1, "title": "Using the basket" }, { "level": 1, "title": "See also" } ], "word_count": 330, "official_url": "https://www.uniprot.org/help/basket", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/basket.md", "source_path": "basket.md", "sha256": "d675939d87ec66420877666cc2f7790b13cc2c2f0d66abdf871885f306a455d9" }, { "slug": "bateman", "title": "Alex Bateman", "type": "help", "categories": [ "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search" ], "excerpt": "Senior Team Leader Protein Sequence Resources and Group Leader Bateman Research Group. E-mail: agb  [at]  ebi.ac.uk EMBL Outstation European Bioinformatics Institute (EMBL/EBI) Wellcome Trust Genome Campus Hinxton, Cambridge CB10 1SD United Kingdom Phone: +44 (0)1223 379 494100 Fax: +44 (0)1223 494469 Short biography Dr. Alex Bateman joined EMBL-EBI as the H...", "headings": [ { "level": 1, "title": "Short biography" }, { "level": 1, "title": "Groups" } ], "word_count": 224, "official_url": "https://www.uniprot.org/help/bateman", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/bateman.md", "source_path": "bateman.md", "sha256": "519fcf9856fba7fccf7d7cb311e2e92cbb5e1ba3b217e82d1dde13833954412e" }, { "slug": "binary_interactions", "title": "Binary interactions", "type": "help", "categories": [ "Interaction", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "API", "Variant" ], "excerpt": "This subsection of the 'Interaction' section provides information about binary protein-protein interactions. The data presented in this section are a quality-filtered subset of binary interactions automatically derived from the IntAct database. It is updated at every UniProt release. Binary interaction plot This is a graphical plot representation of the bina...", "headings": [ { "level": 1, "title": "Binary interaction plot" }, { "level": 1, "title": "Binary interaction table" }, { "level": 1, "title": "Related documents" } ], "word_count": 497, "official_url": "https://www.uniprot.org/help/binary_interactions", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/binary_interactions.md", "source_path": "binary_interactions.md", "sha256": "645103d7e358ff8ab24408a8193e4d65e92899b87491e9676c66cbe51c6e0e4d" }, { "slug": "binary_interactions_import", "title": "Why are only a subset of binary interactions from the IntAct database reported in UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Interaction", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search" ], "excerpt": "The imported subset of binary interactions is determined using a simple scoring system developed by IntAct and a score threshold that has been deliberately chosen to exclude interactions supported by only one experimental observation. Details of how interactions are scored can be found at the IntAct website. This simple score-based filter is used in combinat...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 117, "official_url": "https://www.uniprot.org/help/binary_interactions_import", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/binary_interactions_import.md", "source_path": "binary_interactions_import.md", "sha256": "55467c7eec1a5fa7f505ea557462acabe33fffabad0d39b2e7c5f1bcd45af9ac" }, { "slug": "binding", "title": "Binding site", "type": "help", "categories": [ "Function", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Structure" ], "excerpt": "This subsection of the Function section describes the interaction between protein residues and a chemical entity. Priority is given to the annotation of physiological ligands (metals, cofactors, substrates and products of enzymes, allosteric regulators, physiological inhibitors/activators, ligands of receptors/sensors and transporters/channels, effectors of ...", "headings": [], "word_count": 242, "official_url": "https://www.uniprot.org/help/binding", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/binding.md", "source_path": "binding.md", "sha256": "3be049cf56fff2f657d6696f257e8cb451b7a6f16f989d59a98bfc566c4917f9" }, { "slug": "biocuration", "title": "Biocuration in UniProt", "type": "help", "categories": [ "Biocuration", "Automatic_annotation", "UniProtKB", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Evidence" ], "excerpt": "Introduction One of the central activities of the UniProt Consortium is the biocuration of the UniProt Knowledgebase (UniProtKB). Biocuration involves the interpretation and integration of information relevant to biology into a database or resource that enables integration of the scientific literature as well as large data sets. Accurate and comprehensive re...", "headings": [ { "level": 1, "title": "Introduction" }, { "level": 1, "title": "UniProt manual curation" }, { "level": 1, "title": "See also" }, { "level": 1, "title": "UniProt automatic annotation" }, { "level": 1, "title": "UniProt annotation flow diagram" } ], "word_count": 311, "official_url": "https://www.uniprot.org/help/biocuration", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/biocuration.md", "source_path": "biocuration.md", "sha256": "03ce4213171dda4d695359e7da585a6dec263dcd304b7f64b536f1790d31739e" }, { "slug": "biophysicochemical_properties", "title": "Biophysicochemical properties", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Function' section describes biophysical and chemical properties, such as maximal absorption, kinetic parameters, pH dependence, redox potentials and temperature dependence. Example: Q8W1X2 We report the following biophysical and chemical properties: 1. Absorption The 'Absorption' subsection is mainly used to indicate the wavelength at...", "headings": [ { "level": 1, "title": "1. Absorption" }, { "level": 1, "title": "2. Kinetic parameters" }, { "level": 1, "title": "3. pH dependence" }, { "level": 1, "title": "4. Redox potential" }, { "level": 1, "title": "5. Temperature dependence" } ], "word_count": 463, "official_url": "https://www.uniprot.org/help/biophysicochemical_properties", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/biophysicochemical_properties.md", "source_path": "biophysicochemical_properties.md", "sha256": "4f42758942c6f7451fc0cb534c2d4986a887b04d3c5f01eee2dda77ba93068ae" }, { "slug": "biotechnological_use", "title": "Biotechnological use", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section describes the use of a specific protein in the biotechnological industry. It explains in a few words in which biotechnological process the protein is used or could be used, with an explanation that describes the commercial use of the protein. The brand names of the product and of the firm that ...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 157, "official_url": "https://www.uniprot.org/help/biotechnological_use", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/biotechnological_use.md", "source_path": "biotechnological_use.md", "sha256": "d9b1d7bed5c9fd6451d307b1752ec6926faed6c6a0af5e8eb63170cc3442775b" }, { "slug": "blast-submission", "title": "Sequence similarity searches / BLAST submissions", "type": "help", "categories": [ "Website", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "API", "Sequence tools", "Taxonomy" ], "excerpt": "Overview BLAST (Basic Local Alignment Search Tool) is a widely used algorithm in bioinformatics that identifies regions of similarity between biological sequences (like proteins, DNA, or RNA). BLAST compares a query sequence to a database of sequences and finds matching segments, which can help researchers infer homologous genes, determine protein functions,...", "headings": [ { "level": 2, "title": "Overview" }, { "level": 2, "title": "Where to find the BLAST tool" }, { "level": 2, "title": "Job submission form" }, { "level": 3, "title": "Input sequences" }, { "level": 3, "title": "Choosing the correct target database" }, { "level": 3, "title": "Restrict by taxonomy" }, { "level": 3, "title": "Job name" }, { "level": 3, "title": "Advanced parameters" }, { "level": 2, "title": "Related services" } ], "word_count": 1437, "official_url": "https://www.uniprot.org/help/blast-submission", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/blast-submission.md", "source_path": "blast-submission.md", "sha256": "1a73956d8c7673c7b95312485ba276c6d396b8ebc07b7bd23af790a7244c45e0" }, { "slug": "browser_support", "title": "Browser support", "type": "help", "categories": [ "Website", "Technical", "help" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "UniProt's policy with internet browser support is to support all major browsers up to the oldest version that is also supported by the vendor. We recommend to use one of the following major web browsers for the UniProt website: Firefox: Choosing a Firefox update channel Chrome: Latest stable release Safari: Look for \"Safari\" in Apple security updates Edge: M...", "headings": [], "word_count": 126, "official_url": "https://www.uniprot.org/help/browser_support", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/browser_support.md", "source_path": "browser_support.md", "sha256": "9c7bdbedcb5248c95a31c7aa1946e7ddf148a06dd778ddc47da7deb728fe1cc3" }, { "slug": "ca_bind", "title": "Calcium binding - deprecated", "type": "help", "categories": [], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search" ], "excerpt": "Historically, UniProtKB has described a few classes of ligand binding sites with dedicated annotation types to make it easier to query them. This has been the case for 'Calcium binding', 'Metal binding' and 'Nucleotide binding'. With the switch to the ChEBI ontology for ligand classification, this is no longer necessary: These annotation types were deprecate...", "headings": [], "word_count": 65, "official_url": "https://www.uniprot.org/help/ca_bind", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ca_bind.md", "source_path": "ca_bind.md", "sha256": "89d88748d301e6c99e38d4b9e065b23e0cc6eac664a42ece4c3f4b3b2e95ac8c" }, { "slug": "Caenorhabditis", "title": "Caenorhabditis protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search", "Evidence", "Taxonomy" ], "excerpt": "The Caenorhabditis protein annotation project focuses on the manual annotation of C. elegans and C. briggsae proteins. See: How do we manually annotate a UniProtKB entry? UniProtKB works closely both with the worm research community and with WormBase, the database of the biology and genome of C. elegans and related nematode species, to ensure that UniProtKB ...", "headings": [ { "level": 1, "title": "About Caenorhabditis" } ], "word_count": 344, "official_url": "https://www.uniprot.org/help/Caenorhabditis", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Caenorhabditis.md", "source_path": "Caenorhabditis.md", "sha256": "1392b4b3531c35f7de3a4ed628b16a54322c5a38298ae6af8425d7e3fabcfbf6" }, { "slug": "canonical_and_isoforms", "title": "What is the canonical sequence? Are all isoforms described in one entry?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Text_search", "Download", "Technical", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Search", "Download", "PTM", "Variant" ], "excerpt": "What is the canonical sequence? Each UniProtKB/Swiss-Prot entry contains all curated protein products encoded by a given gene in a given species or strain. For each UniProtKB/Swiss-Prot entry, we choose a canonical (or representative) sequence for display that should conform to at least one of the following criteria: 1. It is functional; 2. It is widely expr...", "headings": [ { "level": 1, "title": "What is the canonical sequence?" }, { "level": 1, "title": "Are all isoforms described in one UniProtKB/Swiss-Prot entry?" }, { "level": 1, "title": "How can I retrieve isoform sequences?" }, { "level": 1, "title": "See also" } ], "word_count": 431, "official_url": "https://www.uniprot.org/help/canonical_and_isoforms", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/canonical_and_isoforms.md", "source_path": "canonical_and_isoforms.md", "sha256": "c365cc2c1eb64859dd9bafa7aec6e64964c38dc0becdc23b73cc707ff6488925" }, { "slug": "canonical_nucleotide", "title": "How do I get the nucleotide sequence that corresponds to the UniProtKB sequence?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Cross-references", "Text_search", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "Variant" ], "excerpt": "How do I get the nucleotide sequence that corresponds to the canonical UniProtKB sequence? You cannot! Although more than 95% of the known protein sequences derive from DNA translation, there is no single nucleic acid reference sequence for a given UniProtKB/Swiss-Prot protein sequence. The canonical protein sequence is the outcome of thorough curation work,...", "headings": [ { "level": 1, "title": "How do I get the nucleotide sequence that corresponds to the canonical UniProtKB sequence?" }, { "level": 1, "title": "How do I get the nucleotide sequence that corresponds to the UniProtKB alternative sequences?" }, { "level": 1, "title": "See also" } ], "word_count": 396, "official_url": "https://www.uniprot.org/help/canonical_nucleotide", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/canonical_nucleotide.md", "source_path": "canonical_nucleotide.md", "sha256": "ded1b8fbcdf3451b7ec6a4251bd57d74fc42ee62a9286b9a5217edaaa7bb55bb" }, { "slug": "carbohyd", "title": "Glycosylation", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Structure" ], "excerpt": "This subsection of the PTM / Processing section specifies the position and type of each covalently attached glycan group (mono-, di-, or polysaccharide). Glycosylation types are classified according to the identity of the atom of the amino acid which binds the carbohydrate chain, i.e. C-linked, N-linked, O-linked or S-linked. N-, C- and S-glycosylation take ...", "headings": [ { "level": 1, "title": "1. N-linked glycosylation" }, { "level": 1, "title": "2. O-linked glycosylation" }, { "level": 1, "title": "3. C-linked glycosylation" }, { "level": 1, "title": "4. S-linked glycosylation" }, { "level": 1, "title": "5. Glycation" } ], "word_count": 1047, "official_url": "https://www.uniprot.org/help/carbohyd", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/carbohyd.md", "source_path": "carbohyd.md", "sha256": "025aededc253ff7cad69d30e03fd5e802924274acf1b370414639dfb9c6841c2" }, { "slug": "catalytic_activity", "title": "Catalytic activity", "type": "help", "categories": [ "Function", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "Evidence" ], "excerpt": "This subsection of the Function section describes the catalytic activity of an enzyme, i.e. a chemical reaction that the enzyme catalyzes. Historically, UniProt has followed the recommendations of the Nomenclature Committee of the International Union of Biochemistry and Molecular Biology (NC-IUBMB) for the description of enzymatic activities, except for reac...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 297, "official_url": "https://www.uniprot.org/help/catalytic_activity", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/catalytic_activity.md", "source_path": "catalytic_activity.md", "sha256": "319f12b2e2e4a6165af8f0ff6894950967491f54e616b82918df703a79ce37c4" }, { "slug": "caution", "title": "Caution", "type": "help", "categories": [ "Sequence", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Function' section reports a variety of possible errors and/or grounds for confusion relevant to different aspects of the information provided on the protein. Note that errors concerning the protein sequence are reported in the 'Sequence caution' subsection. Examples: A6NMY6, P08874, P20285, P03974, Q06429, P26298", "headings": [], "word_count": 49, "official_url": "https://www.uniprot.org/help/caution", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/caution.md", "source_path": "caution.md", "sha256": "ffe637a0434c25fd03e35bb9e576ddc7db989d658f6dfddbdd06fd3a7a38a8f8" }, { "slug": "cds_protein_definition", "title": "What are UniProtKB's criteria for defining a CDS as a protein?", "type": "help", "categories": [ "UniProtKB", "Sequence", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "What are the criteria for defining a CDS as a real protein, i.e. for inclusion in UniProtKB? Most protein sequences are derived from translations of CoDing Sequence (CDS) derived from gene predictions. A CoDing Sequence (CDS) is a region of DNA or RNA whose sequence determines the sequence of amino acids in a protein. It should not be mixed up with an Open R...", "headings": [ { "level": 1, "title": "What are the criteria for defining a CDS as a real protein, i.e. for inclusion in UniProtKB?" }, { "level": 1, "title": "What are UniProtKB's criteria for defining a CDS as 'not a real protein'?" }, { "level": 1, "title": "See also" } ], "word_count": 390, "official_url": "https://www.uniprot.org/help/cds_protein_definition", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/cds_protein_definition.md", "source_path": "cds_protein_definition.md", "sha256": "bac340278a5d7a86895ce276e10423fb94173eff7c1353298c91106665b5d80f" }, { "slug": "chain", "title": "Chain", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Taxonomy" ], "excerpt": "This subsection of the 'PTM / Processing' section describes the extent of a polypeptide chain in the mature protein following processing or proteolytic cleavage. The processing events that may contribute to the formation of a mature chain are described in the 'Initiator methionine', 'Propeptide', 'Signal' and 'Transit peptide' subsections. The 'description' ...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 164, "official_url": "https://www.uniprot.org/help/chain", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/chain.md", "source_path": "chain.md", "sha256": "d4def268d18da0fd68df6401f4636d1dcc7cf93e93113a2a9e9273d016d99b66" }, { "slug": "changes", "title": "Format changes", "type": "help", "categories": [ "Release", "Technical", "help" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "UniProt data is released every eight weeks. Follow us on LinkedIn or X (@uniprot), or check the following pages regularly: Recent changes (included in News archive) Forthcoming changes", "headings": [], "word_count": 28, "official_url": "https://www.uniprot.org/help/changes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/changes.md", "source_path": "changes.md", "sha256": "dbf186c827704c4984ccaa734e80dd5b4a57925c4f00df01c29571ef746b4870" }, { "slug": "checksum", "title": "Checksum", "type": "help", "categories": [ "manual", "Technical" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "The checksum is a form of redundancy check that is calculated from the sequence. It is useful for tracking sequence updates. It should be noted that while, in theory, two different sequences could have the same checksum value, the likelihood that this would happen is extremely low. However UniProtKB may contain entries with identical sequences in case of mul...", "headings": [], "word_count": 156, "official_url": "https://www.uniprot.org/help/checksum", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/checksum.md", "source_path": "checksum.md", "sha256": "b0313aaa85812dc2b6385dc432469074d0ce2e2c0efe9f50d483cfb0e887f632" }, { "slug": "chemical_data_search", "title": "How can I search UniProt for chemical or reaction data?", "type": "help", "categories": [ "Text_search", "Function", "UniProtKB", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Evidence", "Structure" ], "excerpt": "Table of contents Search for small molecules Search with name or identifier Chemical structure search with InChIKey Search for catalytic activity and reaction data Video tutorial Search for small molecules UniProt has standardized annotations that involve small molecules with the ChEBI (Chemical Entities of Biological Interest) ontology to provide high quali...", "headings": [ { "level": 1, "title": "Search for small molecules" }, { "level": 2, "title": "Search with name or identifier" }, { "level": 2, "title": "Chemical structure search with InChIKey" }, { "level": 1, "title": "Search for catalytic activity and reaction data" } ], "word_count": 709, "official_url": "https://www.uniprot.org/help/chemical_data_search", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/chemical_data_search.md", "source_path": "chemical_data_search.md", "sha256": "dd570da0a446aa34736b21ab7394c8479523a9109db57d7146f1faae98e08aa3" }, { "slug": "Chordata", "title": "Chordata protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence", "PTM", "Variant", "Taxonomy" ], "excerpt": "The Chordata protein annotation project focuses on the manual annotation of chordata-specific proteins as well as those that are widely conserved. The aim of this project is twofold: 1. to keep the existing human entries up-to-date and 2. to broaden the manual annotation to other vertebrate species, especially model organisms, including great apes, cow, mous...", "headings": [ { "level": 1, "title": "Update of the human proteome" }, { "level": 1, "title": "Annotation of other mammalian and chordata proteins" } ], "word_count": 437, "official_url": "https://www.uniprot.org/help/Chordata", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Chordata.md", "source_path": "Chordata.md", "sha256": "39d0d20da708a419f0f6f84422f90bf1a3666dfe5513d5a6ffa106c72de8ab33" }, { "slug": "cofactor", "title": "Cofactor", "type": "help", "categories": [ "Function", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the 'Function' section provides information relevant to cofactors. A cofactor is any non-protein substance required for a protein to be catalytically active. Some cofactors are inorganic, such as the metal atoms zinc, iron, and copper in various oxidation states. Others, such as most vitamins, are organic. Cofactors are generally either bo...", "headings": [], "word_count": 415, "official_url": "https://www.uniprot.org/help/cofactor", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/cofactor.md", "source_path": "cofactor.md", "sha256": "0ef6d5f54045b25e1280e0869b625f1facde735e146caeadee6f05eb447f81bd" }, { "slug": "coiled", "title": "Coiled coil", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "This subsection of the 'Family and domains' section denotes the positions of regions of coiled coil within the protein. Coiled coils are built by two or more alpha-helices that wind around each other to form a supercoil. There can be two, three or four helices in the bundle and they might either run in the same (parallel) or in the opposite (antiparallel) di...", "headings": [ { "level": 1, "title": "Coiled coils and Leucine-zippers" } ], "word_count": 384, "official_url": "https://www.uniprot.org/help/coiled", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/coiled.md", "source_path": "coiled.md", "sha256": "66063335038d04273693a4a92206f6fa0ca63717e4173c53035d504a5f43de56" }, { "slug": "color-printing", "title": "Printing an alignment in color", "type": "help", "categories": [ "Website", "Technical", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Sequence tools" ], "excerpt": "To print a sequence alignment from an Align or Blast job result in color, you need to change the print settings of your browser. Note that specific details may vary between different browser and operating system versions. Firefox: Turn on the Print Background Colors option 1. Select File / Print in the normal way. 2. In the Print box, look for the subheading...", "headings": [], "word_count": 142, "official_url": "https://www.uniprot.org/help/color-printing", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/color-printing.md", "source_path": "color-printing.md", "sha256": "6ead794e79cf8f0859c6c952d81ccfa9d026056675e3ac76668ee964392b8a1e" }, { "slug": "compbias", "title": "Compositional bias", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the 'Family and Domains' section describes the position of regions of compositional bias within the protein and the particular type of amino acids that are over-represented within those regions. Regions of compositional bias are predicted by the MobiDB-lite method. These computationally generated annotations are tagged with the evidence co...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 123, "official_url": "https://www.uniprot.org/help/compbias", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/compbias.md", "source_path": "compbias.md", "sha256": "5c230e7925252c5e1ff0dcbd24910b4ede36c9fe890c2053e13f4ae7b4718be9" }, { "slug": "complete_go_annotation", "title": "What is the difference between the GO annotation included in the UniProtKB entry view, and the information accessible via the link \"Complete set of GO annotations\"?", "type": "help", "categories": [ "UniProtKB", "Ontology", "Release", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "Evidence" ], "excerpt": "GO annotations are displayed in the Function and Subcellular location sections of UniProtKB entries. Annotation filtering is applied here, as GO is just one type of information that a UniProtKB entry displays and some well-characterized proteins can have many GO annotations. Therefore annotated terms are displayed in the UniProtKB entry based on their granul...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 215, "official_url": "https://www.uniprot.org/help/complete_go_annotation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/complete_go_annotation.md", "source_path": "complete_go_annotation.md", "sha256": "e3e56d874fdbbadcee1a21f3bf417fae6eecd9f9472764bf7d9341820e3765f9" }, { "slug": "complex_viewer", "title": "Complex Viewer", "type": "help", "categories": [ "Interaction", "manual" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Download" ], "excerpt": "The Complex Viewer visualizes protein complexes expertly curated by the Complex Portal, an encyclopaedic resource of macromolecular complexes. The Viewer allows the user to study the internal topology and stoichiometry of a complex, when this is known, and clicking on a node enables the visualization of any recognized binding domains. When a protein is found...", "headings": [ { "level": 1, "title": "See also:" } ], "word_count": 149, "official_url": "https://www.uniprot.org/help/complex_viewer", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/complex_viewer.md", "source_path": "complex_viewer.md", "sha256": "7543e4a40165b191b53aa5dd7bc6283d630c9236666349b964646e0a16be4994" }, { "slug": "compression", "title": "Compression", "type": "help", "categories": [ "Programmatic_access", "Website", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API" ], "excerpt": "Data compression refers to the use of algorithms in order to reduce the size of a file. In UniProt, we offer on most downloads the ability to get compressed files in order to speed up its download time and reduce network usage. It also allows to have a smaller file on disk in case it needs to be exchanged or moved (through email or USB drive) before processi...", "headings": [], "word_count": 248, "official_url": "https://www.uniprot.org/help/compression", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/compression.md", "source_path": "compression.md", "sha256": "bd6f831a6dd04f0fd67241964f20b29442b4953ade01b2f26108d25a35513d18" }, { "slug": "conflict", "title": "Sequence conflict", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Taxonomy" ], "excerpt": "This subsection of the 'Sequence' section reports difference(s) between the canonical sequence (displayed by default in the entry) and the different sequence submissions merged in the entry. These various submissions may originate from different sequencing projects, different types of experiments, or different biological samples. Sequence conflicts are usual...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 276, "official_url": "https://www.uniprot.org/help/conflict", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/conflict.md", "source_path": "conflict.md", "sha256": "ab49492285d0ec27c9ab0d476db2948dcee1e20227dc441d28c58bae758642c7" }, { "slug": "controlled_vocabulary", "title": "Controlled vocabulary", "type": "help", "categories": [ "Controlled_vocabulary", "Ontology", "Biocuration", "Nomenclature", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Variant", "Taxonomy" ], "excerpt": "Journals (citations/publications) The Controlled vocabulary of journals lists the journal abbreviations used in UniProtKB/Swiss-Prot. The abbreviations are those proposed by the ISO (International Organization for Standardization) and they generally correspond to those used by the National Library of Medicine (NLM) in PubMed. UniProtKB/Swiss-Prot document: C...", "headings": [ { "level": 1, "title": "Journals (citations/publications)" }, { "level": 1, "title": "Keywords" }, { "level": 1, "title": "Subcellular locations" }, { "level": 1, "title": "Pathways" }, { "level": 1, "title": "Plasmids" }, { "level": 1, "title": "Post-translational modifications" }, { "level": 1, "title": "Taxonomy" }, { "level": 2, "title": "Species" }, { "level": 2, "title": "Strains" }, { "level": 1, "title": "Tissues" }, { "level": 1, "title": "Human diseases" }, { "level": 1, "title": "Extracellular domains" } ], "word_count": 640, "official_url": "https://www.uniprot.org/help/controlled_vocabulary", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/controlled_vocabulary.md", "source_path": "controlled_vocabulary.md", "sha256": "efddab60dab2d649b1ff7751dd46fb1b787fa8b933fe2571c8c1bdbf60e287f4" }, { "slug": "copyright", "title": "What is UniProt's policy regarding copyright and database distribution?", "type": "help", "categories": [ "UniProtKB", "UniParc", "UniRef", "About_UniProt", "faq" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "We have chosen to apply a \"Creative Commons\" License to all copyrightable parts of our databases. Please refer to our License & disclaimer documentation.", "headings": [], "word_count": 23, "official_url": "https://www.uniprot.org/help/copyright", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/copyright.md", "source_path": "copyright.md", "sha256": "a9a5d22df7367ac3b887b4cadbfec65ecd99aaaf9d105098f5ca54c5c96523c7" }, { "slug": "courses", "title": "Course and seminar announcements", "type": "help", "categories": [ "Outreach", "About_UniProt", "help" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "Training provided by UniProt Consortium members European Institute of Bioinformatics (EBI) training Protein Information Resource (PIR) training SIB Swiss Institute of Bioinformatics training", "headings": [ { "level": 1, "title": "Training provided by UniProt Consortium members" } ], "word_count": 23, "official_url": "https://www.uniprot.org/help/courses", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/courses.md", "source_path": "courses.md", "sha256": "55df125ef1fdad9690a11b2e96243609a9915be7321393233ff0a8f46879ab57" }, { "slug": "creation_date", "title": "When was sequence Xxxx entered in UniProtKB/Swiss-Prot?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Text_search", "Release", "Entry_information", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search" ], "excerpt": "When was sequence Xxxx published? When was sequence Xxxx submitted? The answer to these questions is dependent on what you really want this information for! If it is for legal reasons, this is a non-issue: most sequence data is NOT directly deposited in UniProtKB/Swiss-Prot, but originates from translation of a DNA sequence entry which has been itself deposi...", "headings": [ { "level": 1, "title": "When was sequence Xxxx published? When was sequence Xxxx submitted?" }, { "level": 2, "title": "Entry complete history" }, { "level": 1, "title": "See also" } ], "word_count": 412, "official_url": "https://www.uniprot.org/help/creation_date", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/creation_date.md", "source_path": "creation_date.md", "sha256": "3bd85ea172b890f5868738f5a0fe14b83eb4edcce33fcf6e3b3053dfc4879306" }, { "slug": "cross-references_in_uniprotkb", "title": "Cross-references in UniProtKB", "type": "help", "categories": [ "Cross-references", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Taxonomy" ], "excerpt": "The cross-references section of UniProtKB entries displays explicit and implicit links to databases such as nucleotide sequence databases, model organism databases and genomics and proteomics resources. A single entry can have cross-references to several dozen different databases and have several hundred individual links. UniProt web page: Cross-referenced d...", "headings": [], "word_count": 68, "official_url": "https://www.uniprot.org/help/cross-references_in_uniprotkb", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/cross-references_in_uniprotkb.md", "source_path": "cross-references_in_uniprotkb.md", "sha256": "87282f6d5b76c0cd3a29ab57d3b2f09cb9df98a7985e708db91154c862569afb" }, { "slug": "cross_references_section", "title": "Cross-references section", "type": "help", "categories": [ "Cross-references", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "PTM", "Structure", "Taxonomy" ], "excerpt": "This section is used to point to information related to entries and found in data collections other than UniProtKB. The databases to which UniProtKB is cross-referenced can be listed and searched in 'Cross-referenced databases'. Each database is described by its name and abbreviation and a link to its web server is provided, as well as literature references ...", "headings": [ { "level": 1, "title": "List of categories of the databases cross-referenced in UniProtKB" }, { "level": 1, "title": "Cross-references to 'Sequence databases'" }, { "level": 1, "title": "Related documents" } ], "word_count": 357, "official_url": "https://www.uniprot.org/help/cross_references_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/cross_references_section.md", "source_path": "cross_references_section.md", "sha256": "fdc915ab66a032da22262467aa2dcba16e66cdce15b01a08d6641ecb831b68dd" }, { "slug": "crosslnk", "title": "Cross-link", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the PTM / Processing section describes covalent linkages of various types formed between two proteins (interchain cross-links) or between two parts of the same protein (intrachain cross-links), except the disulfide bonds that are annotated in the 'Disulfide bond' subsection. Interchain cross-links are involved in the formation of covalentl...", "headings": [ { "level": 1, "title": "1. Intrachain cross-links" }, { "level": 1, "title": "2. Interchain cross-links" }, { "level": 2, "title": "a. Cross-link between homodimers" }, { "level": 2, "title": "b. Cross-links between two chains or peptides from the same protein precursor" }, { "level": 1, "title": "3. Other common cross-links" }, { "level": 2, "title": "a. Ubiquitin and Ubiquitin-like conjugation" }, { "level": 3, "title": "Ubiquitination" }, { "level": 3, "title": "Sumoylation" }, { "level": 3, "title": "Atg12 conjugation" }, { "level": 3, "title": "Neddylation" }, { "level": 2, "title": "b. Transglutamination" }, { "level": 2, "title": "c. Thioether bond" }, { "level": 2, "title": "d. Thioester bond" }, { "level": 2, "title": "e. Special cases" } ], "word_count": 759, "official_url": "https://www.uniprot.org/help/crosslnk", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/crosslnk.md", "source_path": "crosslnk.md", "sha256": "112c1852211c475e862665132784c4510573368ec0efad670bdec12ceb64a2a3" }, { "slug": "customize", "title": "Customize display options", "type": "help", "categories": [ "Website", "Text_search", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API" ], "excerpt": "Searches in the Protein Knowledgebase (UniProtKB), as well as in all other namespaces in the UniProt website, display results either in a card format, or in a tabular format. In the tabular format you can configure which columns are shown in the result table, and have your selection reflected in the download of your data in form of a tab-separated file. You ...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 364, "official_url": "https://www.uniprot.org/help/customize", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/customize.md", "source_path": "customize.md", "sha256": "f8e366932cf80bec238e2b9f660e23977e8141de45a2fa022a590c66672c5265" }, { "slug": "date_formats", "title": "What are the date formats accepted in the relevant fields of the query builder (e.g. UniProtKB entry creation or modification dates)?", "type": "help", "categories": [ "Text_search", "faq" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "The advanced query form provides a date picker to specify dates for entry creation, annotation update and sequence updates. The only date formats supported for programmatic access are 20060424 current \\ (for \"any\") \"current\" is transformed into the date of the most recent release, in the format \"YYYYMMDD\".", "headings": [], "word_count": 47, "official_url": "https://www.uniprot.org/help/date_formats", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/date_formats.md", "source_path": "date_formats.md", "sha256": "042392c6bdcc4ac3145bf651822255072cb0637d99e313fdc6cccce885b04080" }, { "slug": "deleted_accessions", "title": "Why have some UniProtKB accession numbers been deleted?", "type": "help", "categories": [ "UniProtKB", "Entry_information", "UniParc", "Release", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence", "Structure" ], "excerpt": "An accession number (AC) is assigned to each protein sequence upon inclusion into UniProtKB. Accession numbers are stable from release to release (What is the difference between an accession number (AC) and the entry name?). It can however happen that a protein sequence (and its corresponding accession number) is deleted from UniProtKB. Deleted entries in Un...", "headings": [ { "level": 1, "title": "How can I track UniProtKB accessions that have been deleted?" }, { "level": 1, "title": "Deletion reasons" }, { "level": 1, "title": "See also" } ], "word_count": 697, "official_url": "https://www.uniprot.org/help/deleted_accessions", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/deleted_accessions.md", "source_path": "deleted_accessions.md", "sha256": "e7ac2a59a11fd182b643e9af105231e7954b3b823b473d28ff6a092ea186d63d" }, { "slug": "developmental_stage", "title": "Developmental stage", "type": "help", "categories": [ "Expression", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This subsection of the 'Expression' section provides information on the expression of the gene product at various stages of a cell, tissue or organism development. By default, the information is derived from experiments at the mRNA level, unless specified 'at the protein level'. Examples: Q925Q8, P33124, Q96EP1 Note : The content of the 'Developmental stage'...", "headings": [], "word_count": 64, "official_url": "https://www.uniprot.org/help/developmental_stage", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/developmental_stage.md", "source_path": "developmental_stage.md", "sha256": "459f03bcf1e12f0b8e1c450dde6ab0dfc947e2e120f1230b45f5a1a5590e076a" }, { "slug": "difference_accession_entryname", "title": "What is the difference between an accession number (AC) and the entry name?", "type": "help", "categories": [ "UniProtKB", "Entry_information", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [], "excerpt": "An accession number (AC) is assigned to each sequence upon inclusion into UniProtKB. Accession numbers are stable from release to release. If several UniProtKB entries are merged into one, for reasons of minimizing redundancy, the accession numbers of all relevant entries are kept. Each entry has one primary AC and optional secondary ACs. The 'Entry name' (f...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 158, "official_url": "https://www.uniprot.org/help/difference_accession_entryname", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/difference_accession_entryname.md", "source_path": "difference_accession_entryname.md", "sha256": "7b5c2d1a30c26f4fdd7b0863c88aa89a79f7f60f4413693f8eaf9170f5d66658" }, { "slug": "different_protein_gene_names", "title": "Why does the UniProtKB use so many different names for the same protein?", "type": "help", "categories": [ "UniProtKB", "Nomenclature", "Names_and_taxonomy", "Biocuration", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Taxonomy" ], "excerpt": "Ambiguities regarding gene/protein names are a major problem in the literature and in the sequence databases which tend to propagate the confusion. As administrators of UniProt we feel that we can play a major role in standardization of protein nomenclature. We try to attribute a recommended name to all the proteins of UniProtKB/Swiss-Prot, following as far ...", "headings": [ { "level": 1, "title": "Protein isoform name" }, { "level": 1, "title": "See also" } ], "word_count": 351, "official_url": "https://www.uniprot.org/help/different_protein_gene_names", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/different_protein_gene_names.md", "source_path": "different_protein_gene_names.md", "sha256": "6361188e12dbbe0482311284c063a07091b2f1566b3a8c0263414a119a80cb6f" }, { "slug": "disease_phenotypes_variants_section", "title": "Disease/Phenotypes and variants section", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Download", "API", "Variant", "Taxonomy" ], "excerpt": "previously called \"pathology and biotech\" This section provides information on the disease(s), phenotype(s), and variants associated with a protein. The information is filed in different subsections, and is manually curated and maintained by UniProt. The current subsections and their content are listed below: The data in the Variant Viewer includes both manu...", "headings": [], "word_count": 209, "official_url": "https://www.uniprot.org/help/disease_phenotypes_variants_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/disease_phenotypes_variants_section.md", "source_path": "disease_phenotypes_variants_section.md", "sha256": "6be68f959dcff9c9548283fa0f02787efccbbb676086063228cb5631bf15dc04" }, { "slug": "disease_query", "title": "How can I get all the proteins involved in a given disease?", "type": "help", "categories": [ "UniProtKB", "Keywords", "Text_search", "Human", "disease_phenotypes_variants", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "Variant" ], "excerpt": "Information relevant to diseases associated with a given protein are found in the section 'Disease/Phenotypes and variants'. The information given (including the disease name) is consistent with the literature and the OMIM database. You can use three methods to search proteins associated with a given disease. 1\\) Search for proteins using the query builder :...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 289, "official_url": "https://www.uniprot.org/help/disease_query", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/disease_query.md", "source_path": "disease_query.md", "sha256": "cdd891e2c2d8c0258df2a2c5ab6a87bf65c1e10dc89704a59468c73c3301a752" }, { "slug": "disruption_phenotype", "title": "Disruption phenotype", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant", "Taxonomy" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section describes the in vivo effects caused by ablation of the gene (or one or more transcripts) coding for the protein described in the entry. This includes gene knockout and knockdown, provided experiments have been performed in the context of a whole organism or a specific tissue, and not at the si...", "headings": [], "word_count": 186, "official_url": "https://www.uniprot.org/help/disruption_phenotype", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/disruption_phenotype.md", "source_path": "disruption_phenotype.md", "sha256": "e6f3c25bc337d5257ad0461ea99744836490d0a43f02ef4af3b3878a01c4e438" }, { "slug": "disulfid", "title": "Disulfide bond", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the PTM / Processing section describes the positions of cysteine residues participating in disulfide bonds. Disulfide bond formation generally occurs in the endoplasmic reticulum by oxidation. Therefore disulfide bonds are mostly found in extracellular, secreted and periplasmic proteins, although they can also be formed in cytoplasmic prot...", "headings": [ { "level": 1, "title": "1. Intrachain disulfide bonds" }, { "level": 1, "title": "2. Interchain disulfide bonds (between homo- and heterodimers)" }, { "level": 2, "title": "a. Disulfide bonds between homodimers" }, { "level": 2, "title": "b. Disulfide bonds between 2 chains or peptides from the same protein precursor" }, { "level": 2, "title": "c. Disulfide bonds between heterodimers" }, { "level": 1, "title": "3. Redox-active centers" }, { "level": 1, "title": "4. Annotation of predicted disulfide bonds" } ], "word_count": 668, "official_url": "https://www.uniprot.org/help/disulfid", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/disulfid.md", "source_path": "disulfid.md", "sha256": "4ac34cf7534f4a6a0374af0f9bd9c247c74ab81981c2aea628c6d8735de72b7a" }, { "slug": "dna_bind", "title": "DNA binding", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the Function section specifies the position and type of each DNA-binding domain present within the protein. We annotate experimentally defined DNA-binding domains and conserved DNA-binding domains defined by the InterPro resources PROSITE, Pfam and SMART; examples include the AP2/ERF domain, the ETS domain, the Fork-Head domain, the HMG bo...", "headings": [ { "level": 1, "title": "1. Predicted DNA-binding domains" }, { "level": 2, "title": "Special types of DNA-binding domain" }, { "level": 3, "title": "a. bHLH and bZIP proteins" }, { "level": 3, "title": "b. Homeobox proteins" }, { "level": 1, "title": "2. Experimentally determined DNA-binding domains" }, { "level": 1, "title": "See also" } ], "word_count": 310, "official_url": "https://www.uniprot.org/help/dna_bind", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/dna_bind.md", "source_path": "dna_bind.md", "sha256": "7d39413d422b1b28603d554bf09bb931c2d362ed79dbdb8ce34614f79c630c96" }, { "slug": "domain", "title": "Domain", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Evidence", "Structure" ], "excerpt": "This subsection of the Family and Domains section describes the position and type of a domain, which is defined as a specific combination of secondary structures organized into a characteristic three-dimensional structure or fold. Protein domains often correspond to structural domains which are self-stabilizing and fold independently of the rest of the prote...", "headings": [ { "level": 1, "title": "Expert curation of domains in UniProtKB/Swiss-Prot" }, { "level": 1, "title": "Automatic domain annotation in UniProtKB/TrEMBL" }, { "level": 1, "title": "See also" } ], "word_count": 227, "official_url": "https://www.uniprot.org/help/domain", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/domain.md", "source_path": "domain.md", "sha256": "d8e7da76033bfeb628026a040b9bd0117ac41877a7ce6a410a2f95e4072289d6" }, { "slug": "domain_cc", "title": "Domain (non-positional annotation)", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Family and domains' section provides general information on the biological role of a domain. The term 'domain' is intended here in its wide acceptation, it may be a structural domain, a transmembrane region or a functional domain. Several domains are described in this subsection. The domains described in this subsection are generally ...", "headings": [], "word_count": 99, "official_url": "https://www.uniprot.org/help/domain_cc", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/domain_cc.md", "source_path": "domain_cc.md", "sha256": "f988a704719afa1262693515b94a377fd76c514c8544949d4be3ed538474c9c7" }, { "slug": "download_human_viruses", "title": "How can I download a list of all viruses infecting humans?", "type": "help", "categories": [ "Taxonomy", "Viruses", "Text_search", "UniProtKB", "Human", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "Download", "Taxonomy" ], "excerpt": "Using the query builder: Select Search in : Taxonomy Click Advanced to open the query builder Select Virus host from the dropdown menu Type 9606 for human Click on the search button result. Direct query by viral host using the taxonomy identifier for human (9606).", "headings": [], "word_count": 44, "official_url": "https://www.uniprot.org/help/download_human_viruses", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/download_human_viruses.md", "source_path": "download_human_viruses.md", "sha256": "843082820d7727a10e69489ff7c7303e802d9e197c70f00d5d4f499e84d68553" }, { "slug": "download_mapping", "title": "Can I download a complete mapping table between different databases?", "type": "help", "categories": [ "UniProtKB", "UniParc", "UniRef", "Download", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Download", "API", "ID mapping" ], "excerpt": "You can download the data underlying our database identifier service mapping service from https://ftp.uniprot.org/pub/databases/uniprot/currentrelease/knowledgebase/idmapping/ Additional information on the database mapping service (accessible via Retrieve/ID mapping): Retrieve/ID mapping help page How to use the database mapping service programmatically", "headings": [], "word_count": 48, "official_url": "https://www.uniprot.org/help/download_mapping", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/download_mapping.md", "source_path": "download_mapping.md", "sha256": "7206d88702d8fd2862d44a293c560b7ce3229bcdb645a91d89b37df60d1ede6f" }, { "slug": "download_subsequences", "title": "How can I download the sequences corresponding to a specified domain or region, or the sequences of mature chains or peptides, from a list of UniProt entries?", "type": "help", "categories": [ "UniProtKB", "Download", "Sequence", "Text_search", "Family_and_domains", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "FASTA", "Search", "Download", "ID mapping" ], "excerpt": "Download the sequences of all annotated disintegrin domains Run your query, e.g. to retrieve the UniProtKB entries annotated to contain disintegrin domains, (or alternatively, with a list of identifiers). Then click on \"Download\" and choose to download the results in GFF format. You can modify the GFF file as follows: Keep only the lines containing your doma...", "headings": [ { "level": 2, "title": "Download the sequences of all annotated disintegrin domains" }, { "level": 2, "title": "Download the sequences of all mature chains or peptides, e.g. cleavage products in case of viral polyprotein entries" } ], "word_count": 314, "official_url": "https://www.uniprot.org/help/download_subsequences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/download_subsequences.md", "source_path": "download_subsequences.md", "sha256": "2ea8b033cb22d0131318ae743ccb258b9f3b0535f3d05cad12e4020205c7db24" }, { "slug": "downloads", "title": "Downloads", "type": "help", "categories": [ "Download", "Release" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "FASTA", "Proteome", "Search", "Download", "API", "ID mapping", "Evidence", "Variant", "Taxonomy" ], "excerpt": "UniProt is updated roughly every eight weeks. You can download small data sets and subsets directly from this website by following the download link on any search result page. For downloading complete data sets we recommend using ftp.uniprot.org. If you are located in Europe, the Middle East or Africa, you may want to download data from our mirror site in th...", "headings": [ { "level": 1, "title": "UniProtKB" }, { "level": 1, "title": "UniRef" }, { "level": 1, "title": "UniParc" }, { "level": 1, "title": "UniProt RDF distribution" }, { "level": 1, "title": "UniProt information" }, { "level": 1, "title": "Embeddings" } ], "word_count": 257, "official_url": "https://www.uniprot.org/help/downloads", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/downloads.md", "source_path": "downloads.md", "sha256": "5bebdbea20abacadb11cd83ebfc33ba94139085e9695e6f58e40c811987588e8" }, { "slug": "Drosophila", "title": "Drosophila protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search", "Evidence", "Taxonomy" ], "excerpt": "The Drosophila protein annotation project focuses on the manual annotation of characterised D.melanogaster proteins with experimental information propagated to orthologous proteins in other Drosophila species. See: How do we manually annotate a UniProtKB entry? UniProtKB works closely with FlyBase, the database for Drosophila genetics and molecular biology, ...", "headings": [ { "level": 1, "title": "About Drosophila" } ], "word_count": 283, "official_url": "https://www.uniprot.org/help/Drosophila", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Drosophila.md", "source_path": "Drosophila.md", "sha256": "b38e9b059cdfbcfe7f32b3e571062e8767f80e72963cfba64af69db36e3b37a8" }, { "slug": "dubious_sequences", "title": "Why do we keep dubious sequences in UniProtKB? How to discard them from a protein set?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Text_search", "Protein_existence", "faq" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search", "Evidence" ], "excerpt": "About 98% of the protein sequences provided by UniProtKB come from the translations of coding sequences (CDS) submitted to the EMBL-Bank/GenBank/DDBJ nucleotide sequence resources. These CDS are either generated by the application of gene prediction programs to genomic DNA sequences or via the translation of cDNAs (see Where do the UniProtKB protein sequence...", "headings": [ { "level": 1, "title": "Important remark" }, { "level": 1, "title": "See also" } ], "word_count": 655, "official_url": "https://www.uniprot.org/help/dubious_sequences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/dubious_sequences.md", "source_path": "dubious_sequences.md", "sha256": "b7ac0ced585b5f8db1fcdc518633d116f29a7409e2117edc9e97af7060a593a7" }, { "slug": "embeddings", "title": "Protein Embeddings", "type": "help", "categories": [ "UniProtKB", "Automatic_annotation", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Download", "API", "Taxonomy" ], "excerpt": "Protein embeddings are a way to encode functional and structural properties of a protein, mostly from its sequence only, in a machine-friendly format (vector representation). Generating such embeddings is computationally expensive, but once computed they can be leveraged for different tasks, such as sequence similarity search, sequence clustering, and sequen...", "headings": [ { "level": 2, "title": "Sample code" } ], "word_count": 208, "official_url": "https://www.uniprot.org/help/embeddings", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/embeddings.md", "source_path": "embeddings.md", "sha256": "05c8cf980c3d6affad758abd6ff5a0457d50cede731b1c0f8759bdba1b93230f" }, { "slug": "encoded_in", "title": "Encoded in", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Variant", "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section indicates if the gene coding for the protein originates from the hydrogenosome, the mitochondrion, the nucleomorph, different plastids or a plasmid. The absence of this section means that the gene is located in one of the main chromosomal element(s). Examples: Hydrogenosome, Nucleomorph 6 categories exist for...", "headings": [], "word_count": 252, "official_url": "https://www.uniprot.org/help/encoded_in", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/encoded_in.md", "source_path": "encoded_in.md", "sha256": "5705d7d95b6e7c15b9eedf5fa7cbc29992529f9d73e8a2c2db3c874a7799e326" }, { "slug": "entries_since_rel_x", "title": "How can I get all green plant entries integrated in UniProtKB since release 12.0?", "type": "help", "categories": [ "UniProtKB", "Text_search", "Release", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "1. Go to the news archive and find the date of the UniProt release under consideration, e.g. Release 12.0 was published on July 24, 2007 2. Use the query builder as described below. Retrieve all green plant entries: Select Search in : Protein Knowledgebase (UniProtKB) Click Advanced to open the query builder Select Field : Taxonomy [OC] Type Viridiplantae (u...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 168, "official_url": "https://www.uniprot.org/help/entries_since_rel_x", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entries_since_rel_x.md", "source_path": "entries_since_rel_x.md", "sha256": "46fb4bdefe1dc6ce8f20539009ae68b9cd9bb6489b09ba1bfaf828c54b8c4c60" }, { "slug": "entry_count", "title": "How can I (programmatically) obtain the number of results returned by my query?", "type": "help", "categories": [ "Programmatic_access", "Text_search", "Technical", "faq" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API" ], "excerpt": "If you are accessing UniProt programmatically, using our REST API, and are just interested in the number of entries returned by your query, but not in downloading or listing all the hits, you can check the X-Total-Results response header. This returns the entry count, allowing you to count the hits without actually retrieving them. See also REST API - Access...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 63, "official_url": "https://www.uniprot.org/help/entry_count", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entry_count.md", "source_path": "entry_count.md", "sha256": "6452feffe01e555f55d98d8b6bae8f313f87cfd4c92919db1fae910cdabe8ca4" }, { "slug": "entry_history", "title": "Entry history", "type": "help", "categories": [ "Entry_information", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Evidence" ], "excerpt": "This subsection of the 'Entry information' section shows the date of integration of the entry into UniProtKB, the date of the last sequence update and the date of the last annotation modification ('Last modified'). The version number for both the entry and the canonical sequence are also displayed. Example: P55209 Sequence updates are always accompanied by m...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 195, "official_url": "https://www.uniprot.org/help/entry_history", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entry_history.md", "source_path": "entry_history.md", "sha256": "fd42fc6cd2dc9c1f0efaed5f46f9db845325f4b7b25dae56a19eb202c0d6de94" }, { "slug": "entry_information_section", "title": "Entry information section", "type": "help", "categories": [ "Entry_information", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "Taxonomy" ], "excerpt": "This section provides general information on the entry. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Entry name | Mnemonic identifier for a UniProtKB entry | | Accession | Provides a stable way of identifying UniProtKB entries | | Entry history | Dates of creation an...", "headings": [], "word_count": 83, "official_url": "https://www.uniprot.org/help/entry_information_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entry_information_section.md", "source_path": "entry_information_section.md", "sha256": "8367e2b856dce731f7261c00f7c0e6955af5fc9a63de41fd93b2953e8b98db3d" }, { "slug": "entry_name", "title": "Entry name", "type": "help", "categories": [ "Entry_information", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Evidence", "Taxonomy" ], "excerpt": "This subsection of the 'Entry information' section provides a mnemonic identifier for a UniProtKB entry, but it is not a stable identifier. Each reviewed entry is assigned a unique entry name upon integration into UniProtKB/Swiss-Prot. UniProtKB/Swiss-Prot entry name The UniProtKB/Swiss-Prot entry name consists of up to 11 uppercase alphanumeric characters w...", "headings": [ { "level": 1, "title": "UniProtKB/Swiss-Prot entry name" }, { "level": 1, "title": "UniProtKB/TrEMBL entry names" }, { "level": 2, "title": "Important tip" }, { "level": 1, "title": "Related documents" } ], "word_count": 668, "official_url": "https://www.uniprot.org/help/entry_name", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entry_name.md", "source_path": "entry_name.md", "sha256": "e91e7fb41572e97fca96a4ffcf86f12f12351a9cc55c4a386b4d1af7d8c0be0b" }, { "slug": "entry_status", "title": "Entry status", "type": "help", "categories": [ "Entry_information", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the 'Entry information' section indicates whether the entry has been manually annotated and reviewed by UniProtKB curators or not, in other words, if the entry belongs to the Swiss-Prot section of UniProtKB (reviewed) or to the computer-annotated TrEMBL section (unreviewed). UniProtKB/Swiss-Prot entries are tagged with a yellow reviewed ic...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 77, "official_url": "https://www.uniprot.org/help/entry_status", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/entry_status.md", "source_path": "entry_status.md", "sha256": "b78c698297b0b9189d9c652368b065864093dc6d386493b92480fee40ce37bfd" }, { "slug": "enzyme_regulation", "title": "Enzyme regulation - renamed to 'Activity regulation", "type": "help", "categories": [ "manual" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [], "excerpt": "In UniProtKB entries, the topic 'Enzyme regulation' was used to display information about factors that regulate the activity of enzymes, but also of transporters and microbial transcription factors. To clarify the situation, we have renamed this topic to Activity regulation.", "headings": [], "word_count": 40, "official_url": "https://www.uniprot.org/help/enzyme_regulation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/enzyme_regulation.md", "source_path": "enzyme_regulation.md", "sha256": "7bc1b7ebc739423e525140b130a479886e5d8dd6dc07dbd17b67a16950ed99aa" }, { "slug": "epitopes", "title": "Epitopes", "type": "help", "categories": [ "manual" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Download", "API", "Evidence", "Variant" ], "excerpt": "Epitopes are specific, localized regions on an antigen that are recognized by immune cells such as B cells and T cells, helping to facilitate the immune response. 1. UniProt curated epitopes Epitope regions are expertly curated from experimental evidence found in published literature and annotated on the protein sequence as Regions. The annotation defines th...", "headings": [ { "level": 1, "title": "1. UniProt curated epitopes" }, { "level": 1, "title": "2. Epitopes from IEDB" } ], "word_count": 231, "official_url": "https://www.uniprot.org/help/epitopes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/epitopes.md", "source_path": "epitopes.md", "sha256": "95b9226ee1ad0f2a9fc1e828e34d56b25054ad00213aca539f3c75c1ca41e4af" }, { "slug": "evidence_in_swissprot", "title": "Why don't all UniProtKB/Swiss-Prot annotations have evidence?", "type": "help", "categories": [ "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "Evidence", "Variant" ], "excerpt": "The annotations which are missing evidence were created before we started to manually curate information with evidence attribution in UniProtKB/Swiss-Prot. The manual attribution of evidence to these existing annotations was not possible due to the huge amount of existing data. Therefore we wrote a program to automatically add the evidence based on how prove...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 208, "official_url": "https://www.uniprot.org/help/evidence_in_swissprot", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/evidence_in_swissprot.md", "source_path": "evidence_in_swissprot.md", "sha256": "12748492c354dd6a5b3590d7a8dbd2e3682d8eb655f1de7e4a6f1a2e4a0c0302" }, { "slug": "evidence_table", "title": "How can I query UniProtKB annotations by evidence?", "type": "help", "categories": [ "UniProtKB", "Text_search", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Evidence", "Structure", "Taxonomy" ], "excerpt": "The table below summarizes the different evidence types used in UniProtKB annotation, and details how they are labeled in the Advanced search menu and in the UniProtKB entry view. | Advanced search | ECO\\0000XXX | Source | Entry view labels | Notes | Experimental | Manual | Automatic | | Manual assertions (in UniProtKB/Swiss-Prot) | | | | | | | | | Experimen...", "headings": [], "word_count": 260, "official_url": "https://www.uniprot.org/help/evidence_table", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/evidence_table.md", "source_path": "evidence_table.md", "sha256": "a7ebb5b51e93b40a699e59f1429da4605b52d3c8758d276a30bf0993f1e56376" }, { "slug": "evidences", "title": "Evidence", "type": "help", "categories": [ "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence" ], "excerpt": "Table of contents Introduction Evidence types used for UniProtKB annotations Evidence types used for GO annotations Related documents Introduction Most information in UniProtKB has one or several \"evidence tags\" which describe the source of the information, e.g. an experiment that has been published in the scientific literature, an orthologous protein, a rec...", "headings": [ { "level": 1, "title": "Table of contents" }, { "level": 1, "title": "Introduction" }, { "level": 1, "title": "Evidence types used for UniProtKB annotations" }, { "level": 2, "title": "Evidence used only in manual assertions" }, { "level": 2, "title": "Evidence used in manual and automatic assertions" }, { "level": 1, "title": "Evidence types used for GO annotations" }, { "level": 2, "title": "Experimental evidence codes" }, { "level": 2, "title": "Experimental 'high throughput' evidence codes" }, { "level": 2, "title": "Phylogenetically-inferred annotations" }, { "level": 2, "title": "Computational analysis evidence codes" }, { "level": 2, "title": "Author statement evidence codes" }, { "level": 2, "title": "Curator statement evidence codes" }, { "level": 2, "title": "Electronic annotation evidence code" }, { "level": 1, "title": "Related documents" } ], "word_count": 1939, "official_url": "https://www.uniprot.org/help/evidences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/evidences.md", "source_path": "evidences.md", "sha256": "4a8270457e7dff34ea1b8afce625edc7f527e5c7c2e2623e0638a2ef6652a813" }, { "slug": "explore_proteomes", "title": "Explore Proteomes", "type": "help", "categories": [ "Get_started", "Proteomes" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Download", "Taxonomy" ], "excerpt": "A proteome is the set of proteins believed to be expressed by an organism. The majority of the UniProt proteomes are based on the translation of a genome assembly, and normally include sequences that derive from extra-chromosomal elements such as plasmids, or organellar genomes in organisms where these are present. The UniProt proteomes resource consists of ...", "headings": [], "word_count": 315, "official_url": "https://www.uniprot.org/help/explore_proteomes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/explore_proteomes.md", "source_path": "explore_proteomes.md", "sha256": "820512b1d8192e2e2e94e6c8b643f04efd23c5f090cc4ced65f79291da12dfbd" }, { "slug": "explore_sequence_archive", "title": "Explore the sequence archive UniParc", "type": "help", "categories": [ "Get_started", "UniParc" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Download", "Sequence tools", "Taxonomy" ], "excerpt": "UniParc is a comprehensive and non-redundant database that contains most of the publicly available protein sequences in the world. UniParc stores each unique sequence only once, giving it a stable and unique identifier (UPI). You can access UniParc from the UniProt homepage or by selecting it from the dropdown in front of the search bar and entering your sea...", "headings": [], "word_count": 262, "official_url": "https://www.uniprot.org/help/explore_sequence_archive", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/explore_sequence_archive.md", "source_path": "explore_sequence_archive.md", "sha256": "57e1feacb648bc64a74ce31ba0130d8ba4c2a3b3ac029e3a62d6c24dee85b056" }, { "slug": "explore_uniprotkb_entry", "title": "Explore UniProtKB entry", "type": "help", "categories": [ "Get_started", "UniProtKB" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence", "Variant", "Taxonomy" ], "excerpt": "Key identifying information UniProtKB is a protein database that consists of individual entries, each of which provides detailed information about a particular protein. The top of each protein entry page provides key identifying information about the protein and the status of the entry. Firstly the unique UniProtKB accession number, which is a stable identif...", "headings": [ { "level": 1, "title": "Key identifying information" }, { "level": 1, "title": "Entry tabs" }, { "level": 2, "title": "Entry" }, { "level": 2, "title": "Variant viewer" }, { "level": 2, "title": "Feature viewer" }, { "level": 2, "title": "Genomic coordinates" }, { "level": 2, "title": "Publications" }, { "level": 2, "title": "External links" }, { "level": 2, "title": "History" }, { "level": 1, "title": "Tools and Feedback Links" }, { "level": 1, "title": "Further UniProtKB protein entry help" } ], "word_count": 791, "official_url": "https://www.uniprot.org/help/explore_uniprotkb_entry", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/explore_uniprotkb_entry.md", "source_path": "explore_uniprotkb_entry.md", "sha256": "1c65229b8a244a572660a001a44ed5f8f8f6f37eb96e477a07a29f23d75dbf5b" }, { "slug": "expression_section", "title": "Expression section", "type": "help", "categories": [ "Expression", "manual" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This section provides information on the expression of a gene at the mRNA or protein level in cells or in tissues of multicellular organisms. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Tissue specificity | Description of the expression of a gene in different tissue...", "headings": [], "word_count": 115, "official_url": "https://www.uniprot.org/help/expression_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/expression_section.md", "source_path": "expression_section.md", "sha256": "94eb94e1411cdfad652924a1bf10b8110531d2c207d26cf0641f059deb4ae38a" }, { "slug": "extinct_organisms", "title": "Protein sequences from extinct organisms", "type": "help", "categories": [ "UniProtKB", "Taxonomy", "faq" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [ "Taxonomy" ], "excerpt": "All the protein sequences from extinct organisms are associated with the keyword 'Extinct organism protein'. You can find additional information on extinct organisms that are represented with DNA sequence data at GenBank.", "headings": [], "word_count": 32, "official_url": "https://www.uniprot.org/help/extinct_organisms", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/extinct_organisms.md", "source_path": "extinct_organisms.md", "sha256": "00b21656039740c709ea2892f24628c61e2f1aa89b151d182555c7104669923d" }, { "slug": "family_and_domains_section", "title": "Family and Domains section", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [ "API" ], "excerpt": "This section provides information on sequence similarities with other proteins and the domain(s) present in a protein. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Domain | Denotes the position and type of each modular protein domain | | Repeat | Denotes the position...", "headings": [], "word_count": 162, "official_url": "https://www.uniprot.org/help/family_and_domains_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/family_and_domains_section.md", "source_path": "family_and_domains_section.md", "sha256": "693647f1efb9509e0309182123dfda86e49b91497e132709ae22265e4ff50029" }, { "slug": "family_membership", "title": "How is protein family membership assigned in UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Family_and_domains", "Cross-references", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search" ], "excerpt": "How is protein family membership assigned in UniProtKB? The task of assigning proteins to families makes use of a range of sources including protein family databases, sequence analysis tools, scientific literature and sequence similarity search tools. InterPro integrates predictive signatures representing protein domains, families and functional sites into a...", "headings": [ { "level": 1, "title": "How is protein family membership assigned in UniProtKB?" }, { "level": 1, "title": "See also" } ], "word_count": 191, "official_url": "https://www.uniprot.org/help/family_membership", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/family_membership.md", "source_path": "family_membership.md", "sha256": "0a8c1d8cd003bcad31dc7bdccb25f56e9e630939d2aded03d01d56f1006e8c42" }, { "slug": "fasta-headers", "title": "FASTA headers", "type": "help", "categories": [ "Technical", "Sequence", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Evidence", "Taxonomy" ], "excerpt": "The following is a description of FASTA headers for UniProtKB (including alternative isoforms), UniRef, UniParc (including proteomes) and archived UniProtKB versions. NCBI's program formatdb (in particular its -o option) is compatible with the UniProtKB FASTA headers. Note that in the document below square brackets [ ] indicate optional fields. Table of cont...", "headings": [ { "level": 1, "title": "UniProtKB" }, { "level": 2, "title": "UniProtKB alternative isoforms" }, { "level": 1, "title": "UniRef" }, { "level": 1, "title": "UniParc" }, { "level": 2, "title": "UniParc proteomes" }, { "level": 1, "title": "Archived UniProtKB sequence versions" }, { "level": 1, "title": "Pan Proteome FASTA" } ], "word_count": 979, "official_url": "https://www.uniprot.org/help/fasta-headers", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/fasta-headers.md", "source_path": "fasta-headers.md", "sha256": "33000345632ce20e83853aed54cc3d67c2335f5f646d5b03109028153d129eb7" }, { "slug": "feature_viewer", "title": "Feature viewer", "type": "help", "categories": [ "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Download", "PTM", "Structure", "Variant" ], "excerpt": "The feature viewer is a comprehensive graphical representation of protein sequence features that are mapped to a protein's amino acid sequence. It includes a range of data from multiple sources such as domains, sites, post-translational modifications, mutagenesis, proteomics-derived peptides, antigenic sequences and natural variants. Data is composed of a mi...", "headings": [ { "level": 2, "title": "Navigating the feature viewer" }, { "level": 2, "title": "Where to find the feature viewer" }, { "level": 2, "title": "How to download data found in the feature viewer" }, { "level": 2, "title": "Feature viewer tracks and associated help pages" } ], "word_count": 557, "official_url": "https://www.uniprot.org/help/feature_viewer", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/feature_viewer.md", "source_path": "feature_viewer.md", "sha256": "04f8c38d0001678dcbfb567de06aaa04ad6fa5d71c76e452605c5259abdc030d" }, { "slug": "file-generation-download", "title": "File Generation & Download", "type": "help", "categories": [ "UniProtKB", "help", "Download", "async_download", "file_generation" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "Download", "API", "ID mapping", "Sequence tools" ], "excerpt": "File Generation for Downloading Large Files - BETA Feature When users download data from UniProtKB, it is typically treated as a \"normal\" download, which is offered as a stream. For larger files (currently query results with more than 10 million entries), a separate file must be generated for download. Much like BLAST or ID mapping services at UniProt, this ...", "headings": [ { "level": 1, "title": "File Generation for Downloading Large Files - BETA Feature" }, { "level": 2, "title": "What are the advantages?" }, { "level": 2, "title": "When does UniProt trigger File Generation?" }, { "level": 2, "title": "What are the different file formats and compression?" }, { "level": 2, "title": "How can I unzip the downloaded files?" } ], "word_count": 372, "official_url": "https://www.uniprot.org/help/file-generation-download", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/file-generation-download.md", "source_path": "file-generation-download.md", "sha256": "d058c21dbf2bcd2b65965ce7c8baef3f9034395dccc103831bf2c0352dee5f37" }, { "slug": "filter_options", "title": "UniProtKB filter options", "type": "help", "categories": [ "UniProtKB", "Text_search", "Website", "help" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "A search result page is subdivided into a filter panel on the left, and the actual result table on the right, occupying the majority of the screen space. You can use the filter panel to filter your search results in UniProtKB by reviewed/unreviewed status, or by organism, or you can restrict your search terms to certain query fields. Organism filters Under t...", "headings": [ { "level": 1, "title": "Organism filters" }, { "level": 2, "title": "Notes" } ], "word_count": 309, "official_url": "https://www.uniprot.org/help/filter_options", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/filter_options.md", "source_path": "filter_options.md", "sha256": "94238a57c6aa8e1a7496a03c24d03244803febe55e7f517d718605ff7e62e43e" }, { "slug": "find_protein_clusters", "title": "Find protein clusters", "type": "help", "categories": [ "Get_started", "UniRef" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "Download", "Sequence tools", "Taxonomy" ], "excerpt": "UniRef provides clustered sets of sequences from UniProtKB, including isoforms and selected UniParc records. (UniRef offers complete coverage of the sequence space at three resolutions: UniRef100 database combines identical sequences from any organism into a single UniRef entry, displaying the sequence of a representative protein, the accession numbers of al...", "headings": [], "word_count": 298, "official_url": "https://www.uniprot.org/help/find_protein_clusters", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/find_protein_clusters.md", "source_path": "find_protein_clusters.md", "sha256": "2353b42a57ba3f0f6a889b346b0966e52768d57533bf8131ea42801f085e1e8e" }, { "slug": "find_your_protein", "title": "Find your protein", "type": "help", "categories": [ "Get_started", "UniProtKB" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API", "Sequence tools", "Evidence", "Taxonomy" ], "excerpt": "The UniProt Knowledgebase (UniProtKB) is the central hub for the collection of functional information on proteins, with accurate, consistent and rich annotation. UniProtKB consists of two sections, one containing manually annotated reviewed/SwissProt proteins entries and the other containing computationally annotated unreviewed/TrEMBL protein entries. UniPro...", "headings": [ { "level": 1, "title": "Finding proteins using the website search" }, { "level": 1, "title": "Finding proteins using BLAST search" }, { "level": 1, "title": "Finding proteins programmatically" } ], "word_count": 547, "official_url": "https://www.uniprot.org/help/find_your_protein", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/find_your_protein.md", "source_path": "find_your_protein.md", "sha256": "52b55ddeb69f83c32705889f1bd435d8ddd905c2ed0253a1ab0089eb83b6be2c" }, { "slug": "function", "title": "Function", "type": "help", "categories": [ "Function", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the Function describes the function(s) of a protein. When a protein is a precursor of different chains/peptides having different functions, we specify the role of each peptide in separate paragraphs. Examples: Q8MMJ7, Q9UBU3 The same holds true for isoform-specific functions. Example: P16157 Multifunctional enzymes should have only one 'Fu...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 136, "official_url": "https://www.uniprot.org/help/function", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/function.md", "source_path": "function.md", "sha256": "02e7108a10fd0e097f41bffb6c46f9249c0debe9a6e451a01730edc79c514935" }, { "slug": "function_section", "title": "Function section", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "API" ], "excerpt": "This section provides any useful information about the protein, mostly biological knowledge. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Function | General function(s) of a protein | | Miscellaneous | Any relevant information that doesn't fit in any other defined se...", "headings": [], "word_count": 249, "official_url": "https://www.uniprot.org/help/function_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/function_section.md", "source_path": "function_section.md", "sha256": "cec8fa8d58627bd7af226b50421bd35fe658f47f9a6ff61687702d27095b7f12" }, { "slug": "fungal_protein_annotation_project", "title": "Fungal protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search", "API", "Evidence" ], "excerpt": "The Fungal protein annotation project focuses on the manual annotation of fungi-specific proteins and protein families. See: How do we manually annotate a UniProtKB entry? The fungal kingdom Species of the fungal kingdom occupy almost every ecological niche, and include important human, animal and plant pathogens. They are of tremendous industrial importance...", "headings": [ { "level": 1, "title": "The fungal kingdom" }, { "level": 1, "title": "Priorities" }, { "level": 1, "title": "Annotation propagation" }, { "level": 1, "title": "About yeasts" }, { "level": 2, "title": "Budding yeast" }, { "level": 2, "title": "Fission yeast" } ], "word_count": 689, "official_url": "https://www.uniprot.org/help/fungal_protein_annotation_project", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/fungal_protein_annotation_project.md", "source_path": "fungal_protein_annotation_project.md", "sha256": "bab827b77ae13aa8bbe08244a5b6b6c13ee9a6d541665e3035689e116824e7fb" }, { "slug": "fungi", "title": "Fungi", "type": "help", "categories": [ "Fungi", "Biocuration", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence" ], "excerpt": "Candida albicans This documents lists all the Candida albicans SC5314 entries present in UniProtKB/Swiss-Prot, together with their gene names. UniProtKB/Swiss-Prot document: Candida albicans: entries and gene names UniProt web page: Fungal protein annotation program Schizosaccharomyces pombe This documents lists all the Schizosaccharomyces pombe (strain 972 ...", "headings": [ { "level": 1, "title": "Candida albicans" }, { "level": 1, "title": "Schizosaccharomyces pombe" }, { "level": 1, "title": "Yeast (Saccharomyces cerevisiae)" }, { "level": 1, "title": "List of entries found on Yeast (Saccharomyces cerevisiae) chromosomes" } ], "word_count": 205, "official_url": "https://www.uniprot.org/help/fungi", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/fungi.md", "source_path": "fungi.md", "sha256": "3b287a0e32686b0357bc3e47536d73e86642b29a01cd5000d87006edefd6cfaf" }, { "slug": "gene_centric_isoform_mapping", "title": "Automatic gene-centric isoform mapping for eukaryotic reference proteome entries", "type": "help", "categories": [ "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "In eukaryotic reference proteomes, unreviewed entries that are likely to belong to the same gene are computationally mapped, based on gene identifiers from Ensembl, EnsemblGenomes and model organism databases. Some proteomes have been (manually and algorithmically) selected as reference proteomes. They cover well-studied model organisms and other organisms o...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 307, "official_url": "https://www.uniprot.org/help/gene_centric_isoform_mapping", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/gene_centric_isoform_mapping.md", "source_path": "gene_centric_isoform_mapping.md", "sha256": "ecee8074ff3dd5a2ff6466b69e93dd8a315e0d22c8b796cc3e32064ee1f08421" }, { "slug": "gene_name", "title": "Gene names", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section indicates the name(s) of the gene(s) that code for the protein sequence(s) described in the entry. Four distinct tokens exist: 'Name', 'Synonyms', 'Ordered locus names' and 'ORF names'. 1. Name The recommended name is used to officially represent a gene. However, in many cases, more than one name have been as...", "headings": [ { "level": 1, "title": "1. Name" }, { "level": 1, "title": "2. Synonyms" }, { "level": 1, "title": "3. Ordered Locus Names" }, { "level": 1, "title": "4. ORF Names" }, { "level": 2, "title": "Important remarks" } ], "word_count": 728, "official_url": "https://www.uniprot.org/help/gene_name", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/gene_name.md", "source_path": "gene_name.md", "sha256": "6fc2d4f42bedc2917cb063b39cd58fa17af4ffb5ae0fd4f80004807a2fbbdb7e" }, { "slug": "gene_ontology", "title": "Gene Ontology (GO)", "type": "help", "categories": [ "Website", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "Overview The Gene Ontology (GO) is a collaborative effort to provide structured, standardized descriptions of gene products (protein or ncRNA) across biological databases. GO describes biological knowledge with respect to three aspects: Molecular function: activities performed by gene products (e.g. enzymatic activity). Biological process: biological modules...", "headings": [ { "level": 2, "title": "Overview" }, { "level": 2, "title": "Where to find Gene Ontology annotations in UniProt" }, { "level": 3, "title": "GO (standard) annotations" }, { "level": 3, "title": "GO-CAMs" } ], "word_count": 400, "official_url": "https://www.uniprot.org/help/gene_ontology", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/gene_ontology.md", "source_path": "gene_ontology.md", "sha256": "379b0426ac5994e18f3bba37c30f2374f35293dda81dc60312a6d606b15bd0e7" }, { "slug": "gene_symbol_mapping", "title": "Can I convert gene symbols to UniProtKB identifiers? How can I map UniProtKB IDs or ACs to gene symbols?", "type": "help", "categories": [ "UniProtKB", "Text_search", "Names_and_taxonomy", "Website", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Proteome", "Search", "Download", "API", "ID mapping", "Evidence", "Taxonomy" ], "excerpt": "1. UniProtKB AC/ID to gene symbols You can upload your list of UniProtKB identifiers (AC or ID) to the batch retrieval service (ID mapping) and map from UniProtKB to UniProtKB. Then click on \"Customize columns\" to hide all columns except gene names. In the resulting page, click on \"Download\" and select the TSV format. To show only the recommended gene names ...", "headings": [], "word_count": 455, "official_url": "https://www.uniprot.org/help/gene_symbol_mapping", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/gene_symbol_mapping.md", "source_path": "gene_symbol_mapping.md", "sha256": "bb1f60a83fb979a3e6e0a64a729a95fbf013a273ec3e71d80fc84dbdedc0a376" }, { "slug": "general_annotation", "title": "General annotation (Comments)", "type": "help", "categories": [ "manual" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "PTM", "Structure", "Variant", "Taxonomy" ], "excerpt": "Position-independent general annotations used to be found in the 'General annotation (Comments)' section in previous versions of the UniProtKB entry view. They provide any useful information about the protein, mostly biological knowledge. General annotations are frequently written in free text, although we increasingly try to standardize them and use control...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 390, "official_url": "https://www.uniprot.org/help/general_annotation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/general_annotation.md", "source_path": "general_annotation.md", "sha256": "82071fcaf415a66ddb90eb4e0c17fb31c7439b4caac0e643b8cfd392be1b727c" }, { "slug": "genomic_coordinates", "title": "Genomic coordinates tab", "type": "help", "categories": [ "UniProtKB", "manual" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Proteome", "API", "Evidence" ], "excerpt": "This tab displays genomic coordinates information for a UniProtKB entry. Origin of the data UniProtKB entries are mainly created from translations of coding sequences (CDS) that are annotated in nucleotide sequence and genome databases. We provide genomic coordinates on the corresponding nucleotide sequences for all UniProtKB entries that have been created b...", "headings": [ { "level": 2, "title": "Origin of the data" }, { "level": 2, "title": "Sections of the tab" } ], "word_count": 208, "official_url": "https://www.uniprot.org/help/genomic_coordinates", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/genomic_coordinates.md", "source_path": "genomic_coordinates.md", "sha256": "44458d74e5bcd4308924855dc5dd997213a348bda5cd0e3e57c46c33ba1108bb" }, { "slug": "hamap", "title": "What is HAMAP?", "type": "help", "categories": [ "UniProtKB", "Family_and_domains", "Automatic_annotation", "faq" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "HAMAP is a system, based on manually curated family profiles and associated annotation rules, which identifies and automatically annotates proteins that are part of well-conserved families or subfamilies. UniProtKB/TrEMBL sequences that match one of the HAMAP profiles are annotated using the associated annotation rule. The results of this annotation are inte...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 78, "official_url": "https://www.uniprot.org/help/hamap", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/hamap.md", "source_path": "hamap.md", "sha256": "55bef1c8eab6938a17265deb272bb3db604d8b60caa8d365262b795980d58168" }, { "slug": "Home", "title": "Home", "type": "help", "categories": [], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "Welcome to the UniProt-manual wiki!", "headings": [], "word_count": 5, "official_url": "https://www.uniprot.org/help/Home", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Home.md", "source_path": "Home.md", "sha256": "dafdf3618ccbadfaf29a5cd96ef20ec92c8feb6d27c797893f520796d8741e5f" }, { "slug": "homo_sapiens", "title": "Homo sapiens", "type": "help", "categories": [ "Human", "Proteomes", "Biocuration", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "API", "Evidence", "Variant" ], "excerpt": "Human proteome In 2008, a draft of the complete human proteome was released from UniProtKB/Swiss-Prot: the approximately 20,000 putative human protein-coding genes were represented by one UniProtKB/Swiss-Prot entry, later linked to proteome identifier UP000005640. This UniProtKB/Swiss-Prot H. sapiens proteome (manually reviewed) can be considered as complete...", "headings": [ { "level": 1, "title": "Human proteome" }, { "level": 1, "title": "Human diseases" }, { "level": 1, "title": "Human entries with variants" }, { "level": 1, "title": "MIM cross-references" }, { "level": 1, "title": "Human blood group antigen proteins" }, { "level": 1, "title": "Human and mouse protein kinases" }, { "level": 1, "title": "Human cell differentiation molecules (CD)" }, { "level": 1, "title": "List of entries found on human chromosomes" } ], "word_count": 552, "official_url": "https://www.uniprot.org/help/homo_sapiens", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/homo_sapiens.md", "source_path": "homo_sapiens.md", "sha256": "37d732bb63eda8b8ec7811f6c6af26f08d8cda2e079c1ca8e228e90aed8246a4" }, { "slug": "homologs_section", "title": "Homologs section", "type": "help", "categories": [ "Similar_proteins", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Taxonomy" ], "excerpt": "Orthology and paralogy Ths section provides orthology and paralogy information which has been retrieved from the Alliance of Genome Resources (AGR). Orthology describes genes from different species that have evolved from a common ancestral gene through a speciation event, meaning these genes typically perform similar functions across species. Paralogy, on th...", "headings": [ { "level": 1, "title": "Orthology and paralogy" }, { "level": 2, "title": "Data source" }, { "level": 2, "title": "Additional information and help" }, { "level": 1, "title": "Related documents" } ], "word_count": 175, "official_url": "https://www.uniprot.org/help/homologs_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/homologs_section.md", "source_path": "homologs_section.md", "sha256": "eb5edec1293e48a2595498bc3acdbebb3fb54c4dfcd0fb1e985e0bac26a7ed15" }, { "slug": "human_proteome", "title": "What is UniProt's human proteome?", "type": "help", "categories": [ "Proteomes", "Download", "UniProtKB", "Keywords", "Sequence", "Human", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Download", "API", "Evidence" ], "excerpt": "In 2008, the first draft of the complete human (Homo sapiens) proteome was released in UniProtKB/Swiss-Prot with approximately 20,000 putative human protein-coding genes, each represented by one UniProtKB/Swiss-Prot entry. The human proteome is assigned the unique proteome identifier: UP000005640. The UniProtKB/Swiss-Prot human proteome contains one represen...", "headings": [ { "level": 1, "title": "How is the human proteome selected?" }, { "level": 1, "title": "Accessing human proteome data" }, { "level": 1, "title": "See also" } ], "word_count": 631, "official_url": "https://www.uniprot.org/help/human_proteome", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/human_proteome.md", "source_path": "human_proteome.md", "sha256": "f5d7df82ccb467e420d74f24fc9f4c76a0b47eb2bcc2dc090770a83890455af4" }, { "slug": "id_mapping", "title": "ID Mapping", "type": "help", "categories": [ "Website", "help" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "API", "ID mapping", "Evidence" ], "excerpt": "Overview The ID mapping service can map between the identifiers used in one database, to the identifiers of another, e.g., from UniProt to Ensembl, or to PomBase, etc. If you map to UniProtKB, UniParc or UniRef data, the full entries will be returned to you for convenience. This document serves as a basic guide to using the ID mapping services offered. Where...", "headings": [ { "level": 2, "title": "Overview" }, { "level": 3, "title": "Where to find the ID mapping tool" }, { "level": 2, "title": "The ID mapping job submission form" }, { "level": 3, "title": "Input identifiers" }, { "level": 3, "title": "Choosing the correct ‘From’ and ‘To’ databases" }, { "level": 4, "title": "Supported databases" }, { "level": 3, "title": "Job name" }, { "level": 2, "title": "Programmatic Access for ID Mapping" }, { "level": 2, "title": "See also" } ], "word_count": 743, "official_url": "https://www.uniprot.org/help/id_mapping", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/id_mapping.md", "source_path": "id_mapping.md", "sha256": "85a5ff045faf777d52d85f15b176d768cb1e11d4889588bfd75834315dbb5100" }, { "slug": "id_mapping_prog", "title": "Programmatic Access for ID Mapping", "type": "help", "categories": [ "Programmatic_access", "Technical", "Website", "help" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "Download", "API", "ID mapping" ], "excerpt": "To explore and try out the ID mapping services on the website, please refer to the ID mapping website tool. For technical documentation for the ID mapping API, please refer to our Swagger document. Overview The ID mapping service can map between the identifiers used in one database, to the identifiers of another, e.g., from UniProt to Ensembl, or to PomBase,...", "headings": [ { "level": 1, "title": "Overview" }, { "level": 1, "title": "Submitting an ID mapping job" }, { "level": 1, "title": "Various limits on ID mapping job submission" }, { "level": 1, "title": "Valid from and to databases pairs" }, { "level": 1, "title": "How to interpret the response" }, { "level": 2, "title": "Example: finding which databases UniParc identifiers can be mapped to" }, { "level": 1, "title": "Polling the status of a job" }, { "level": 1, "title": "Fetching the results of a job" }, { "level": 2, "title": "Paged results" }, { "level": 2, "title": "Downloading results" }, { "level": 2, "title": "Warnings and errors for /results" }, { "level": 1, "title": "Fetching details about a job" }, { "level": 1, "title": "Python example" }, { "level": 1, "title": "{'results': [{'from': 'P05067', 'to': 'CHEMBL2487'}], 'failedIds': ['P12345']}" }, { "level": 1, "title": "Retrieving website results programmatically" }, { "level": 1, "title": "Getting a Pandas DataFrame from results" }, { "level": 2, "title": "From TSV results" }, { "level": 2, "title": "From Excel/XLSX results" }, { "level": 1, "title": "R example" } ], "word_count": 1317, "official_url": "https://www.uniprot.org/help/id_mapping_prog", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/id_mapping_prog.md", "source_path": "id_mapping_prog.md", "sha256": "bee81e7fd7b1ae0e4e8d9ad4fa4f50a0c005211e9f9ef33e98b80505378e331d" }, { "slug": "immunoglobulins", "title": "Immunoglobulins", "type": "help", "categories": [ "UniProtKB", "Biocuration", "Cross-references", "Human", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Taxonomy" ], "excerpt": "Background The existence of an agent in the blood that could neutralize diphteria toxin was reported as early as 1890. Over a century after this major discovery, much is known about immunoglobulins (IG) or antibodies. They are large heterodimeric proteins made up of 2 heavy (H) chains and 2 light (L) kappa or lambda chains, held together by disulfide bonds t...", "headings": [ { "level": 1, "title": "Background" }, { "level": 1, "title": "Immunoglobulins in UniProtKB/Swiss-Prot" }, { "level": 1, "title": "Cross-references to IMGT/Gene-DB" }, { "level": 1, "title": "Non-germline immunoglobulins" }, { "level": 1, "title": "Cross-references to antibody databases" } ], "word_count": 701, "official_url": "https://www.uniprot.org/help/immunoglobulins", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/immunoglobulins.md", "source_path": "immunoglobulins.md", "sha256": "ca22107c1af4c13ec717b0c1c9814561d7767a6f931e6df2579f0cec5e13363d" }, { "slug": "induction", "title": "Induction", "type": "help", "categories": [ "Expression", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Expression' section reports the experimentally proven effects of inducers and repressors (usually chemical compounds or environmental factors) on the level of protein (or mRNA) expression (up-regulation, down-regulation, constitutive expression). Example: Q7XTE8, P29305 Transcriptional regulation by transcription factors or repressors...", "headings": [], "word_count": 96, "official_url": "https://www.uniprot.org/help/induction", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/induction.md", "source_path": "induction.md", "sha256": "8f91cb2ca6cad8f966711d0b33a609f51db91be20e0fc185563ebe67e02f1abd" }, { "slug": "init_met", "title": "Initiator methionine", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the PTM / Processing section indicates that the initiator methionine is cleaved from the mature protein. Example: Q9H425 Cleavage of the initiator methionine is one of the most common protein modifications and occurs co-translationally. This subsection is only present when cleavage has been experimentally proven or when it can be propagate...", "headings": [], "word_count": 82, "official_url": "https://www.uniprot.org/help/init_met", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/init_met.md", "source_path": "init_met.md", "sha256": "dc0f4629f2a73b862275bd4f18c224660f10cf1ceb4b2d9620a44797f23d5c1b" }, { "slug": "interaction_section", "title": "Interaction section", "type": "help", "categories": [ "Interaction", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Structure" ], "excerpt": "This section provides information on the quaternary structure of a protein and on interaction(s) with other proteins or protein complexes. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Subunit structure | Description of the quaternary structure of a protein | | Binary...", "headings": [], "word_count": 77, "official_url": "https://www.uniprot.org/help/interaction_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/interaction_section.md", "source_path": "interaction_section.md", "sha256": "19850a6676824a19cbbde9f45acb89cd44bd1fc88def86796c8bbeaa811626a1" }, { "slug": "international_protein_nomenclature_guidelines", "title": "International Protein Nomenclature Guidelines", "type": "help", "categories": [ "Biocuration", "Nomenclature", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search" ], "excerpt": "Mission statement These guidelines have been produced jointly by the European Bioinformatics Institute (EMBL-EBI), the National Center for Biotechnology Information (NCBI), the Protein Information Resource (PIR) and the Swiss Institute for Bioinformatics (SIB) and are intended for use by anyone who wants to name a protein to promote consistency in protein na...", "headings": [ { "level": 2, "title": "1. Introduction" }, { "level": 2, "title": "2. Formats for Protein Names" }, { "level": 3, "title": "A. Language" }, { "level": 3, "title": "B. Abbreviations and symbols" }, { "level": 3, "title": "C. Punctuation" }, { "level": 3, "title": "D. Notation" }, { "level": 3, "title": "E. Style and format" }, { "level": 3, "title": "F. Word usage" }, { "level": 2, "title": "3. Choosing Protein Names" }, { "level": 3, "title": "A. Sources of protein name annotation" }, { "level": 3, "title": "B. Naming procedure for specific cases" } ], "word_count": 3812, "official_url": "https://www.uniprot.org/help/international_protein_nomenclature_guidelines", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/international_protein_nomenclature_guidelines.md", "source_path": "international_protein_nomenclature_guidelines.md", "sha256": "1a22117e3d808b7655ca4290ea3c9c1a439c7c025a3b1427e96cf8a56403e4df" }, { "slug": "InterPro_rep_domain", "title": "InterPro Representative Domain", "type": "help", "categories": [ "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search" ], "excerpt": "Representative domains are protein signatures selected to best represent domain annotations from multiple InterPro member databases and thus provide a non-redundant view of a protein’s features. Domains are filtered by signature type to only include domains, repeats or homologous superfamilies which achieve maximal coverage of the protein sequence. Overlappi...", "headings": [ { "level": 1, "title": "Where can I find InterPro Representative Domains?" } ], "word_count": 180, "official_url": "https://www.uniprot.org/help/InterPro_rep_domain", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/InterPro_rep_domain.md", "source_path": "InterPro_rep_domain.md", "sha256": "494a73d26bf4a76c28f406739936740caba94f2f27a54e9686d53357fee061b9" }, { "slug": "intramem", "title": "Intramembrane", "type": "help", "categories": [ "Subcellular_location", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the 'Subcellular location' section describes the extent of a region that is buried within a membrane, but does not cross it. Examples: Q03135, A8MYU2. Related keyword: Membrane See also Evidence Transmembrane Sequence annotation (features)", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 37, "official_url": "https://www.uniprot.org/help/intramem", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/intramem.md", "source_path": "intramem.md", "sha256": "ff4ead1209ceb200709328ad8263eaa3779522a28a2a9c1cb7bfe1fa455f0b8b" }, { "slug": "invertebrates", "title": "Invertebrates", "type": "help", "categories": [ "Invertebrates", "Biocuration", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [], "excerpt": "Caenorhabditis elegans This document lists all the Caenorhabditis elegans entries present in UniProtKB/Swiss-Prot together with their gene names and cross-references to WormBase. UniProtKB/Swiss-Prot document: Caenorhabditis elegans: entries, gene names and cross-references to WormBase UniProt web page: Caenorhabditis protein annotation program Dictyostelium...", "headings": [ { "level": 1, "title": "Caenorhabditis elegans" }, { "level": 1, "title": "Dictyostelium discoideum" }, { "level": 1, "title": "Drosophila" } ], "word_count": 116, "official_url": "https://www.uniprot.org/help/invertebrates", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/invertebrates.md", "source_path": "invertebrates.md", "sha256": "fcb90844d8ff71f8eb6da6eb4386d952d6e9cb87628538d98e9eb8fe723e0fc9" }, { "slug": "involvement_in_disease", "title": "Involvement in disease", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "Variant", "Taxonomy" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section provides information on the disease(s) associated with genetic variations in a given protein. The information is extracted from the scientific literature and diseases that are also described in the OMIM database are represented with a controlled vocabulary in the following way: Disease name (Di...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 321, "official_url": "https://www.uniprot.org/help/involvement_in_disease", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/involvement_in_disease.md", "source_path": "involvement_in_disease.md", "sha256": "fa7a39cb881e75a0f09a12339efb469da9349e5728c174f26001050820651cf5" }, { "slug": "isoform_crossreferences", "title": "Cross-references for isoform sequences", "type": "help", "categories": [ "UniProtKB", "Cross-references", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [], "excerpt": "Some of the resources to which we link contain information that is specific to an isoform sequence. Where this is known, we indicate the corresponding UniProtKB isoform sequence identifier in cross-references as described below. Text format The UniProtKB isoform sequence identifier is shown in square brackets at the end of the DR line as an optional field: D...", "headings": [ { "level": 1, "title": "Text format" } ], "word_count": 105, "official_url": "https://www.uniprot.org/help/isoform_crossreferences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/isoform_crossreferences.md", "source_path": "isoform_crossreferences.md", "sha256": "9d7c43dd01f9ad57f9cfd887d78754a23987fc3ef7f6d0c2faa113eeecb9e83f" }, { "slug": "journal_abbreviations", "title": "What journal abbreviations are used in UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Publications", "Controlled_vocabulary", "faq" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [], "excerpt": "The document jourlist.txt contains this information (and more) for all journals cited in UniProtKB/Swiss-Prot. The journal abbreviation used in UniProtKB/Swiss-Prot are those proposed by the ISO (International Organization for Standardization) and generally correspond to those used by the National Library of Medicine (NLM) in PubMed. UniProtKB/TrEMBL can con...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 68, "official_url": "https://www.uniprot.org/help/journal_abbreviations", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/journal_abbreviations.md", "source_path": "journal_abbreviations.md", "sha256": "7dd0a453942d9e640db48c016ad814e29a2e7828e045b1f5fc7e4822bc3d46d0" }, { "slug": "key_staff", "title": "UniProt key staff", "type": "help", "categories": [ "Staff", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "API" ], "excerpt": "Lionel Breuza, Ph.D. Head of Chordata Curation (SIB) Dr. Breuza joined the Swiss-Prot group at the SIB Swiss Institute of Bioinformatics in 2004 where he worked as a Swiss-Prot database biocurator with a focus on vertebrate proteomes. Since 2009 he heads the chordata curation program at the SIB, managing a team of biocurators and organizing the curation work...", "headings": [], "word_count": 1224, "official_url": "https://www.uniprot.org/help/key_staff", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/key_staff.md", "source_path": "key_staff.md", "sha256": "17f2f4d5dde07baf63e3591062734b29f3360e98576063c2b1023396a501350e" }, { "slug": "keywords", "title": "Keywords", "type": "help", "categories": [ "Controlled_vocabulary", "Keywords", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "API", "PTM", "Structure", "Variant" ], "excerpt": "UniProtKB Keywords constitute a controlled vocabulary with a hierarchical structure. Keywords summarise the content of a UniProtKB entry and facilitate the search for proteins of interest. Keywords are classified in 10 categories: Biological process Cellular component Coding sequence diversity Developmental stage Disease Domain Ligand Molecular function Post...", "headings": [ { "level": 1, "title": "Keywords in UniProtKB/TrEMBL" }, { "level": 1, "title": "Related documents" } ], "word_count": 236, "official_url": "https://www.uniprot.org/help/keywords", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/keywords.md", "source_path": "keywords.md", "sha256": "aea4fa579b6a4f7316b2ffa5cc99f1d05f3bc84ad688e245ec52521b8a5fc132" }, { "slug": "keywords_vs_go", "title": "What are the differences between UniProtKB keywords and the GO terms?", "type": "help", "categories": [ "UniProtKB", "Ontology", "Keywords", "Controlled_vocabulary", "faq" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Taxonomy" ], "excerpt": "UniProtKB keywords are controlled vocabulary developed according to the need and content of UniProtKB/Swiss-Prot entries. They provide a summary of the entry content and are used to index entries based on 10 categories. Each keyword is attributed manually to UniProtKB/Swiss-Prot entries and automatically to UniProtKB/TrEMBL entries (according to specific ann...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 162, "official_url": "https://www.uniprot.org/help/keywords_vs_go", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/keywords_vs_go.md", "source_path": "keywords_vs_go.md", "sha256": "53c2f9e2db5d5ae5a8616bd7482b19350128aed758ae3322507280ab60e433a2" }, { "slug": "license", "title": "License & disclaimer", "type": "help", "categories": [ "About_UniProt", "Technical", "help" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [ "Search", "API" ], "excerpt": "License We have chosen to apply the Creative Commons Attribution 4.0 International (CC BY 4.0) License to all copyrightable parts of our databases. How to cite us Disclaimer We make no warranties regarding the correctness of the data, and disclaim liability for damages resulting from its use. We cannot provide unrestricted permission regarding the use of the...", "headings": [ { "level": 1, "title": "License" }, { "level": 1, "title": "Disclaimer" } ], "word_count": 106, "official_url": "https://www.uniprot.org/help/license", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/license.md", "source_path": "license.md", "sha256": "e9d9dbc4ef39450b51e1cb1206dc7249534641ef5926f99fe988cedcc4dca0df" }, { "slug": "link_old_versions", "title": "How do I link to a specific version of a UniProtKB entry?", "type": "help", "categories": [ "UniProtKB", "Technical", "Release", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API" ], "excerpt": "In order to keep up-to-date with scientific knowledge, we update entries thus producing a new version of the entry each time. For example, there have been over 250 updates to P00750 (TPAHUMAN). The version number appears below the accession number right at the top of a UniProtKB entry view. The History link allows you to browse and compare various versions o...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 123, "official_url": "https://www.uniprot.org/help/link_old_versions", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/link_old_versions.md", "source_path": "link_old_versions.md", "sha256": "a82ba53e354fb3125e65df6eceebb2d5e862e9f71646b3d48eb6b068696d4c77" }, { "slug": "linking_to_uniprot", "title": "How to link to UniProt entries (UniProtKB, UniParc and UniRef)", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Technical", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "API" ], "excerpt": "Standard format The standard way of linking to UniProt databases, displaying the UniProt HTML view is: https://www.uniprot.org/dataset/identifier where the value of dataset is either uniprot, uniparc or uniref Examples: https://www.uniprot.org/uniprotkb/P99999 https://www.uniprot.org/uniref/UniRef100P99999 (cf remark 2) https://www.uniprot.org/uniref/UniRef9...", "headings": [ { "level": 1, "title": "Standard format" }, { "level": 1, "title": "Other formats" }, { "level": 1, "title": "See also" } ], "word_count": 403, "official_url": "https://www.uniprot.org/help/linking_to_uniprot", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/linking_to_uniprot.md", "source_path": "linking_to_uniprot.md", "sha256": "a48894f8ec33c886a539e304720df2e672ec918d4d2ffd744459737d9386f303" }, { "slug": "linking_to_uniref", "title": "Are UniRef cluster identifiers permanent? How can I link to UniRef clusters?", "type": "help", "categories": [ "UniRef", "faq" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [ "Search" ], "excerpt": "Are UniRef cluster identifiers permanent? No. However, the vast majority do not change from release to release even if clusters are recomputed, and the representative entry usually remains the same. For example, UniRef50P99999 has over 450 members, and Cytochrome C from Human is the representative. This will probably remain so, as it is by far the best annot...", "headings": [ { "level": 1, "title": "Are UniRef cluster identifiers permanent?" }, { "level": 1, "title": "How do I link to UniRef clusters, and what if the cluster ID changed?" }, { "level": 1, "title": "See also" } ], "word_count": 196, "official_url": "https://www.uniprot.org/help/linking_to_uniref", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/linking_to_uniref.md", "source_path": "linking_to_uniref.md", "sha256": "1abea5f86b6cecd5b62034a9091bd78fceb73980c303005462042337835331cc" }, { "slug": "links", "title": "Links", "type": "help", "categories": [ "help" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "Links provided by the UniProt Consortium members | EMBL-EBI Services | | ExPASy: Bioinformatics resource portal of SIB Swiss Institute of Bioinformatics | | PIR Resources |", "headings": [], "word_count": 21, "official_url": "https://www.uniprot.org/help/links", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/links.md", "source_path": "links.md", "sha256": "031c497339694593201e3bc675320bf7d8cb84708f0f57ae5de1fece054d0bca" }, { "slug": "lipid", "title": "Lipidation", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the PTM / Processing section specifies the position(s) and the type of covalently attached lipid group(s). The covalent binding of a lipid group to a peptide chain, also known as lipidation, can affect the activity of the protein and/or alter its subcellular location. For instance, palmitoylation, myristoylation or prenylation of cytoplasm...", "headings": [ { "level": 1, "title": "1. N-Myristoylation" }, { "level": 1, "title": "2. Palmitoylation" }, { "level": 1, "title": "3. GPI-anchor addition" }, { "level": 1, "title": "4. Prenylation" }, { "level": 1, "title": "5. Lipidation of bacterial proteins (S-diacylglycerol)" }, { "level": 1, "title": "6. Other examples of lipidation" } ], "word_count": 652, "official_url": "https://www.uniprot.org/help/lipid", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/lipid.md", "source_path": "lipid.md", "sha256": "724f0da0830dcb68718239f63367a6b600d018c1e67fcd29d900b73b3ea3620f" }, { "slug": "list_specific_proteins", "title": "Lists of specific protein families", "type": "help", "categories": [ "Biocuration", "Family_and_domains", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "7-transmembrane G-linked receptors 7-transmembrane G-linked receptors (also known as G protein coupled receptors (GPCRs), seven-transmembrane domain receptors, 7TM receptors, heptahelical receptors, serpentine receptor and G protein-linked receptors (GPLR)) constitute a large protein family of receptors that sense molecules outside the cell and activate insi...", "headings": [ { "level": 1, "title": "7-transmembrane G-linked receptors" }, { "level": 1, "title": "Aminoacyl-tRNA synthetases" }, { "level": 1, "title": "Intein-containing proteins" }, { "level": 1, "title": "Translation initiation factors" }, { "level": 1, "title": "Uncharacterized protein families (UPF)" } ], "word_count": 266, "official_url": "https://www.uniprot.org/help/list_specific_proteins", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/list_specific_proteins.md", "source_path": "list_specific_proteins.md", "sha256": "fbebca3df7a5f8b992e4c3190a71ab14463c5eb61d721de685cdfef662115357" }, { "slug": "literature_references", "title": "On what basis are literature references inserted in UniProtKB/Swiss-Prot entries?", "type": "help", "categories": [ "UniProtKB", "Publications", "Biocuration", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "API", "PTM", "Structure", "Variant" ], "excerpt": "One of our primary source of protein knowledge are journal articles. Information on a given protein is often spread between many different reports. All relevant references used by the annotators to create or update an entry are generally added. This includes references dealing with sequences, structures, protein-protein interactions, post-translational modif...", "headings": [ { "level": 1, "title": "Query UniProtKB" }, { "level": 1, "title": "See also" } ], "word_count": 465, "official_url": "https://www.uniprot.org/help/literature_references", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/literature_references.md", "source_path": "literature_references.md", "sha256": "8412059bcbda5e5e38b87419457ff0190f5213f4f1cca1e5e08dd4ea79c1ed95" }, { "slug": "manual_curation", "title": "How do we manually annotate a UniProtKB entry?", "type": "help", "categories": [ "UniProtKB", "Biocuration", "About_UniProt", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "Sequence tools", "Evidence", "PTM", "Taxonomy" ], "excerpt": "A well-defined manual curation process is essential to ensure that all manually annotated entries are handled in a consistent manner. This process consists of 6 major mandatory steps: (1) sequence curation, (2) sequence analysis, (3) literature curation, (4) family-based curation, (5) evidence attribution, (6) quality assurance and integration of completed e...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 579, "official_url": "https://www.uniprot.org/help/manual_curation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/manual_curation.md", "source_path": "manual_curation.md", "sha256": "b60c731b9fd75b6c358befc309db7e8fc3c07c7afafc8cb0c7fbdc73942f0c40" }, { "slug": "mass_spectrometry", "title": "Mass spectrometry", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Sequence tools" ], "excerpt": "This subsection of the 'Sequence' section reports information derived from mass spectrometry experiments done on the entire protein or on biologically active derived peptide(s). The following information items are provided: optionally: the name of an isoform or product of proteolytic cleavage; determined molecular weight (mass) (in Daltons) and, if known, th...", "headings": [], "word_count": 129, "official_url": "https://www.uniprot.org/help/mass_spectrometry", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/mass_spectrometry.md", "source_path": "mass_spectrometry.md", "sha256": "2d3f0eb756f60744be96a1b4a797c36f9cbc0fafa3b6bf0cd09107ad103eb339" }, { "slug": "medical_advice", "title": "How can I get medical advice from UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Text_search", "disease_phenotypes_variants", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "API", "Variant" ], "excerpt": "UniProtKB is a protein sequence database and our staff consists of biologists and biochemists that are not trained to give medical advice. UniProtKB/Swiss-Prot contains a limited amount of information concerning genetic diseases (in the Disease/Phenotypes and variants section, Involvement in disease subsection), as well as sequence information on some diseas...", "headings": [], "word_count": 156, "official_url": "https://www.uniprot.org/help/medical_advice", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/medical_advice.md", "source_path": "medical_advice.md", "sha256": "a2378a0f78fa168a5f71e272079ae0cdc93e013edd312d8472e9002e62c629c7" }, { "slug": "metal", "title": "Metal binding - deprecated", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search" ], "excerpt": "Historically, UniProtKB has described a few classes of ligand binding sites with dedicated annotation types to make it easier to query them. This has been the case for 'Calcium binding', 'Metal binding' and 'Nucleotide binding'. With the switch to the ChEBI ontology for ligand classification, this is no longer necessary: These annotation types were deprecate...", "headings": [], "word_count": 65, "official_url": "https://www.uniprot.org/help/metal", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/metal.md", "source_path": "metal.md", "sha256": "2aea5901df8f4498a86c487c327e47c7ffcac6cdf63dbf5e2c3f686d9053d54a" }, { "slug": "metalink", "title": "Downloaded data seems incomplete or corrupted - how can I get help with download problems?", "type": "help", "categories": [ "Download", "Technical", "faq" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "FASTA", "Search", "Download", "API", "Taxonomy" ], "excerpt": "FTP downloads Every folder on our FTP server contains a file called RELEASE.metalink that specifies the size and MD5 checksum of every file in that folder, e.g. Metalink is an extensible metadata file format that describes one or more computer files available for download. It facilitates file verification and recovery from data corruption and lists alternate...", "headings": [ { "level": 1, "title": "FTP downloads" }, { "level": 1, "title": "HTTP downloads" } ], "word_count": 440, "official_url": "https://www.uniprot.org/help/metalink", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/metalink.md", "source_path": "metalink.md", "sha256": "3ccb8725dc53450b62d056faa073b88a58d61c88dc0ef3140601b60254e4331a" }, { "slug": "miscellaneous", "title": "Miscellaneous", "type": "help", "categories": [ "Miscellaneous", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Function' section describes relevant information that doesn't fall into the scope of any other subsections, but is thought to be valuable enough to be cited in UniProtKB. Examples: Q96KQ4, Q5G859", "headings": [], "word_count": 34, "official_url": "https://www.uniprot.org/help/miscellaneous", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/miscellaneous.md", "source_path": "miscellaneous.md", "sha256": "662f5b300535bbafdf1abb0fa07fa433d2887af4e3cb702efa8c54864c2bf9de" }, { "slug": "miscellaneous_section", "title": "Miscellaneous section", "type": "help", "categories": [ "Miscellaneous", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This section contains any relevant information that doesn't fit in any other defined sections The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Keywords 'Technical term' | Selection of controlled vocabulary which summarises the content of an entry | | Documents | Selected...", "headings": [], "word_count": 56, "official_url": "https://www.uniprot.org/help/miscellaneous_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/miscellaneous_section.md", "source_path": "miscellaneous_section.md", "sha256": "c830e47e69103c84883bb7d5dc67105bd33853bc41e5d373c62626e82baa9a7c" }, { "slug": "mod_res", "title": "Modified residue", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "PTM", "Variant", "Taxonomy" ], "excerpt": "This subsection of the 'PTM / Processing' section specifies the position and type of each modified residue excluding lipids, glycans and protein cross-links. Common modifications include phosphorylation, methylation, acetylation, amidation, formation of pyrrolidone carboxylic acid, isomerization, hydroxylation, sulfation, flavin-binding, cysteine oxidation a...", "headings": [ { "level": 1, "title": "1. Phosphorylation" }, { "level": 1, "title": "2. Methylation" }, { "level": 2, "title": "Carboxyl methylation" }, { "level": 2, "title": "Nitrogen methylation" }, { "level": 2, "title": "Histidine methylation" }, { "level": 2, "title": "Lysine methylation" }, { "level": 2, "title": "Arginine methylation" }, { "level": 2, "title": "Other rare examples of side chain methylation" }, { "level": 1, "title": "3. Acetylation" }, { "level": 2, "title": "N-terminal acetylation" }, { "level": 2, "title": "Internal acetylation" }, { "level": 1, "title": "4. Amidation" }, { "level": 2, "title": "Terminal amidation" }, { "level": 2, "title": "Glutamate amidation" }, { "level": 1, "title": "5. Pyrrolidone carboxylic acid" }, { "level": 1, "title": "6. Isomerization" }, { "level": 1, "title": "7. Hydroxylation" }, { "level": 2, "title": "Hydroxyproline" }, { "level": 2, "title": "Hydroxylysine" }, { "level": 2, "title": "Hydroxyasparagine" }, { "level": 1, "title": "8. Sulfation" }, { "level": 2, "title": "Tyrosine sulfation" }, { "level": 2, "title": "Serine and threonine sulfation:" }, { "level": 1, "title": "9. Flavin-binding" }, { "level": 1, "title": "10. Cysteine oxidation and nitrosylation" }, { "level": 2, "title": "Sulfenic and sulfinic acid" }, { "level": 2, "title": "S-nitrosocysteine" }, { "level": 1, "title": "Related documents" } ], "word_count": 2886, "official_url": "https://www.uniprot.org/help/mod_res", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/mod_res.md", "source_path": "mod_res.md", "sha256": "a56a57ae219d68059dd7545e23c1d8c4d91836492437241df0fad731e8aceab6" }, { "slug": "mod_res_large_scale", "title": "Large scale modified residue", "type": "help", "categories": [ "PTM_processing" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Download", "Evidence", "PTM", "Variant", "Taxonomy" ], "excerpt": "Modified residues from large scale data In addition to manually curated post-translational modification (PTM) data which is included in the downloadable versions of our data, some entries on our website also include additional large-scale PTM data. These originate from large-scale mass spectrometry (MS) datasets, which have been reanalyzed. Example: B9FXV5 W...", "headings": [ { "level": 1, "title": "Modified residues from large scale data" }, { "level": 2, "title": "Where does the data come from?" }, { "level": 2, "title": "Evidence" }, { "level": 2, "title": "Which species is large-scale data available for?" }, { "level": 1, "title": "How can I access this data in UniProt?" }, { "level": 2, "title": "How can I download this data?" }, { "level": 1, "title": "What is a peptidoform?" }, { "level": 1, "title": "Scoring and statistical analysis for PTM’s imported from the PTMeXchange project." }, { "level": 2, "title": "Confidence score" }, { "level": 3, "title": "How is the score calculated?" }, { "level": 3, "title": "What is the gold/silver/bronze criterion?" }, { "level": 2, "title": "Statistical attributes" }, { "level": 3, "title": "PSM (Peptide Spectrum Match) count" }, { "level": 3, "title": "Site probability" }, { "level": 3, "title": "Universal Spectrum Identifier (USI)" }, { "level": 3, "title": "Experimental Peptidoform" } ], "word_count": 1315, "official_url": "https://www.uniprot.org/help/mod_res_large_scale", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/mod_res_large_scale.md", "source_path": "mod_res_large_scale.md", "sha256": "32dfaad3ca5bbcf452c1b7920101596a925fe9aa600fe8c6ae6307b718677b15" }, { "slug": "motif", "title": "Motif", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the 'Family and Domains' section describes a short (usually not more than 20 amino acids) conserved sequence motif of biological significance. Specific sequence motifs usually mediate a common function, such as protein-binding or targeting to a particular subcellular location, in a variety of proteins. Due to their short length and high le...", "headings": [ { "level": 1, "title": "Some examples of specific motifs" }, { "level": 1, "title": "See also" } ], "word_count": 250, "official_url": "https://www.uniprot.org/help/motif", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/motif.md", "source_path": "motif.md", "sha256": "9fcc22bf8a6c45fb39fb760935e78e5e358f3984851d690d88fda2c0c6ba83eb" }, { "slug": "mouse", "title": "Mouse", "type": "help", "categories": [ "Chordata", "Biocuration", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome" ], "excerpt": "UniProtKB/Swiss-Prot document: MGD cross-references in UniProtKB/Swiss-Prot UniProt web page: Chordata protein annotation program Mouse annotation statistics What are reference proteomes? UniProtKB/Swiss-Prot document: Human and mouse protein kinases Related terms: mgdtosp.txt, MGI, pkinfam.txt", "headings": [], "word_count": 37, "official_url": "https://www.uniprot.org/help/mouse", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/mouse.md", "source_path": "mouse.md", "sha256": "ff3f97f825a436c3d8fa596b72a3be4418e346ce934f81fbfc8244c34c236566" }, { "slug": "multiple_pdb_xrefs", "title": "Why are there multiple cross-references to PDB in a UniProtKB entry?", "type": "help", "categories": [ "UniProtKB", "Cross-references", "3D_structure", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "3D structures convey important experimental evidence on a protein: its secondary structure, how it is folded, which parts of the polypeptide chain are available for interactions with other proteins, and which residues are directly involved in the catalytic activity or in ligand-binding. There is often more than one experimentally determined structure availab...", "headings": [], "word_count": 205, "official_url": "https://www.uniprot.org/help/multiple_pdb_xrefs", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/multiple_pdb_xrefs.md", "source_path": "multiple_pdb_xrefs.md", "sha256": "9dfc2c954d0ed6e27aad0d528070f6c5b1defd192037d232f56cb9f555c46ef9" }, { "slug": "mutagen", "title": "Mutagenesis data", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Download", "API", "PTM", "Structure", "Variant", "Taxonomy" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section describes the effect of the experimental mutation of one or more amino acid(s) on the biological properties of the protein. 1. Mutagenesis experimental data from the literature We describe only those experiments in which a limited number of amino acid residues are altered: gross alterations in ...", "headings": [ { "level": 1, "title": "1. Mutagenesis experimental data from the literature" }, { "level": 1, "title": "2. Mutagenesis (large scale data)" } ], "word_count": 389, "official_url": "https://www.uniprot.org/help/mutagen", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/mutagen.md", "source_path": "mutagen.md", "sha256": "b73aa955cbf00189ff74921474a9ce7c1b4938d21f754e51266d0c29bea88d62" }, { "slug": "names_and_taxonomy_section", "title": "Names and Taxonomy section", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Taxonomy" ], "excerpt": "This section provides information about the protein and gene name(s) and synonym(s) and about the organism that is the source of the protein sequence. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Protein names | Name and synonyms of the protein | | Gene names | Name(...", "headings": [], "word_count": 138, "official_url": "https://www.uniprot.org/help/names_and_taxonomy_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/names_and_taxonomy_section.md", "source_path": "names_and_taxonomy_section.md", "sha256": "3f310f0e93be0836ba62659f9da6d8298cbd371ada3a298cf7bf1fb58c686f44" }, { "slug": "ncbi_mappings", "title": "Mapping between UniProtKB and NCBI resources (GeneID, RefSeq): how does it work?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Cross-references", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "ID mapping", "Taxonomy" ], "excerpt": "How does UniProt do GeneID and RefSeq mappings? As per a protocol we have formalized with the NCBI, we create a RefSeq protein-centric mapping. If a UniProtKB protein (canonical or isoform sequence) is 100% identical (over the entire sequence length) to a RefSeq protein and is from the same organism or has common EMBL/DDBJ/GenBank protein accession numbers (...", "headings": [ { "level": 1, "title": "How does UniProt do GeneID and RefSeq mappings?" }, { "level": 1, "title": "Why are GeneID cross-references absent from some human entries?" }, { "level": 1, "title": "Why do some GeneID entries link to UniProtKB entries, but those UniProtKB entries do not have the GeneID cross-reference?" }, { "level": 1, "title": "See also" } ], "word_count": 189, "official_url": "https://www.uniprot.org/help/ncbi_mappings", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ncbi_mappings.md", "source_path": "ncbi_mappings.md", "sha256": "bfb6b68702398633584a71e977afd1752e0f4ec0e7ce863fa076f45e76f57d1f" }, { "slug": "ncbifam_rules", "title": "NCBIfam equivalog rules", "type": "help", "categories": [ "Automatic_annotation", "Biocuration", "UniProtKB", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "NCBIfam rules are based on equivalog protein family models (owned and maintained by NCBI, and encompass TIGRFAMs), where these models describe proteins homologous to each other and conserved in function since their last common ancestor. To know more about equivalog models, please consult the TIGRFAM article and NCBI website. We are adding some NCBIfam rules ...", "headings": [], "word_count": 69, "official_url": "https://www.uniprot.org/help/ncbifam_rules", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ncbifam_rules.md", "source_path": "ncbifam_rules.md", "sha256": "a3135642c6e053ceae66e1edd08bd4e1a990ed79523742c9775741c092e231ed" }, { "slug": "negative_datasets", "title": "I would like to test the performance of a sequence-based prediction method: Can I use UniProt to build a negative data set?", "type": "help", "categories": [ "UniProtKB", "Text_search", "Sequence", "Biocuration", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "Evidence", "PTM", "Taxonomy" ], "excerpt": "The manual curation process of UniProtKB/Swiss-Prot includes extensive literature curation, and the annotation items with experimental evidence can be used to construct positive data sets for predictors of post-translational modifications (PTM) and other events, e.g. all human entries with experimentally determined signal sequences%20AND%20(organismid:9606))...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 245, "official_url": "https://www.uniprot.org/help/negative_datasets", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/negative_datasets.md", "source_path": "negative_datasets.md", "sha256": "15048fdb4a0e31fca2e0908c757a20282000589e026bc6dc6525f8a2d6530211" }, { "slug": "nomenclature_classification_specific_proteins", "title": "Nomenclature/classification of specific proteins", "type": "help", "categories": [ "Nomenclature", "Biocuration", "Family_and_domains", "Human", "UniProtKB", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Search", "API", "Variant" ], "excerpt": "Allergens A nomenclature system exists for antigens (allergens) that cause IgE-mediated atopic allergies in humans and is applied to UniProtKB/Swiss-Prot entries. UniProtKB/Swiss-Prot document: Nomenclature of allergens and list of entries Related keyword: Allergen Relevant UniProtKB/Swiss-Prot entries cross-referenced to Allergome Glycosyl hydrolases O-Glyc...", "headings": [ { "level": 1, "title": "Allergens" }, { "level": 1, "title": "Glycosyl hydrolases" }, { "level": 1, "title": "Human blood group antigen proteins" }, { "level": 1, "title": "Human and mouse protein kinases" }, { "level": 1, "title": "Human cell differentiation molecules (CD)" }, { "level": 1, "title": "Metallothioneins" }, { "level": 1, "title": "Peptidase families" }, { "level": 1, "title": "Restriction enzymes and methylases" }, { "level": 1, "title": "Ribosomal proteins" }, { "level": 1, "title": "Scorpion potassium channel toxins" }, { "level": 1, "title": "Vertebrate homeotic Hox proteins" } ], "word_count": 646, "official_url": "https://www.uniprot.org/help/nomenclature_classification_specific_proteins", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/nomenclature_classification_specific_proteins.md", "source_path": "nomenclature_classification_specific_proteins.md", "sha256": "0a0f2f6843e3e685e036ea5f64184a0707fa72d1d1b72ffe488e98faa610a2c3" }, { "slug": "non_cons", "title": "Non-adjacent residues", "type": "help", "categories": [ "Sequence", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "This subsection of the 'Sequence' section is used to indicate that two residues in a sequence are not consecutive and that there is an undetermined number of unsequenced residues between them. Example: P68251 The 'Non-adjacent residues' subsection is used for incomplete protein sequence entries and is accompanied by the 'Fragments' flag in the 'Sequence stat...", "headings": [], "word_count": 56, "official_url": "https://www.uniprot.org/help/non_cons", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/non_cons.md", "source_path": "non_cons.md", "sha256": "98879b0a64720b32478b0e7e371c3550614a39fbabfa5dc9d11901a33a24a148" }, { "slug": "non_std", "title": "Non-standard residue", "type": "help", "categories": [ "Sequence", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [], "excerpt": "This subsection of the 'Sequence' section describes the occurrence of non-standard amino acids selenocysteine (Sec) or pyrrolysine (Pyl) in the protein sequence. Selenocysteine and pyrrolysine are represented in the sequence using the one-letter codes 'U' for selenocysteine and 'O' for pyrrolysine. Incorporation of a selenocysteine or of a pyrrolysine in the...", "headings": [], "word_count": 193, "official_url": "https://www.uniprot.org/help/non_std", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/non_std.md", "source_path": "non_std.md", "sha256": "0558c2458c5b563c08fb2034ecbe8cdd8575b5d0c6d7aa7843670fb2977f9f70" }, { "slug": "non_ter", "title": "Non-terminal residue", "type": "help", "categories": [ "Sequence", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "This subsection of the 'Sequence' section is used for sequence fragments to indicate that the residue at the extremity of the sequence is not the actual terminal residue in the complete protein sequence. The first residue of the displayed protein sequence may not correspond to the true N-terminus of the complete protein sequence. Example: P29309 The last res...", "headings": [], "word_count": 109, "official_url": "https://www.uniprot.org/help/non_ter", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/non_ter.md", "source_path": "non_ter.md", "sha256": "af07397783f42a314a23e4f32924352fd3962eaa82409cc001bdaa3b2650c8a0" }, { "slug": "np_bind", "title": "Nucleotide binding - deprecated", "type": "help", "categories": [ "Function", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search" ], "excerpt": "Historically, UniProtKB has described a few classes of ligand binding sites with dedicated annotation types to make it easier to query them. This has been the case for 'Calcium binding', 'Metal binding' and 'Nucleotide binding'. With the switch to the ChEBI ontology for ligand classification, this is no longer necessary: These annotation types were deprecate...", "headings": [], "word_count": 65, "official_url": "https://www.uniprot.org/help/np_bind", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/np_bind.md", "source_path": "np_bind.md", "sha256": "0ab8c8d7bc0f892529a9b58d12c877c4c2d3b6df1b4963aa5d76f0cd8ce3ccd6" }, { "slug": "organism-name", "title": "Organism", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "API", "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section provides information on the name(s) of the organism that is the source of the protein sequence. The organism designation consists of the Latin scientific name, usually composed of the genus and species names (the binomial system developed by Linnaeus), followed optionally by the English common name and a syno...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 239, "official_url": "https://www.uniprot.org/help/organism-name", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/organism-name.md", "source_path": "organism-name.md", "sha256": "53f2e60896b09f2f6c365d6800904a611d429495f121c58bb4c24bf0799a0af6" }, { "slug": "orthologs_between_two_species", "title": "Is there a download file available where all UniProt IDs from X.laevis are matched to their human equivalents (homologs)? How can I obtain an ortholog mapping of human proteins to S.pombe proteins?", "type": "help", "categories": [ "UniProtKB", "Text_search", "Cross-references", "Taxonomy", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "Download", "API", "Evidence", "Taxonomy" ], "excerpt": "There are no such ready-made files available from UniProt, but a number of phylogenomic databases exist which may be in a better position to answer this question. There is quite a useful thread on the BioStars website. If you want to use UniProtKB, you should first find out which of the phylogenomic databases cross-referenced by UniProtKB provides the best c...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 325, "official_url": "https://www.uniprot.org/help/orthologs_between_two_species", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/orthologs_between_two_species.md", "source_path": "orthologs_between_two_species.md", "sha256": "d4de87f888804f11bcadda47eab422fb6c045940097103a8e9fc937dd9e22f67" }, { "slug": "orthology", "title": "How is orthology established in UniProtKB/Swiss-Prot?", "type": "help", "categories": [ "UniProtKB", "Family_and_domains", "Cross-references", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Download", "Sequence tools" ], "excerpt": "How is orthology established in UniProtKB/Swiss-Prot? Information is combined from a variety of complementary sources to establish orthology relationships. Potential orthologs are initially identified using sequence similarity search programs such as BLAST. Orthology relationships are then verified manually using a combination of resources including scientif...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 116, "official_url": "https://www.uniprot.org/help/orthology", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/orthology.md", "source_path": "orthology.md", "sha256": "b0ff277b1e2431a94f4e22987e4a656a2e940a54d59c1d90b97ca76df77d71ef" }, { "slug": "pagination", "title": "Programmatic Pagination", "type": "help", "categories": [ "Programmatic_access", "Text_search", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "Querying UniProt's datasets can yield many results. Instead of returning all results in a single payload (time consuming and expensive), the search behaviour is designed to return results in batches (pages), i.e., those that are more relevant to the user's query coming in earlier batches. In addition to these results, a set of HTTP headers are returned, one ...", "headings": [ { "level": 1, "title": "search UniProtKB and display both response headers and body" } ], "word_count": 167, "official_url": "https://www.uniprot.org/help/pagination", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pagination.md", "source_path": "pagination.md", "sha256": "36e13b5295593a4394664682dd1b14fff8c4e36e0ebfbb3f473c4bfa6db20672" }, { "slug": "pan_proteomes", "title": "Pan proteomes", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Download", "Sequence tools", "Taxonomy" ], "excerpt": "A pan proteome is a set of proteins from multiple proteomes thought to be expressed by a taxonomic group in order to reflect the proteome diversity of the species. What pan proteomes does UniProt provide? UniProt provides pan proteomes at the species level to capture unique sequences absent from the reference proteome, in order to reflect the proteome divers...", "headings": [ { "level": 2, "title": "What pan proteomes does UniProt provide?" }, { "level": 2, "title": "How are species pan proteomes generated?" }, { "level": 2, "title": "Where can I find this data in UniProt?" }, { "level": 3, "title": "Access via the website" }, { "level": 3, "title": "Access via FTP download" }, { "level": 4, "title": "1. Accessing pan proteomes for all species" }, { "level": 4, "title": "2. Accessing a species-specific pan proteome" }, { "level": 3, "title": "Explanation of FTP file formats" }, { "level": 4, "title": "Pan Proteome FASTA file" }, { "level": 4, "title": "Pan Proteome Matrix" }, { "level": 4, "title": "Pan Proteome Statistics" }, { "level": 1, "title": "See also" } ], "word_count": 637, "official_url": "https://www.uniprot.org/help/pan_proteomes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pan_proteomes.md", "source_path": "pan_proteomes.md", "sha256": "06d5112cec55f5a070f98bbb4704d695a9924bd6f16c902cef6f397a8adf8961" }, { "slug": "pan_proteomes_workflow", "title": "Pan proteomes workflow", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Proteome", "Search", "Taxonomy" ], "excerpt": "In UniProt, pan proteomes are generated by clustering proteins from multiple proteomes of the same species, then selecting one representative sequence per protein cluster. UniProt pan proteomes are generated at every UniProt release. Workflow overview 1. Assessment of species and proteome eligibility A species is considered for pan proteome generation when a...", "headings": [ { "level": 1, "title": "Workflow overview" }, { "level": 2, "title": "1. Assessment of species and proteome eligibility" }, { "level": 2, "title": "2. MMseqs2 protein clustering is performed for each species" }, { "level": 2, "title": "3. Filtering for singleton protein clusters" }, { "level": 2, "title": "4. Representative protein sequences are selected hierarchically" }, { "level": 2, "title": "5. Generation of standardized output files" }, { "level": 2, "title": "6. Release and versioning" }, { "level": 1, "title": "FAQs" }, { "level": 2, "title": "1. How can pan proteomes be used?" }, { "level": 2, "title": "2. What is a singleton protein cluster?" }, { "level": 2, "title": "3. Are singleton protein clusters always removed from pan proteomes?" }, { "level": 2, "title": "4. Why does a species not have a pan proteome?" }, { "level": 2, "title": "5. What is Protein Frequency?" }, { "level": 2, "title": "6. What are “core” and “accessory” proteins?" }, { "level": 2, "title": "7. How is the representative sequence chosen for each protein cluster?" }, { "level": 2, "title": "8. How can I find the corresponding genome assembly for a protein in a pan proteome?" }, { "level": 2, "title": "9. Can I identify exact protein sequences behind matrix counts?" }, { "level": 2, "title": "10. Where are MMseqs2 clustering parameters documented?" }, { "level": 2, "title": "11. Where should users go for full technical details of the pan proteomes selection workflow?" }, { "level": 2, "title": "12. What should users consider when interpreting pan proteome results?" }, { "level": 1, "title": "See also" } ], "word_count": 1028, "official_url": "https://www.uniprot.org/help/pan_proteomes_workflow", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pan_proteomes_workflow.md", "source_path": "pan_proteomes_workflow.md", "sha256": "6f21a3aafab19362ea1185e491e1044cef82473c9253890c26ebe198d6f995db" }, { "slug": "pathway", "title": "Pathway", "type": "help", "categories": [ "Function", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Structure" ], "excerpt": "This subsection of the 'Function' section describes the metabolic pathway(s) associated with a protein. Example: P77731 The 'Pathway' subsection uses a structured hierarchy of controlled vocabulary. Each process is split up into 'super-pathway', 'pathway' and/or 'sub-pathway' associated with the protein. When known, the step number mediated by the protein wi...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 124, "official_url": "https://www.uniprot.org/help/pathway", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pathway.md", "source_path": "pathway.md", "sha256": "bd8a1c54ebcc1c47a90abb11bc7aa3b8c8ac8d5e6f043035859de2b272be908d" }, { "slug": "peptide", "title": "Peptide", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "PTM" ], "excerpt": "This subsection of the 'PTM / Processing' section describes the position and length of an active peptide in the mature protein. An active peptide is defined as a small polypeptide (<= 40 to 50 amino acid long) that is processed (e.g. by proteolytic cleavage) from a larger precursor protein and has a well defined biological activity on its own. The processing...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 152, "official_url": "https://www.uniprot.org/help/peptide", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/peptide.md", "source_path": "peptide.md", "sha256": "a257834ece84ee6b8f0b118b666cc71ad90da35115d4f628a70fe00736f5e691" }, { "slug": "peptide_search", "title": "Peptide Search", "type": "help", "categories": [ "Website", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API", "Sequence tools", "Taxonomy" ], "excerpt": "Overview The peptide search tool searches UniProtKB for protein entries that match peptide sequences of a minimum length of 7 amino acids and returns results in a customizable and downloadable format. Submitting a peptide search job Submissions must contain a minimum of 1 peptide and a maximum of 100 peptides. Peptides do not necessarily have to be the resul...", "headings": [ { "level": 2, "title": "Overview" }, { "level": 2, "title": "Submitting a peptide search job" }, { "level": 3, "title": "Restrict by organism" }, { "level": 3, "title": "Job name" }, { "level": 2, "title": "Where to find the peptide search tool" }, { "level": 2, "title": "Programmatic access to the peptide search tool" } ], "word_count": 260, "official_url": "https://www.uniprot.org/help/peptide_search", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/peptide_search.md", "source_path": "peptide_search.md", "sha256": "98837bacbfc6d23f94f6a647ba5ac252c4d2193f2a90a71733194905717c60f9" }, { "slug": "pharmaceutical_use", "title": "Pharmaceutical use", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section describes the use of a protein as a pharmaceutical drug. It indicates the name of the drug, the name of the firm that commercializes it and explains in a few words in which context the drug is used. In some cases, drugs that are under development are also described. Examples: P01275, P42166, P1...", "headings": [ { "level": 1, "title": "Related document" } ], "word_count": 86, "official_url": "https://www.uniprot.org/help/pharmaceutical_use", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pharmaceutical_use.md", "source_path": "pharmaceutical_use.md", "sha256": "646e6f8b4722f0e42db09fa098dae58e653a9a88f8ab3f8559e53dbb1ca0d56a" }, { "slug": "pir_psd", "title": "What happened to PIR-PSD entries? Are all PIR-PSD entries now in the UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Cross-references", "UniParc", "faq" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "To avoid duplication of work within UniProtKB, PIR-PSD ceased to be maintained as of release 80.00 (31-Dec-2004). All suitable sequences in PIR-PSD that were missing from Swiss-Prot + TrEMBL at that time were incorporated into the TrEMBL section of UniProtKB. Moreover, all valid references and experimentally verified data - present in PIR-PSD, but missing fr...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 108, "official_url": "https://www.uniprot.org/help/pir_psd", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pir_psd.md", "source_path": "pir_psd.md", "sha256": "4550445e13dc5134d82de0655a0dead4201a1850afeeb8586af2114b22789c13" }, { "slug": "pir_rules", "title": "What is PIRSR and PIRNR?", "type": "help", "categories": [ "UniProtKB", "Automatic_annotation", "Family_and_domains", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [], "excerpt": "What is PIRSR and PIRNR? PIRSR (site rule) and PIRNR (name rule) are annotation rules based on PIRSF (protein families with full-length sequence similarity). These rules are manually curated to accurately and automatically annotate protein sequences. PIRSRs annotate sequence features for sites, such as catalytic site, and binding site. PIRNRs annotations may...", "headings": [ { "level": 1, "title": "What is PIRSR and PIRNR?" }, { "level": 1, "title": "See also" } ], "word_count": 97, "official_url": "https://www.uniprot.org/help/pir_rules", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/pir_rules.md", "source_path": "pir_rules.md", "sha256": "1a35f304dbcb37c6c17eb9b835da54046e59339c34da571b30c73a943799c828" }, { "slug": "Plants", "title": "Plant protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "API", "Taxonomy" ], "excerpt": "The main goal of the Plant protein annotation project is the manual annotation of plant-specific proteins or protein families. See: How do we manually annotate a UniProtKB entry? Due to the polyploid nature of plant genomes (potato is tetraploid, wheat is hexaploid...) and to frequent genome duplications, plants are known to contain large genes families, som...", "headings": [ { "level": 1, "title": "About Arabidopsis" }, { "level": 1, "title": "About rice" } ], "word_count": 447, "official_url": "https://www.uniprot.org/help/Plants", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Plants.md", "source_path": "Plants.md", "sha256": "d87df9f769a8cf29db81c5332dd0c02991f8a3279d87ba2eb486aa798af641fa" }, { "slug": "polymorphism", "title": "Polymorphism", "type": "help", "categories": [ "Sequence", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant" ], "excerpt": "This subsection of the 'Sequence' section provides information on polymorphic variants. If the variant is associated with a disease state, the description of the latter can be found in the 'Involvement in disease' subsection. Comments on single variants are usually found in the 'Natural variant' subsection. The subsection 'Polymorphism' is used only when the...", "headings": [], "word_count": 133, "official_url": "https://www.uniprot.org/help/polymorphism", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/polymorphism.md", "source_path": "polymorphism.md", "sha256": "8466cd3b329cb232d0e3b82efa8fcf8860d0fa70f568e0408d3a228034d318e9" }, { "slug": "post-translational_modification", "title": "Post-translational modification", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Search", "Download", "PTM" ], "excerpt": "What is a post-translational modification (PTM)? A post-translational modification is a covalent processing event resulting from a proteolytic cleavage or from the addition of a modifying group to one amino acid. So far, more than 200 PTMs have been characterized. They modulate the function of most eukaryote proteins by altering their activity state, localiz...", "headings": [ { "level": 1, "title": "What is a post-translational modification (PTM)?" }, { "level": 1, "title": "Types of PTM data" }, { "level": 1, "title": "Where can PTM data be found in UniProt?" }, { "level": 2, "title": "Protein entry page" }, { "level": 2, "title": "Feature viewer" }, { "level": 1, "title": "How to download PTM data?" }, { "level": 2, "title": "Features" }, { "level": 2, "title": "Proteomics-PTM" } ], "word_count": 879, "official_url": "https://www.uniprot.org/help/post-translational_modification", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/post-translational_modification.md", "source_path": "post-translational_modification.md", "sha256": "185453e38b852118d27d0555f4cefec2c6ae72c75859fa36f31b236d4c39eb1d" }, { "slug": "privacy", "title": "1. Who controls your personal data and how to contact us?", "type": "help", "categories": [], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Structure" ], "excerpt": "title: UniProt privacy notice type: help categories: AboutUniProt,help This Privacy Notice explains what personal data is collected by the specific service you are requesting, for what purposes, how it is processed, and how we keep it secure. 1. Who controls your personal data and how to contact us? The UniProt Consortium is formed by three institutions that...", "headings": [ { "level": 1, "title": "1. Who controls your personal data and how to contact us?" }, { "level": 1, "title": "2. Which is the lawful basis for processing personal data?" }, { "level": 1, "title": "3. What personal data is collected from users of the service? How do we use this personal data?" }, { "level": 2, "title": "Website and API" }, { "level": 2, "title": "Help desk" }, { "level": 2, "title": "Bibliography Submission (Community Curation)" }, { "level": 1, "title": "4. Who will have access to your personal data?" }, { "level": 1, "title": "5. Will your personal data be transferred to third countries (i.e. countries not part of EU/EAA) and/or international organisations?" }, { "level": 1, "title": "6. How long do we keep your personal data?" }, { "level": 1, "title": "7. The joint Data Controllers provide these rights regarding your personal data" } ], "word_count": 997, "official_url": "https://www.uniprot.org/help/privacy", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/privacy.md", "source_path": "privacy.md", "sha256": "2c16b5fc6770b6fa8c5fd354dd0dd9ea1237053d24825be0735b5f364868da83" }, { "slug": "programmatic_access", "title": "Programmatic access", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Programmatic_access", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "FASTA", "Search", "API" ], "excerpt": "UniProt provides several application programming interfaces (APIs) to query and access its data programmatically: UniProt website REST API What: RESTful URLs that can be bookmarked, linked and used in programs for all entries, queries and tools available through this website. Data is available in all formats provided on the website, e.g. text, XML, RDF, FAST...", "headings": [ { "level": 1, "title": "UniProt website REST API" }, { "level": 1, "title": "Proteins REST API" }, { "level": 1, "title": "UniProt SPARQL API" }, { "level": 1, "title": "UniProt Java API" } ], "word_count": 258, "official_url": "https://www.uniprot.org/help/programmatic_access", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/programmatic_access.md", "source_path": "programmatic_access.md", "sha256": "df9b3fed0c8d7cf46d7d05012b30ba901b436ad7d8798028100282f95307c9d2" }, { "slug": "Prokaryotes", "title": "Prokaryotic protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence" ], "excerpt": "The Prokaryotic protein annotation project focuses on the manual annotation of bacterial and archaeal-specific proteins and protein families. See: How do we manually annotate a UniProtKB entry? Our major effort is currently directed towards the annotation of proteins from the already well-characterized model bacteria Escherichia coli and Bacillus subtilis, a...", "headings": [ { "level": 1, "title": "High-quality automated annotation propagation" } ], "word_count": 241, "official_url": "https://www.uniprot.org/help/Prokaryotes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Prokaryotes.md", "source_path": "Prokaryotes.md", "sha256": "7fca54983dd7ee82fd07d5aaa790ce4c04212807eaf3c82029afb43c5654f0f5" }, { "slug": "propep", "title": "Propeptide", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the PTM / Processing section describes a propeptide, which is a part of a protein that is cleaved during maturation or activation. Once cleaved, a propeptide generally has no independent biological function. Example: P29958 This subsection is only present when the existence of the propeptide has been demonstrated experimentally in the prot...", "headings": [], "word_count": 115, "official_url": "https://www.uniprot.org/help/propep", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/propep.md", "source_path": "propep.md", "sha256": "ca5dc3e62afd1b64254452e89930415935ee5d91da771afb8c9e017d22b134d7" }, { "slug": "protein_diversity", "title": "How are protein sequence variety and protein diversity represented in UniProtKB?", "type": "help", "categories": [ "UniProtKB", "Keywords", "Text_search", "Biocuration", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "Evidence", "PTM", "Variant" ], "excerpt": "The article C. R. Biol. (2005) gives an overview on cellular processes that can lead to sequence variety and structural diversity in eukaryotes. It explains, with examples, how such processes are represented in UniProtKB. This tutorial also shows how to use the UniProtKB annotation to extract specific datasets of entries, e.g.: proteins containing a selenocy...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 199, "official_url": "https://www.uniprot.org/help/protein_diversity", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/protein_diversity.md", "source_path": "protein_diversity.md", "sha256": "4c9ad27a51e60a0b96a030d475437f1487d768b2ee7bebcace61c981d4d2c243" }, { "slug": "protein_domains_and_families", "title": "Protein domains and families", "type": "help", "categories": [ "Biocuration", "Family_and_domains", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search" ], "excerpt": "The task of assigning proteins to families makes use of a range of sources including protein family databases, sequence analysis tools, scientific literature and sequence similarity search tools. UniProtKB/Swiss-Prot document: Sequence similarities: index UniProtKB/Swiss-Prot document: Uncharacterized protein families User manual: Family and Domains section ...", "headings": [], "word_count": 72, "official_url": "https://www.uniprot.org/help/protein_domains_and_families", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/protein_domains_and_families.md", "source_path": "protein_domains_and_families.md", "sha256": "ca7b44f4318986efc2984917a8e369008b80ca864c2fcf45b1f838f46ee1850d" }, { "slug": "protein_existence", "title": "Protein existence", "type": "help", "categories": [ "Protein_existence", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "This indicates the type of evidence that supports the existence of the protein. Note that the 'protein existence' evidence does not give information on the accuracy or correctness of the sequence(s) displayed. While it gives information on the existence of a protein, it may happen that the sequence slightly differs from genomic sequences, especially for sequ...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 350, "official_url": "https://www.uniprot.org/help/protein_existence", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/protein_existence.md", "source_path": "protein_existence.md", "sha256": "c94dbee23a15a24c789cbb7333d6871a66364506f2b6f2ca1fb3f24756e9cf52" }, { "slug": "protein_names", "title": "Protein names", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section provides an exhaustive list of all names of the protein, from commonly used to obsolete, to allow unambiguous identification of a protein. This subsection also includes information on the activity of the protein, such as a precise description of the catalytic mechanism of enzymes, or information about individ...", "headings": [ { "level": 1, "title": "UniProtKB/Swiss-Prot 'Protein names' subsection" }, { "level": 1, "title": "UniProtKB/TrEMBL 'Protein names' subsection" }, { "level": 1, "title": "Related documents" } ], "word_count": 495, "official_url": "https://www.uniprot.org/help/protein_names", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/protein_names.md", "source_path": "protein_names.md", "sha256": "73534c9b8e98a2459cb8bed783ecc28c5be268ad10f05559902596aa0d7ec59f" }, { "slug": "proteome", "title": "What are proteomes?", "type": "help", "categories": [ "Proteomes", "UniProtKB", "Keywords", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Download", "API", "Evidence", "Taxonomy" ], "excerpt": "UniProt provides proteome sets of proteins whose genomes have been completely sequenced. What is a proteome? A proteome is the set of proteins thought to be expressed by an organism. The majority of the UniProt proteomes are based on the translation of a sequenced genome, and will normally include sequences that derive from extra-chromosomal elements such as...", "headings": [ { "level": 1, "title": "What is a proteome?" }, { "level": 1, "title": "What is the curation status of UniProt proteomes?" }, { "level": 1, "title": "What is the source of the sequences for proteomes?" }, { "level": 2, "title": "See also" }, { "level": 1, "title": "Which sequenced genomes are available as proteomes at UniProt?" }, { "level": 2, "title": "See also" }, { "level": 1, "title": "How to retrieve proteomes?" }, { "level": 1, "title": "How can I download proteomes?" }, { "level": 1, "title": "See also" } ], "word_count": 1109, "official_url": "https://www.uniprot.org/help/proteome", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome.md", "source_path": "proteome.md", "sha256": "f4565a3a4f6ad4db9d4131fcc65878d4caa968a7dab869432be497dfb6f6660a" }, { "slug": "proteome_component", "title": "Proteome component", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome" ], "excerpt": "A UniProt proteome can consist of several components. The component name refers to the genomic component encoding a set of proteins. These range from a single component such as Viral genomes to several components as in the case of eukaryotic chromosomes. They may also represent different stages in a genome project and include components such as contigs, scaf...", "headings": [], "word_count": 65, "official_url": "https://www.uniprot.org/help/proteome_component", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_component.md", "source_path": "proteome_component.md", "sha256": "ac15e324e7cf178a6a6c34c9494bb9bee4727c7549e0a1da81eca5cf49c1d46e" }, { "slug": "proteome_exclusion_reasons", "title": "Reasons to exclude a proteome from UniProtKB", "type": "help", "categories": [ "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Taxonomy" ], "excerpt": "UniProt excludes certain proteomes where the assembly has been excluded from the NCBI Reference Sequence (RefSeq) project for any of the reasons listed below. This list is a subset of the exclusion reasons used by RefSeq, complemented by a number of exclusion reasons defined by UniProt. The exclusion reason is provided in the proteome page for an excluded pr...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 477, "official_url": "https://www.uniprot.org/help/proteome_exclusion_reasons", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_exclusion_reasons.md", "source_path": "proteome_exclusion_reasons.md", "sha256": "22888f845ea13f6fbec9d5cc17966b3607306381ae445c995f5c79f4561e8bcf" }, { "slug": "proteome_id", "title": "Proteome identifier", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome" ], "excerpt": "The proteome identifier (UPID) is the unique identifier assigned to the set of proteins that constitute the proteome. It consists of the characters 'UP' followed by 9 digits, is stable across releases and can therefore be used to cite a UniProt proteome. UniProtKB entries can be linked to one or more UPIDs. UPIDs generally correspond to one genome assembly, ...", "headings": [], "word_count": 81, "official_url": "https://www.uniprot.org/help/proteome_id", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_id.md", "source_path": "proteome_id.md", "sha256": "620f079e0fc97757599f0eac3d21f6e291a8a7f5b2beec6c502e0e74dd203fad" }, { "slug": "proteome_redundancy", "title": "Reducing proteome redundancy", "type": "help", "categories": [ "Proteomes", "UniProtKB", "UniParc", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome" ], "excerpt": "Methods to reduce proteome redundancy have been in effect since release 201504. These methods were aimed at reducing the number of proteins in the UniProt Knowledgebase (UniProtKB) from redundant proteomes, in which all or nearly all protein sequences are highly similar or identical to an existing proteome from the same species. Reducing proteins from redund...", "headings": [], "word_count": 139, "official_url": "https://www.uniprot.org/help/proteome_redundancy", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_redundancy.md", "source_path": "proteome_redundancy.md", "sha256": "e26c377e45af829bb1054f67fe9adb647b5b0ff09ca05ed4f03aae6ab54aa5f5" }, { "slug": "proteome_redundancy_faq", "title": "What is a redundant proteome? Can reference proteomes become redundant? Can reviewed UniProtKB (Swiss-Prot) entries be deleted when a proteome becomes redundant?", "type": "help", "categories": [ "Proteomes", "UniProtKB", "UniParc", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence" ], "excerpt": "Methods to reduce proteome redundancy have been in effect since release 201504. These methods were aimed at reducing the number of proteins in the UniProt Knowledgebase (UniProtKB) from redundant proteomes, in which all or nearly all protein sequences are highly similar or identical to an existing proteome from the same species. Reducing proteins from redund...", "headings": [], "word_count": 139, "official_url": "https://www.uniprot.org/help/proteome_redundancy_faq", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_redundancy_faq.md", "source_path": "proteome_redundancy_faq.md", "sha256": "44679721193d882258b73c49b2ce5e9ca123437593f9672d051d1d5004fc8997" }, { "slug": "proteome_similarity", "title": "Proteome similarity score", "type": "help", "categories": [ "Proteomes", "UniProtKB", "Keywords", "Sequence" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Sequence tools", "Taxonomy" ], "excerpt": "What is the proteome similarity score? In cases where there are multiple proteomes for a given species, the proteome similarity score indicates how similar a proteome is to the reference proteome(s) of that species. How can the proteome similarity score be used? The score can be used to determine how similar a given proteome (non-reference or reference, but ...", "headings": [ { "level": 1, "title": "What is the proteome similarity score?" }, { "level": 1, "title": "How can the proteome similarity score be used?" }, { "level": 1, "title": "What proteomes have a similarity score?" }, { "level": 1, "title": "How is the proteome similarity score calculated?" }, { "level": 1, "title": "Where to find the proteome similarity score" } ], "word_count": 559, "official_url": "https://www.uniprot.org/help/proteome_similarity", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_similarity.md", "source_path": "proteome_similarity.md", "sha256": "57d07841dfa45ce15ea231c9142f2c1759bfa5f4219ce6d3f06b5b87a447444f" }, { "slug": "proteome_terminology", "title": "Proteome terminology", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Download", "Taxonomy" ], "excerpt": "A proteome is the set of proteins thought to be expressed by an organism. Proteome status There are 3 proteome status categories: reference proteome and non-reference proteome, which are assigned based on the reference proteome selection workflow, and excluded proteomes. Number of entries Number of UniProtKB entries for reference proteomes, or UniParc entrie...", "headings": [ { "level": 2, "title": "Proteome status" }, { "level": 2, "title": "Number of entries" }, { "level": 2, "title": "Gene count" }, { "level": 2, "title": "Genome Assembly" } ], "word_count": 208, "official_url": "https://www.uniprot.org/help/proteome_terminology", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteome_terminology.md", "source_path": "proteome_terminology.md", "sha256": "ec4610e390d3ea03e33d81591773d41d2f06c62e417256c03bc6a6c44e38b192" }, { "slug": "proteomes_manual", "title": "Proteomes", "type": "help", "categories": [ "Proteomes", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section is present for entries that are part of a proteome, i.e. of a set of proteins thought to be expressed by organisms whose genomes have been completely sequenced. A UniProt entry can be linked to one or more proteomes. For each proteome, the information displayed in this section consists of a proteome ID (UPID)...", "headings": [], "word_count": 67, "official_url": "https://www.uniprot.org/help/proteomes_manual", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteomes_manual.md", "source_path": "proteomes_manual.md", "sha256": "2fdce37e2cd9948483a54ff3ab669bfd9193f210a1dd86e99cbb990a0014cd67" }, { "slug": "proteomics", "title": "Mass spectrometry-based proteomics data in UniProtKB", "type": "help", "categories": [ "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Download", "Evidence", "PTM", "Variant" ], "excerpt": "Data from high-throughput proteomics experiments constitute a rich potential source of annotations for UniProtKB, providing supporting evidence for the existence of specific protein isoforms and post-translational modifications. However, a number of challenges exist for integrating high-throughput proteomics data in UniProtKB. Publications and dataset report...", "headings": [ { "level": 1, "title": "1. Data from public mass spectrometry-based proteomics resources" }, { "level": 1, "title": "2. Mass spectrometry-based proteomics data from the scientific literature" }, { "level": 1, "title": "3. Human Proteome Project" }, { "level": 1, "title": "4. Post-translational modification (PTM) data derived from large scale mass spectrometry (MS) datasets" } ], "word_count": 1055, "official_url": "https://www.uniprot.org/help/proteomics", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/proteomics.md", "source_path": "proteomics.md", "sha256": "0002e3e0c7f83ddd917ec328466e436d28ab3333f6e6924091b4a13da5d320aa" }, { "slug": "ProtNLM", "title": "Automatic annotation using ProtNLM", "type": "help", "categories": [ "UniProtKB", "Automatic_annotation", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Download", "Evidence", "Structure", "Taxonomy" ], "excerpt": "UniProt’s Automatic Annotation pipeline enhances unreviewed/TrEMBL UniProtKB entries with automatic classification and annotation. UniProt leverages machine learning / artificial intelligence (AI) using a Protein Natural Language Model (ProtNLM) developed by collaborators at Google DeepMind. ProtNLM was originally used to predict protein names but has now be...", "headings": [ { "level": 1, "title": "ProtNLM methodology" }, { "level": 1, "title": "Timeline of ProtNLM generated data in UniProt" }, { "level": 1, "title": "ProtNLM2: expanding annotation beyond protein names" }, { "level": 1, "title": "ProtNLM2 prediction quality assessment" }, { "level": 2, "title": "ProtNLM model score" }, { "level": 2, "title": "Post-processing corroboration strategy" }, { "level": 3, "title": "Corroboration by sequence similarity" }, { "level": 3, "title": "Corroboration by structural similarity" }, { "level": 2, "title": "Summary of prediction exclusion criteria" }, { "level": 1, "title": "Accessing ProtNLM annotated data" }, { "level": 2, "title": "FTP download" }, { "level": 2, "title": "On the website" }, { "level": 2, "title": "Interpreting prediction evidence information" }, { "level": 1, "title": "Links" } ], "word_count": 1168, "official_url": "https://www.uniprot.org/help/ProtNLM", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ProtNLM.md", "source_path": "ProtNLM.md", "sha256": "18e34ceeb10f59990e448b12fbe374c271a3e4578d78d03b5efc8debd2e960ad" }, { "slug": "ptm_processing_section", "title": "PTM / Processing section", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This section describes post-translational modifications (PTMs) and/or processing events. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Initiator methionine | Cleaved initiator methionine | | Signal | Sequence targeting proteins to the secretory pathway or periplasmic ...", "headings": [], "word_count": 159, "official_url": "https://www.uniprot.org/help/ptm_processing_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ptm_processing_section.md", "source_path": "ptm_processing_section.md", "sha256": "9fb6e267d24208adccde74a53e9c96f1766dce141b6b1f4ed671382e726dfb12" }, { "slug": "publications", "title": "Publications on UniProt", "type": "help", "categories": [ "About_UniProt", "Publications", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API", "Variant" ], "excerpt": "How to cite us If you find UniProt useful, please consider citing our latest publication: The UniProt Consortium UniProt: the Universal Protein Knowledgebase in 2025 Nucleic Acids Res. 53:D609–D617 (2025) ...or choose the publication that best covers the UniProt aspects or components you used in your work: 2025 Ahmad S, da Costa Gonzales L J, Bowler-Barnett ...", "headings": [ { "level": 1, "title": "How to cite us" }, { "level": 2, "title": "2025" }, { "level": 2, "title": "2023" }, { "level": 2, "title": "2021" }, { "level": 2, "title": "2020" }, { "level": 2, "title": "2019" }, { "level": 2, "title": "2018" }, { "level": 2, "title": "2017" }, { "level": 2, "title": "2016" }, { "level": 2, "title": "2015" }, { "level": 2, "title": "2014" }, { "level": 2, "title": "2013" }, { "level": 2, "title": "2012" }, { "level": 2, "title": "2011" }, { "level": 2, "title": "2010" }, { "level": 2, "title": "2009" }, { "level": 2, "title": "2008" }, { "level": 2, "title": "2007" }, { "level": 2, "title": "2006" }, { "level": 2, "title": "2005" }, { "level": 2, "title": "2004" }, { "level": 2, "title": "2003 and earlier" } ], "word_count": 4169, "official_url": "https://www.uniprot.org/help/publications", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/publications.md", "source_path": "publications.md", "sha256": "e46c4487296731aff4a8c453bc5050344875a531ff9666353d7cd79e4bb5271d" }, { "slug": "publications_section", "title": "Publications section", "type": "help", "categories": [ "Publications", "manual" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [ "Search", "API" ], "excerpt": "The set of publications fully curated in UniProtKB/Swiss-Prot and publications imported in UniProtKB/TrEMBL is complemented by additional publications that have been computationally mapped from other resources to UniProtKB entries, as well as by community-submitted publications. The publications from multiple sources are shown in the \"Publications\" view, whi...", "headings": [ { "level": 1, "title": "1. Number" }, { "level": 1, "title": "2. Title" }, { "level": 1, "title": "3. Author(s) names" }, { "level": 1, "title": "4. Reference information" }, { "level": 2, "title": "a) Journal citations" }, { "level": 2, "title": "b) Electronic publications" }, { "level": 2, "title": "c) Book citations" }, { "level": 2, "title": "d) Unpublished observations" }, { "level": 2, "title": "e) Thesis" }, { "level": 2, "title": "f) Patent applications" }, { "level": 2, "title": "g) Submissions" }, { "level": 1, "title": "5. Cross-references" }, { "level": 1, "title": "6. Cited for" }, { "level": 1, "title": "7. Sequence origin" }, { "level": 1, "title": "Expertly curated bibliography" }, { "level": 2, "title": "Where to find expertly curated bibliography" }, { "level": 1, "title": "Additional bibliography" }, { "level": 2, "title": "Where to find additional bibliography" }, { "level": 1, "title": "Community-submitted bibliography" }, { "level": 1, "title": "Related documents" } ], "word_count": 2326, "official_url": "https://www.uniprot.org/help/publications_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/publications_section.md", "source_path": "publications_section.md", "sha256": "23fd5fd349c9b6baa315055d8cd0d537a83b11c4991c941ee324eff2f7d62ad2" }, { "slug": "query-fields", "title": "UniProtKB query fields", "type": "help", "categories": [ "Text_search", "Technical", "Website", "help" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "API", "Structure" ], "excerpt": "Since July 2021, we are providing a new API to access UniProt's data and tools. This replaces the services previously provided and you might have to update any workflow or scripts written before that date. Supported query fields for searching specific data in UniProtKB (see also query syntax) are shown in the table below. General annotation (comment) and Seq...", "headings": [], "word_count": 975, "official_url": "https://www.uniprot.org/help/query-fields", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/query-fields.md", "source_path": "query-fields.md", "sha256": "05378752751905946bee385a4ad90011b3182bdb72150837a4bfeafc60b8285e" }, { "slug": "redundancy", "title": "How redundant are the UniProt databases?", "type": "help", "categories": [ "UniParc", "UniProtKB", "Sequence", "UniRef", "Biocuration", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Variant" ], "excerpt": "Each of the 3 UniProt databases - UniProtKB (Swiss-Prot and TrEMBL), UniParc and UniRef - are 'non-redundant'. However, the definition of 'redundancy' varies among the 3. Summary Non-redundancy means in: UniProtKB/TrEMBL: one record for 100% identical full-length sequences in one species; UniProtKB/Swiss-Prot: one record per gene in one species; UniParc: one...", "headings": [ { "level": 1, "title": "Summary" }, { "level": 1, "title": "UniProtKB" }, { "level": 2, "title": "See also" }, { "level": 2, "title": "Remarks" }, { "level": 1, "title": "UniParc" }, { "level": 1, "title": "UniRef" } ], "word_count": 574, "official_url": "https://www.uniprot.org/help/redundancy", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/redundancy.md", "source_path": "redundancy.md", "sha256": "92e3fc300504c3dc2534a9a80f5dd04494ae8d8335b8f82da98c52fddcac636f" }, { "slug": "ref_proteomes_workflow", "title": "How are reference proteomes selected?", "type": "help", "categories": [ "Proteomes", "UniProtKB", "Keywords", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Taxonomy" ], "excerpt": "UniProt selects reference proteomes for all species, to provide users with the best quality data in the UniProt Knowledgebase (UniProtKB) and the Proteomes resource. Reference proteomes are selected from all proteomes for a given species using a combination of automatic and manual selection methods. For each species, the minimum number of reference proteomes...", "headings": [ { "level": 1, "title": "Summary" }, { "level": 1, "title": "Reference proteomes workflow" }, { "level": 1, "title": "FAQs" }, { "level": 2, "title": "Why are some VMR genomes from ICTV missing as reference proteomes in UniProt?" }, { "level": 2, "title": "Why is my genome assembly not associated with a reference proteome in UniProt?" }, { "level": 2, "title": "Why do some species have more than one reference proteome?" }, { "level": 2, "title": "Is the reference proteome set stable from release to release?" }, { "level": 2, "title": "If a reference proteome is demoted to non-reference proteome, what happens to its proteins?" } ], "word_count": 935, "official_url": "https://www.uniprot.org/help/ref_proteomes_workflow", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/ref_proteomes_workflow.md", "source_path": "ref_proteomes_workflow.md", "sha256": "bd62fdc36ba92c931ba8456cf7c7ca0b78535fb3f7847c5f3c38e7480755b4ea" }, { "slug": "reference_proteome", "title": "What are reference proteomes?", "type": "help", "categories": [ "Proteomes", "Taxonomy", "UniProtKB", "Keywords", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Download", "API", "Taxonomy" ], "excerpt": "Proteomes UniProt provides several sets of proteins thought to be expressed by organisms whose genomes have been completely sequenced, termed \"proteomes\". As more and more genomes of the same organism are being sequenced, we introduced unique proteome identifiers to distinguish individual proteomes from the same taxonomy identifier. These proteomes can be qu...", "headings": [ { "level": 1, "title": "Proteomes" }, { "level": 1, "title": "Reference proteomes" }, { "level": 1, "title": "Reference proteome download" }, { "level": 1, "title": "See also" } ], "word_count": 269, "official_url": "https://www.uniprot.org/help/reference_proteome", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/reference_proteome.md", "source_path": "reference_proteome.md", "sha256": "2febcc0c5a89b637d5a76416c861b16709ce771c67e941709fdb099897f6ba14" }, { "slug": "refprot_only_changes", "title": "A quick summary of proteomes changes", "type": "help", "categories": [ "Proteomes", "Taxonomy", "UniProtKB" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence", "Taxonomy" ], "excerpt": "As of release 202602 (May 2026) a comprehensive package of changes to our reference proteome workflow will be complete. The changes will affect how reference proteomes are selected and also what protein entries are included in UniProtKB. A comprehensive list of affected protein entries and proteomes is available here. See below a summary of the changes imple...", "headings": [ { "level": 1, "title": "Our current release" }, { "level": 2, "title": "Release 202602" }, { "level": 1, "title": "Past releases" }, { "level": 2, "title": "Release 202601" }, { "level": 2, "title": "Release 202504" }, { "level": 1, "title": "Further documentation" }, { "level": 1, "title": "FAQs" }, { "level": 2, "title": "How are bacterial strains being taken into account by the new reference proteome selection workflow?" }, { "level": 2, "title": "How would having one reference proteome per species be applied to virus isolates?" }, { "level": 2, "title": "How will entries removed by this change be identified in UniParc?" } ], "word_count": 778, "official_url": "https://www.uniprot.org/help/refprot_only_changes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/refprot_only_changes.md", "source_path": "refprot_only_changes.md", "sha256": "1466d8d31d1dd150add56f74e73e4744f7bc8fd2c652db3334bbf05a85b0f080" }, { "slug": "region", "title": "Region", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API" ], "excerpt": "This subsection of the 'Family and Domains' section describes a region of interest that cannot be described in other subsections. It may be used to describe characteristics of a region that have been experimentally defined, such as the role of a region in mediating protein-protein interactions or some other biological process, to describe the different regio...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 92, "official_url": "https://www.uniprot.org/help/region", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/region.md", "source_path": "region.md", "sha256": "61fe4cda51321303a23af1885846a54fba0ffdfc59165a6ac05757b2d973bf06" }, { "slug": "regular_downloads", "title": "How can I download data at every UniProt release?", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Download", "Technical", "Release", "faq" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API" ], "excerpt": "If the data sets you need are available on our ftp site, we recommend that you download them from there. Other data sets can be downloaded by querying this website (read how to retrieve entries via queries programmatically), but please use check the release associated with your requested data in the HTTP header x-uniprot-release to avoid download the same da...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 116, "official_url": "https://www.uniprot.org/help/regular_downloads", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/regular_downloads.md", "source_path": "regular_downloads.md", "sha256": "459046f7b25627d027585f2687a57d99aeeef1abb0cf4b8fba9fa351a1f36c92" }, { "slug": "release-statistics", "title": "Release statistics", "type": "help", "categories": [ "Release", "statistics" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [ "Download" ], "excerpt": "UniProtKB statistics of the current release UniProtKB (Swiss-Prot & TrEMBL) statistics UniProtKB statistics of previous releases are available from our FTP server Release YYYYNN statistics can be found in the directory: Examples: UniProtKB/Swiss-Prot statistics for release 201701: https://ftp.uniprot.org/pub/databases/uniprot/previousreleases/release-201701/...", "headings": [ { "level": 1, "title": "UniProtKB statistics of the current release" }, { "level": 1, "title": "UniProtKB statistics of previous releases are available from our FTP server" } ], "word_count": 67, "official_url": "https://www.uniprot.org/help/release-statistics", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/release-statistics.md", "source_path": "release-statistics.md", "sha256": "a95fa4948178b07d00cad65feebf82a772ab3ab314b27b8ee4732be3cfb6151c" }, { "slug": "repeat", "title": "Repeat", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Structure", "Variant" ], "excerpt": "This subsection of the 'Family and Domains' section indicates the positions and types of repeated sequence motifs or repeated domains within the protein. Repeats vary from short amino acid repetitions, such as the polyglutamine tracts of the Huntington disease gene product huntingtin, to large repetitions containing multiple domains, such as in the cytoskele...", "headings": [ { "level": 1, "title": "1. Annotation of specific repeated sequence motifs" }, { "level": 1, "title": "2. Annotation of predicted repeats" }, { "level": 1, "title": "See also" } ], "word_count": 389, "official_url": "https://www.uniprot.org/help/repeat", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/repeat.md", "source_path": "repeat.md", "sha256": "1ef8a96064a78bcc93bcf7f10b5f4d863767f04a5e2fba1f4068f2918223e708" }, { "slug": "rest-api-headers", "title": "HTTP Status Codes in the REST API", "type": "help", "categories": [ "Technical", "Website", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "This document explains the HTTP response headers returned by the UniProt REST API and gives some examples to make explicit what they mean. HTTP Status Headers HTTP statuses are standard numeric codes indicating whether a specific HTTP request successfully completed. In the following sections, we describe all status codes returned by the UniProt REST API. 200...", "headings": [ { "level": 1, "title": "HTTP Status Headers" }, { "level": 2, "title": "200 OK" }, { "level": 2, "title": "303 See Other" }, { "level": 3, "title": "UniProtKB inactive entry example:" }, { "level": 2, "title": "400 Bad request" }, { "level": 3, "title": "Missing required request parameter" }, { "level": 3, "title": "Invalid parameter value" }, { "level": 2, "title": "404 Resource not found" }, { "level": 2, "title": "500 Internal server error" }, { "level": 1, "title": "x-uniprot-release-date" }, { "level": 1, "title": "x-uniprot-release" }, { "level": 1, "title": "x-total-results" }, { "level": 1, "title": "link" } ], "word_count": 359, "official_url": "https://www.uniprot.org/help/rest-api-headers", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/rest-api-headers.md", "source_path": "rest-api-headers.md", "sha256": "7b46c66ebedca5a03d82856587d1bcf4abd3abf0d0907b4d021743cae5016eaf" }, { "slug": "retrieve_3d", "title": "How can I retrieve UniProtKB entries that have a PDB 3D structure cross-reference?", "type": "help", "categories": [ "UniProtKB", "3D_structure", "Text_search", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Structure" ], "excerpt": "Using the advanced search functionality; Select Searching in ‘UniProtKB’ In the field dropdown list, type ‘PDB’ and select the suggestion ‘Cross-references/3D structure database/PDB’ In the text box enter the value ‘’ (to find all structures) or a relevant PDB ID of interest. You will see a results table of protein entries that contain PDB 3D structure cross...", "headings": [], "word_count": 88, "official_url": "https://www.uniprot.org/help/retrieve_3d", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/retrieve_3d.md", "source_path": "retrieve_3d.md", "sha256": "42b30dd43d397346ca03dca9896a09057be577365dbf81db90ba0a68ae042835" }, { "slug": "retrieve_sets", "title": "How to retrieve sets of protein sequences?", "type": "help", "categories": [ "UniProtKB", "Sequence", "Text_search", "Download", "Technical", "Programmatic_access", "faq" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "FASTA", "Proteome", "Search", "Download", "API", "Evidence" ], "excerpt": "UniProtKB entries are available in three file formats - Text, XML and RDF/XML. UniProtKB entries in these formats each contain only one protein sequence, the so-called 'canonical' sequence. UniProtKB canonical sequences are also available in FASTA format, as are additional manually curated isoform sequences that are described in UniProtKB/Swiss-Prot. Below w...", "headings": [ { "level": 1, "title": "See also" }, { "level": 2, "title": "Retrieving sequences from the website" }, { "level": 2, "title": "Retrieving sequences from the FTP site" } ], "word_count": 375, "official_url": "https://www.uniprot.org/help/retrieve_sets", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/retrieve_sets.md", "source_path": "retrieve_sets.md", "sha256": "0780bf3d5acb1376ab0e232f1f1136dc04e16e8300505a74dff3a0936db6c63a" }, { "slug": "return_fields", "title": "UniProtKB return fields", "type": "help", "categories": [ "Text_search", "Technical", "Website", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Proteome", "Search", "API", "PTM", "Structure", "Variant", "Taxonomy" ], "excerpt": "UniProtKB column names for programmatic access This document lists the differences between the returned columns by RESTful APIs. User can ask required columns returned by an API by passing the Returned Field in the request url and the response will have those requested fields. A specific page listing cross-reference fields can be found here: Return Fields Da...", "headings": [ { "level": 1, "title": "UniProtKB column names for programmatic access" }, { "level": 1, "title": "Names & Taxonomy" }, { "level": 1, "title": "Sequences" }, { "level": 1, "title": "Function" }, { "level": 1, "title": "Miscellaneous" }, { "level": 1, "title": "Interaction" }, { "level": 1, "title": "Expression" }, { "level": 1, "title": "Gene Ontology (GO)" }, { "level": 1, "title": "Pathology & Biotech" }, { "level": 1, "title": "Subcellular location" }, { "level": 1, "title": "PTM / Processsing" }, { "level": 1, "title": "Structure" }, { "level": 1, "title": "Publications" }, { "level": 1, "title": "Date of" }, { "level": 1, "title": "Family & Domains" }, { "level": 1, "title": "Cross-references" } ], "word_count": 504, "official_url": "https://www.uniprot.org/help/return_fields", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/return_fields.md", "source_path": "return_fields.md", "sha256": "13567b27eaa1c99ea6d3bc9d30d10efea64dec1bbeb456f0b407429ae6ee85bc" }, { "slug": "return_fields_databases", "title": "UniProtKB return fields for cross-references", "type": "help", "categories": [ "Text_search", "Technical", "Website", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "Each protein entry in UniProtKB has links to cross-referenced databases, there are currently links to over 180 cross-referenced databases, a comprehensive list can be found here. Cross-references can be queried using the UniProt website REST API using the relevant results fields. For a complete list of results fields please see: https://rest.uniprot.org/conf...", "headings": [], "word_count": 211, "official_url": "https://www.uniprot.org/help/return_fields_databases", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/return_fields_databases.md", "source_path": "return_fields_databases.md", "sha256": "f95549d990bd5574ac75f175f78690465c21083c0adefe16763fb6b38a80ea34" }, { "slug": "rna_editing", "title": "RNA editing", "type": "help", "categories": [ "Sequence", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Download", "Variant" ], "excerpt": "Where can RNA editing data be found in UniProt? RNA editing data can be found in both the protein entry page and the feature viewer. Protein entry page Within the protein entry page RNA editing information can be found in the 'Sequence' section under the 'RNA editing' subsection as well as the the 'Disease/Phenotypes and variants' section under the 'Natural ...", "headings": [ { "level": 1, "title": "Where can RNA editing data be found in UniProt?" }, { "level": 2, "title": "Protein entry page" }, { "level": 2, "title": "Feature Viewer" }, { "level": 1, "title": "How to download RNA editing data?" } ], "word_count": 533, "official_url": "https://www.uniprot.org/help/rna_editing", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/rna_editing.md", "source_path": "rna_editing.md", "sha256": "313d76fbfd9a3334c12c102044ef7683586672c5e17da4fe14e8370fec3ac303" }, { "slug": "rulebase_rules", "title": "RuleBase rules", "type": "help", "categories": [ "Automatic_annotation", "Biocuration", "UniProtKB", "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [], "excerpt": "RuleBase rules are annotation rules based on protein family members, from InterPro. These rules are manually curated to accurately and automatically annotate protein sequences. RuleBase rules may include protein annotation such as recommended name, alternative name, short name, function, catalytic activity, cofactor, similarity comment, subcellular location,...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 91, "official_url": "https://www.uniprot.org/help/rulebase_rules", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/rulebase_rules.md", "source_path": "rulebase_rules.md", "sha256": "557994db8aac1fdae37e582133ebad0a02909234742f0e601ac76734797892ba" }, { "slug": "saas", "title": "SAAS (Statistical Automatic Annotation System) (Obsolete)", "type": "help", "categories": [ "Automatic_annotation", "UniProtKB", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Evidence" ], "excerpt": "UniProt's Automatic Annotation pipeline enhances the unreviewed records in UniProtKB by enriching them with automatic classification and annotation. The Statistical Automatic Annotation System SAAS used to be one of the contributors to this pipeline, but as of release 2020\\04 it has been replaced by the Association-Rule-Based Annotator (ARBA).", "headings": [], "word_count": 49, "official_url": "https://www.uniprot.org/help/saas", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/saas.md", "source_path": "saas.md", "sha256": "7344c90df872fe920add71369e9e5a6cc368a1d5d14449bd237df17800e1fcde" }, { "slug": "sab", "title": "UniProt Scientific Advisory Board (SAB)", "type": "help", "categories": [ "Staff", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search" ], "excerpt": "The UniProt project receives advice and guidance from a scientific advisory board (SAB). The UniProt SAB consists of an international collection of experts on protein biology, bioinformatics and biochemistry, both from academia and industry. Our current SAB members are: Gary Bader, The Donnelly Centre, University of Toronto Nikos Kyrpides, DOE Joint Genome I...", "headings": [], "word_count": 387, "official_url": "https://www.uniprot.org/help/sab", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sab.md", "source_path": "sab.md", "sha256": "3212b8a9191218d81523990f606d31d8d7e5009ff47d7455d9556c255b37e407" }, { "slug": "sam", "title": "SAM - Sequence Analysis Methods for automatic annotation", "type": "help", "categories": [ "help" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence" ], "excerpt": "UniProt's Automatic Annotation pipeline has been designed to enhance the unreviewed records (in UniProtKB/TrEMBL by enriching them with automatic classification and annotation. In this context, we use a suite of Sequence Analysis Methods (SAM) to annotate extra sequence-specific information, some of which are also applied to reviewed records (in UniProtKB/Sw...", "headings": [ { "level": 1, "title": "Methods" }, { "level": 1, "title": "Overlaps and sanity checks" }, { "level": 2, "title": "Transmembrane region" }, { "level": 1, "title": "See also" }, { "level": 2, "title": "Signal peptide" }, { "level": 3, "title": "See also" }, { "level": 2, "title": "Coiled coil region" }, { "level": 3, "title": "See also" }, { "level": 2, "title": "Intrinsically disordered region" }, { "level": 3, "title": "See also" } ], "word_count": 399, "official_url": "https://www.uniprot.org/help/sam", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sam.md", "source_path": "sam.md", "sha256": "ff1da327eaa89bd33f6ab8f0005512e0a528abb08f8196aac95b20122c7b39c5" }, { "slug": "sequence-alignments", "title": "Sequence Alignments", "type": "help", "categories": [ "Website", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "Download", "Sequence tools" ], "excerpt": "Overview The Align Tool aligns multiple protein or nucleotide sequences using the Clustal Omega program. This tool uses the EBI's Multiple Sequence Alignment Job Dispatcher. Where to find the Align tool You can access the Align tool directly from various sections of the UniProt website: Main toolbar: Easily accessible from the top navigation. Basket: Align m...", "headings": [ { "level": 2, "title": "Overview" }, { "level": 2, "title": "Where to find the Align tool" }, { "level": 2, "title": "Job submission form" }, { "level": 3, "title": "Input sequences" }, { "level": 3, "title": "Number of sequences per job" }, { "level": 3, "title": "Job name" }, { "level": 3, "title": "Advanced parameters" }, { "level": 2, "title": "Alignment results" }, { "level": 3, "title": "Overview tab" }, { "level": 3, "title": "Trees tab" }, { "level": 4, "title": "Key features" }, { "level": 4, "title": "Tree types" }, { "level": 4, "title": "Layout options" }, { "level": 4, "title": "Branch length options" }, { "level": 3, "title": "Percent identity matrix" }, { "level": 3, "title": "Text output" }, { "level": 3, "title": "Input parameters" }, { "level": 3, "title": "API request" }, { "level": 2, "title": "Related services" } ], "word_count": 821, "official_url": "https://www.uniprot.org/help/sequence-alignments", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence-alignments.md", "source_path": "sequence-alignments.md", "sha256": "3018da55387dfe3c1bc75cfcf54a1986e778b24fda6eb97fa51bb44605329535" }, { "slug": "sequence_annotation", "title": "Sequence annotation (Features)", "type": "help", "categories": [ "manual", "Technical" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "Download", "API", "Evidence", "PTM", "Structure" ], "excerpt": "Sequence annotations describe regions or sites of interest in the protein sequence, such as post-translational modifications, binding sites, enzyme active sites, local secondary structure or other characteristics reported in the cited references, or predicted. Sequence conflicts between references are also described in this manner. Sequence annotations (posi...", "headings": [ { "level": 1, "title": "Feature types" }, { "level": 2, "title": "Molecule processing" }, { "level": 2, "title": "Regions" }, { "level": 2, "title": "Sites" }, { "level": 2, "title": "Amino acid modifications" }, { "level": 2, "title": "Natural variations" }, { "level": 2, "title": "Experimental info" }, { "level": 2, "title": "Secondary structure" }, { "level": 1, "title": "Querying Features" }, { "level": 2, "title": "Querying for Features with experimental evidence" }, { "level": 1, "title": "Feature identifiers" }, { "level": 1, "title": "See also" } ], "word_count": 901, "official_url": "https://www.uniprot.org/help/sequence_annotation", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_annotation.md", "source_path": "sequence_annotation.md", "sha256": "cda70a40b8296a7da893b0d8602e75fb0b155992f50b7254a1cd121d3c94c529" }, { "slug": "sequence_caution", "title": "Sequence caution", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA" ], "excerpt": "This subsection of the 'Sequence' section reports difference(s) between the protein sequence shown in the UniProtKB entry and other available protein sequences derived from the same gene. The sequence discrepancies described in this subsection are generally severe and thus distinct from those that are described in the 'Sequence conflict' subsection. In this ...", "headings": [], "word_count": 365, "official_url": "https://www.uniprot.org/help/sequence_caution", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_caution.md", "source_path": "sequence_caution.md", "sha256": "f56c40e687969f17a58a8de2aea370b7dd1cc0b0f9171558e0c448c4233ca96c" }, { "slug": "sequence_length", "title": "Sequence length", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA" ], "excerpt": "This indicates the number of amino acids in the canonical sequence displayed by default in the entry's Sequence section. Related documents What is the canonical sequence? Are all isoforms described in one entry? How can I retrieve them?", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 38, "official_url": "https://www.uniprot.org/help/sequence_length", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_length.md", "source_path": "sequence_length.md", "sha256": "3ebe1e8aa57a7ed2a2d10eca276672801e3a6b02aa8daa29e7c5c26788012365" }, { "slug": "sequence_origin", "title": "Where do the UniProtKB protein sequences come from?", "type": "help", "categories": [ "UniProtKB", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "API", "Structure" ], "excerpt": "More than 95% of the protein sequences provided by UniProtKB come from the translations of coding sequences (CDS) submitted to the EMBL-Bank/GenBank/DDBJ nucleotide sequence resources (International Nucleotide Sequence Database Collaboration (INSDC)). These CDS are either generated by gene prediction programs or are experimentally proven. A protein identifie...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 414, "official_url": "https://www.uniprot.org/help/sequence_origin", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_origin.md", "source_path": "sequence_origin.md", "sha256": "4e22719015843040f5a08cf8becf71a768e89bdbf4260180940b18630dbe8c25" }, { "slug": "sequence_processing", "title": "Sequence processing", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Evidence", "PTM" ], "excerpt": "This subsection of the Sequence section indicates if the canonical sequence displayed by default in the entry is in its mature form or if it represents the precursor. The canonical sequence is a precursor If the canonical sequence requires processing to become mature, the following comment is found in the 'Sequence processing' subsection: 'The displayed sequ...", "headings": [ { "level": 1, "title": "The canonical sequence is a precursor" }, { "level": 1, "title": "Other case" } ], "word_count": 145, "official_url": "https://www.uniprot.org/help/sequence_processing", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_processing.md", "source_path": "sequence_processing.md", "sha256": "2d7305c98c62972dd01f2d78bf6b82da8d5b34c8fec99b55b352ec646ffd0c9e" }, { "slug": "sequence_similarities", "title": "Sequence similarities", "type": "help", "categories": [ "Family_and_domains", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [], "excerpt": "This subsection of the 'Family and domains' section provides information about the sequence similarity with other proteins. This subsection only states sequence similarity, thus excluding proteins with a related name that may function in the same biological pathway, but do not share sequence similarities. The 'Sequence similarities' subsection provides infor...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 113, "official_url": "https://www.uniprot.org/help/sequence_similarities", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_similarities.md", "source_path": "sequence_similarities.md", "sha256": "75505821aea512d74f466559f9c743a34d51b9d8c8c8cca3ee86af6d76d101d2" }, { "slug": "sequence_status", "title": "Sequence status", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search" ], "excerpt": "This subsection of the Sequence section indicates if the canonical sequence displayed by default in the entry is complete or not. If the sequence is complete, the term 'Complete' is used. Example: P01889 If the sequence is a fragment, the term 'Fragment' is used. Example: P29306 If the sequence is composed of several fragments, the term 'Fragments' is used (...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 151, "official_url": "https://www.uniprot.org/help/sequence_status", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequence_status.md", "source_path": "sequence_status.md", "sha256": "b9fcacf96675ab12a5728b15d1a4cafa3a106753d65e4481ddae6cec6c5dc9ce" }, { "slug": "sequences", "title": "Sequences", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "PTM" ], "excerpt": "This section displays by default the canonical protein sequence and upon request all isoforms described in the entry. It also includes information pertinent to the sequence(s), including length and molecular weight. The protein sequence displayed by default is the protein sequence to which all positional annotation refers. We call it the 'canonical' sequence...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 260, "official_url": "https://www.uniprot.org/help/sequences", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequences.md", "source_path": "sequences.md", "sha256": "3f749d4fce03ca23d91cb9b5b0b367cb6f24a1ab86cb76c728f72d6432c8084e" }, { "slug": "sequences_section", "title": "Sequence section", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Variant" ], "excerpt": "This section displays by default the canonical protein sequence and upon request all isoforms described in the entry. It also includes information pertinent to the sequence(s), including length and molecular weight. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Sequen...", "headings": [], "word_count": 287, "official_url": "https://www.uniprot.org/help/sequences_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sequences_section.md", "source_path": "sequences_section.md", "sha256": "ffe46ff6db2bc0c84ea777365b3bfb7fd0fa71a639f35730518535381fb05b7b" }, { "slug": "signal", "title": "Signal peptide", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "PTM" ], "excerpt": "This subsection of the 'PTM / Processing' section denotes the presence of an N-terminal signal peptide. Signal peptides are found in proteins that are targeted to the endoplasmic reticulum and eventually destined to be either secreted/extracellular/periplasmic/etc., retained in the lumen of the endoplasmic reticulum, of the lysosome or of any other organelle...", "headings": [ { "level": 1, "title": "1. Annotation of experimentally proven signal peptides" }, { "level": 1, "title": "2. Annotation of predicted signal peptides" }, { "level": 1, "title": "3. Annotation of Tat signal sequences in bacteria and archaea" } ], "word_count": 422, "official_url": "https://www.uniprot.org/help/signal", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/signal.md", "source_path": "signal.md", "sha256": "6c825ddcfc34ffa7fb429249fb9be8812d7c7a223f43e51eb1fe3acec54742b3" }, { "slug": "similar_proteins_section", "title": "Similar proteins section", "type": "help", "categories": [ "Similar_proteins", "manual" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [], "excerpt": "UniRef clusters This section provides links to proteins that are similar to the protein sequence(s) described in this entry at different levels of sequence identity thresholds (100%, 90% and 50%) based on their membership in UniProt Reference Clusters (UniRef). Related documents UniRef", "headings": [ { "level": 1, "title": "UniRef clusters" }, { "level": 1, "title": "Related documents" } ], "word_count": 43, "official_url": "https://www.uniprot.org/help/similar_proteins_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/similar_proteins_section.md", "source_path": "similar_proteins_section.md", "sha256": "1d928e58e379a1aebc9611476f5e8598a9e6b8b33a34117ab0cdd6e72a40c72a" }, { "slug": "site", "title": "Site", "type": "help", "categories": [ "Function", "disease_phenotypes_variants", "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "PTM", "Variant" ], "excerpt": "This subsection describes interesting single amino acid sites on the sequence that are not defined in any other subsection. This subsection can be displayed in different sections ('Function', 'PTM / Processing', 'Disease/Phenotypes and variants') according to its content. Examples: P00451, Q10471, P80969, P02730 The 'Site' subsection is frequently used for: ...", "headings": [ { "level": 1, "title": "1. Cleavage sites" }, { "level": 1, "title": "2. Inhibitory sites for proteases" }, { "level": 1, "title": "3. Breakpoint sites for fusion proteins due to chromosomal rearrangement" } ], "word_count": 144, "official_url": "https://www.uniprot.org/help/site", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/site.md", "source_path": "site.md", "sha256": "6f0b1eeb9f7bf7fd78ade48b8ec0f488788835ab1d5934641f4fe581d01227c9" }, { "slug": "software", "title": "UniProt software", "type": "help", "categories": [ "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Search", "Evidence" ], "excerpt": "Visualization ProtVista A Web Component which uses Nightingale components to display protein sequence information. URL: License: MIT License Nightingale Visualization Web Components for biological data. URL: License: MIT License Franklin pattern library React and Zurb Foundation based design system for life sciences web applications. URL: License: MIT Licens...", "headings": [ { "level": 1, "title": "Visualization" }, { "level": 1, "title": "Command-line tools" }, { "level": 1, "title": "Automatic annotation" } ], "word_count": 346, "official_url": "https://www.uniprot.org/help/software", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/software.md", "source_path": "software.md", "sha256": "d5868266211b1540a069d92f317546419201560c5039b271857044c2d97fae97" }, { "slug": "sparql", "title": "SPARQL for UniProt", "type": "help", "categories": [ "Technical", "Programmatic_access", "Text_search", "UniProtKB", "UniRef", "UniParc", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "Download", "API" ], "excerpt": "SPARQL is a W3C standardized query language for the Semantic Web. If you know SQL, it will look familiar to you and you can do similar types of queries with it. SPARQL also allows you to query and combine data from a variety of SPARQL endpoints, providing a valuable low-cost alternative to building your own data warehouse. You can combine UniProt data from s...", "headings": [], "word_count": 175, "official_url": "https://www.uniprot.org/help/sparql", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/sparql.md", "source_path": "sparql.md", "sha256": "14eafdbbd06c4292bd06aa7294886f78191664fc895579fa3d52b38c0e420f25" }, { "slug": "srs", "title": "Do I still need to use the Sequence Retrieval System (SRS)?", "type": "help", "categories": [ "UniProtKB", "UniParc", "UniRef", "Text_search", "faq" ], "module": "id-mapping", "module_label": "ID Mapping", "proteomics_topics": [ "Search", "ID mapping", "Structure", "Taxonomy" ], "excerpt": "The UniProt search tool allows users to perform Google and SRS-like queries, on UniProtKB, UniRef and UniParc \\. Note that it is also possible to upload a list of accession numbers and then perform a search in that subset. Example: Search for Saccharomyces cerevisiae membrane glycoproteins in UniProtKB Google-like queries Click the Search tab of the toolbar ...", "headings": [ { "level": 1, "title": "Google-like queries" }, { "level": 1, "title": "SRS-like queries (Advanced search)" }, { "level": 1, "title": "Queries on your personal UniProt dataset" }, { "level": 1, "title": "Examples" } ], "word_count": 309, "official_url": "https://www.uniprot.org/help/srs", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/srs.md", "source_path": "srs.md", "sha256": "8c4c48375311d34aa17c7e6390702d1ea6fdd9fe94bfda94ed803e3546dbeb20" }, { "slug": "structure_section", "title": "Structure annotation in UniProt", "type": "help", "categories": [ "3D_structure", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "PTM", "Structure", "Variant" ], "excerpt": "Why are protein structures informative? Protein structures can impart a wealth of information, for example they can: Inform the architecture of multimeric complexes, including the interactions with other proteins, nucleic acids, carbohydrates and lipids Reveal the topological arrangement and transmembrane domains Prove the existence of specific protein folds...", "headings": [ { "level": 1, "title": "Why are protein structures informative?" }, { "level": 1, "title": "Structure Section" }, { "level": 1, "title": "Experimental structures from PDB" }, { "level": 1, "title": "Structure coverage" }, { "level": 1, "title": "AlphaFold DB structural models" }, { "level": 1, "title": "3D-Beacons structural models" }, { "level": 1, "title": "Description of structure table contents" }, { "level": 1, "title": "AlphaMissense prediction of genetic variation consequence in the feature viewer" }, { "level": 1, "title": "See also" } ], "word_count": 812, "official_url": "https://www.uniprot.org/help/structure_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/structure_section.md", "source_path": "structure_section.md", "sha256": "8df06e5ebd67d0351bec1af4f3310d01c92785d1c71cfc6fa8133660b07ef9c2" }, { "slug": "structure_subseq", "title": "Why do some structures only show a portion of the protein sequence?", "type": "help", "categories": [ "UniProtKB", "3D_structure", "Text_search", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "API", "Structure" ], "excerpt": "In some cases, the structure may only include a segment of the protein sequence, in complex with ligands or other proteins. Example: P00734 is complexed with multiple inhibitors: 1A2C, 1A3B, 1A3E and 1A46. It is also possible that only a small subsequence was resolved in the structure, limited by the experimental method or/and the construct used to determine...", "headings": [], "word_count": 201, "official_url": "https://www.uniprot.org/help/structure_subseq", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/structure_subseq.md", "source_path": "structure_subseq.md", "sha256": "bbe3f8d41e82141cdbbffa44be142127bac0b4a82fa0dc737e6bf7aaf8fef6bd" }, { "slug": "subcellular_location", "title": "Subcellular location", "type": "help", "categories": [ "Subcellular_location", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "This subsection provides information on the location and the topology of the mature protein in the cell. The information contained in this subsection uses a structured hierarchy of controlled vocabulary, except for the 'Note' which allows free text. Example: Q9ULX6 The whole ontology is described, if known. Example: Q02630, P38182 The subcellular location ge...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 173, "official_url": "https://www.uniprot.org/help/subcellular_location", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/subcellular_location.md", "source_path": "subcellular_location.md", "sha256": "c800496ee091610693c93e30ff902c47716acb832254e631221e9bf61feb9bd6" }, { "slug": "subcellular_location_section", "title": "Subcellular location section", "type": "help", "categories": [ "Subcellular_location", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [], "excerpt": "This section provides information on the location and the topology of the mature protein in the cell. The information is filed in different subsections. The current subsections and their content are listed below: | Subsection | Content | | Subcellular location | Description of the subcellular location of the mature protein (including isoform locations if ava...", "headings": [], "word_count": 125, "official_url": "https://www.uniprot.org/help/subcellular_location_section", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/subcellular_location_section.md", "source_path": "subcellular_location_section.md", "sha256": "63bbccba04ae45ee96b7d50b1a99a92a12d0be7369de19f687a198676c785941" }, { "slug": "submissions", "title": "Submissions and updates", "type": "help", "categories": [ "About_UniProt", "UniProtKB", "Biocuration", "Technical", "Publications", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Sequence tools" ], "excerpt": "Sequence data flow into UniProt We import protein sequences from a range of collaborative resources during our production cycle, for more information on these sources please see our help page. UniProt creates novel protein entries for sequences imported from a variety of sources, including; Translated nucleotide sequences from ENA Direct protein sequencing u...", "headings": [ { "level": 1, "title": "Sequence data flow into UniProt" }, { "level": 1, "title": "Submitting data to UniProt" }, { "level": 1, "title": "UniProt update requests" }, { "level": 2, "title": "Associate publications and annotations to a protein entry." }, { "level": 2, "title": "Requesting corrections or entry updates." }, { "level": 2, "title": "For general feedback and queries" } ], "word_count": 398, "official_url": "https://www.uniprot.org/help/submissions", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/submissions.md", "source_path": "submissions.md", "sha256": "41a3ac56be79d515d5e0b42c1cf1afe7e4ac9b493379761be17c24ed39e38815" }, { "slug": "subunit_structure", "title": "Subunit structure", "type": "help", "categories": [ "Interaction", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "PTM", "Structure", "Taxonomy" ], "excerpt": "This subsection of the 'Interaction' section provides information about the protein quaternary structure and interaction(s) with other proteins or protein complexes (with the exception of physiological receptor-ligand interactions which are annotated in the 'Function' section). 1. Quaternary structure The composition of the quaternary structure is explicitly...", "headings": [ { "level": 1, "title": "1. Quaternary structure" }, { "level": 1, "title": "2. Protein-protein interactions" }, { "level": 1, "title": "3. Host-pathogen protein-protein interactions" }, { "level": 1, "title": "4. Protein-complex interactions" }, { "level": 1, "title": "See also" } ], "word_count": 252, "official_url": "https://www.uniprot.org/help/subunit_structure", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/subunit_structure.md", "source_path": "subunit_structure.md", "sha256": "5a7197f32d1b7e65997ca4dbd748452a9c00045ee089bfbf38964e16944da551" }, { "slug": "synchronization", "title": "UniProt release cycle", "type": "help", "categories": [ "UniProtKB", "UniRef", "UniParc", "Cross-references", "Download", "Release", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Download" ], "excerpt": "How frequently is UniProt released? UniProt releases are published every 2-3 months, with possible exceptions in January and summer due to reduced staff during holiday periods. The current release number format is YYYY\\XX where YYYY is the calendar year and XX a 2-digit number that is incremented for each release of a given year, e.g. 2025\\04, 2026\\01, etc. ...", "headings": [ { "level": 1, "title": "How frequently is UniProt released?" }, { "level": 1, "title": "What is the synchronization delay with other databases?" }, { "level": 1, "title": "Can I gain access to previous releases?" } ], "word_count": 243, "official_url": "https://www.uniprot.org/help/synchronization", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/synchronization.md", "source_path": "synchronization.md", "sha256": "d26f47cabb4e6bbd868060f114d33dfb098b322d4c2de41ff0a0b8f43f104f77" }, { "slug": "taxonomic_identifier", "title": "Taxonomic identifier", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section shows the unique identifier assigned by the NCBI to the source organism of the protein. This is known as the 'taxonomic identifier' or 'taxid'. A 'taxonomic identifier' consists of one to seven digits. The NCBI provides unique taxonomic identifiers for all organisms (taxons) that are represented in the intern...", "headings": [], "word_count": 128, "official_url": "https://www.uniprot.org/help/taxonomic_identifier", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/taxonomic_identifier.md", "source_path": "taxonomic_identifier.md", "sha256": "9356f624b17552a25b76d499ce9e186b59783e7cc7bd2e2de0a8535c9dd3d6cb" }, { "slug": "taxonomic_lineage", "title": "Taxonomic lineage", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section contains the taxonomic hierarchical classification lineage of the source organism. It lists the nodes as they appear top-down in the taxonomic tree, with the more general grouping listed first. The taxonomy classification is maintained at the NCBI and is used by the nucleotide sequence databases (EMBL/GenBank...", "headings": [], "word_count": 143, "official_url": "https://www.uniprot.org/help/taxonomic_lineage", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/taxonomic_lineage.md", "source_path": "taxonomic_lineage.md", "sha256": "20bc7f9e7384b833c43f677662431bee896a319899442004eec3306dc9c3c570" }, { "slug": "taxonomy", "title": "Taxonomy", "type": "help", "categories": [ "Taxonomy", "Controlled_vocabulary", "help" ], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [ "Search", "API", "Evidence", "Taxonomy" ], "excerpt": "The taxonomy database that is maintained by the UniProt group is based on the NCBI taxonomy database, which is supplemented with data specific to the UniProt Knowledgebase (UniProtKB). While the NCBI taxonomy is updated daily to be in sync with GenBank/EMBL-Bank/DDBJ, the UniProt taxonomy is updated only at UniProt releases to be in sync with UniProtKB. It m...", "headings": [ { "level": 1, "title": "Search" }, { "level": 1, "title": "Organism denomination" }, { "level": 1, "title": "Organism mnemonic" }, { "level": 1, "title": "Other organism names" }, { "level": 1, "title": "Lineage and taxonomy node rank" }, { "level": 1, "title": "Organism strains" }, { "level": 1, "title": "Viral hosts" } ], "word_count": 1153, "official_url": "https://www.uniprot.org/help/taxonomy", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/taxonomy.md", "source_path": "taxonomy.md", "sha256": "84391ef595c7107fc135af04e5ca28f48a2b49ef99e0c48042efbd3e4368c794" }, { "slug": "technical", "title": "Technical corner", "type": "help", "categories": [ "Technical", "Programmatic_access", "UniProtKB", "Website", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "FASTA", "Search", "API" ], "excerpt": "UniProt online tutorial Online tutorial about the UniProt databases and website. UniProtKB entry view manual User manual for the UniProtKB entry view (list of articles). UniProtKB flat file manual User manual for the UniProtKB flat file format. UniProt XML schemas XSD files for the UniProt databases. UniProt RDF schema ontology OWL file for the UniProt datab...", "headings": [], "word_count": 147, "official_url": "https://www.uniprot.org/help/technical", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/technical.md", "source_path": "technical.md", "sha256": "c60f7b0fcefcc29533c8be60a4bdda976c088d96bfe885f9fa12465a76ac098d" }, { "slug": "text-search", "title": "Text search", "type": "help", "categories": [ "Website", "Technical", "Text_search", "Programmatic_access", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "You can use the search bar in the UniProt banner at the top of all pages to search the various data sets provided by the UniProt Consortium. There is a drop-down list that allows to select the data set. To search one of the UniProt resources proceed as follows: 1. select the appropriate data set (the default selection is UniProtKB), 2. type in your query and...", "headings": [ { "level": 1, "title": "Query syntax" }, { "level": 1, "title": "Query builder" }, { "level": 1, "title": "See also" } ], "word_count": 504, "official_url": "https://www.uniprot.org/help/text-search", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/text-search.md", "source_path": "text-search.md", "sha256": "7e4d76b6b09c1407e4652d820b8b95ac897987cb8902066a4ae3b922872c3629" }, { "slug": "thomas", "title": "Paul D. Thomas", "type": "help", "categories": [ "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search" ], "excerpt": "Group Leader Swiss-Prot E-mail: paul.thomas  [at]  sib.swiss SIB Swiss Institute of Bioinformatics CMU, Rue Michel Servet, 1 CH-1211 Geneva Switzerland Phone: +41 (0)22 379 58 22 Short biography Dr. Paul D. Thomas joined the Swiss-Prot group as co-director in 2025. He has over 30 years of experience in computational biology and biomedical data resources. Tra...", "headings": [ { "level": 1, "title": "Short biography" }, { "level": 1, "title": "Group" } ], "word_count": 272, "official_url": "https://www.uniprot.org/help/thomas", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/thomas.md", "source_path": "thomas.md", "sha256": "5a05d05cb063035e46d00a986eef4207afc7bdc884926d79d25ab5453709c8d8" }, { "slug": "tissue_specificity", "title": "Tissue specificity", "type": "help", "categories": [ "Expression", "manual" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [ "Taxonomy" ], "excerpt": "This subsection of the 'Expression' section provides information on the expression of a gene at the mRNA or protein level in cells or in tissues of multicellular organisms. By default, the information is derived from experiments at the mRNA level, unless specified 'at protein level'. Examples: P92958, Q8TDN4, O14734 The documented absence of a given gene pro...", "headings": [], "word_count": 271, "official_url": "https://www.uniprot.org/help/tissue_specificity", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/tissue_specificity.md", "source_path": "tissue_specificity.md", "sha256": "cb47bf6928e31b1c3e3049517311ccfbb961bdc1f292f2346d8144c19b01beea" }, { "slug": "topo_dom", "title": "Topological domain", "type": "help", "categories": [ "Subcellular_location", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence" ], "excerpt": "This subsection of the 'Subcellular location' section describes the subcellular compartment where each non-membrane region of a membrane-spanning protein is found. Topological domains are annotated according to a controlled vocabulary, the elements of which are listed below. Common topological domains Chloroplast intermembrane Cytoplasmic Extracellular Intra...", "headings": [ { "level": 1, "title": "1. Annotation of experimentally proven topological domains:" }, { "level": 1, "title": "2. Annotation of predicted topological domains:" }, { "level": 1, "title": "See also" } ], "word_count": 532, "official_url": "https://www.uniprot.org/help/topo_dom", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/topo_dom.md", "source_path": "topo_dom.md", "sha256": "83b5b8398edb9e3d4e208a399a9557b31119cfeee500cc34bb5a6ede6193a837" }, { "slug": "toxic_dose", "title": "Toxic dose", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Variant" ], "excerpt": "This subsection of the 'Disease/Phenotypes and variants' section describes the lethal dose (LD), paralytic dose (PD), effect dose (ED) or lethal concentration (LC) of a protein toxin. LD(50) is the amount of a toxin, given all at once, which causes the death of 50% of test animals. PD(50) is the amount of a toxin, which causes the paralysis of 50% of test an...", "headings": [], "word_count": 191, "official_url": "https://www.uniprot.org/help/toxic_dose", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/toxic_dose.md", "source_path": "toxic_dose.md", "sha256": "ba33b1b2d429de7dee9a6be9c903572047971380df8475560fd0d5591bc5022a" }, { "slug": "Toxins", "title": "Animal toxin annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Evidence", "PTM", "Taxonomy" ], "excerpt": "The animal toxin annotation project (Tox-Prot) aims to systematically annotate proteins secreted in animal venom. Among venomous animals are snakes, spiders, scorpions, cone snails, centipedes, jellyfish, insects, sea anemones, lizards, a few fish and platypuses. The project also deals with the manual annotation of toxins produced by poisonous animals that l...", "headings": [], "word_count": 210, "official_url": "https://www.uniprot.org/help/Toxins", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Toxins.md", "source_path": "Toxins.md", "sha256": "9e4fc062ad4b2d0e6e1dc0934bd10f3eb0fa13ea821f38211373891b428fac11" }, { "slug": "transit", "title": "Transit peptide", "type": "help", "categories": [ "PTM_processing", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Evidence", "PTM" ], "excerpt": "This subsection of the 'PTM / Processing' section describes the extent of a transit peptide. Transit peptides are responsible for the transport of a protein encoded by a nuclear gene to a particular organelle. To date, we report transit peptides for the following organelles: Mitochondrion Apicoplast Chromoplast Chloroplast Cyanelle Thylakoid Amyloplast Perox...", "headings": [ { "level": 1, "title": "1. Annotation of experimentally proven transit peptides:" }, { "level": 1, "title": "2. Annotation of predicted transit peptides:" }, { "level": 1, "title": "See also" } ], "word_count": 366, "official_url": "https://www.uniprot.org/help/transit", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/transit.md", "source_path": "transit.md", "sha256": "7307b8c5486d8f05f3d744fdea9dbfd49ed1d681dd411015dc966ed79b1502c8" }, { "slug": "transmem", "title": "Transmembrane", "type": "help", "categories": [ "Subcellular_location", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "This subsection of the 'Subcellular location' section describes the extent of a membrane-spanning region of the protein. It denotes the presence of both alpha-helical transmembrane regions and the membrane spanning regions of beta-barrel transmembrane proteins. In UniProtKB/Swiss-Prot, we annotate transmembrane regions, when: 1. the transmembrane regions hav...", "headings": [ { "level": 1, "title": "1. Annotation of experimentally proven transmembrane regions" }, { "level": 1, "title": "2. Annotation of predicted transmembrane regions" }, { "level": 1, "title": "3. Membrane protein topologies in UniProtKB/Swiss-Prot" }, { "level": 2, "title": "a) Single-pass transmembrane proteins" }, { "level": 2, "title": "b) Multi-pass transmembrane proteins" }, { "level": 2, "title": "c) Beta-barrel transmembrane proteins" }, { "level": 1, "title": "See also" } ], "word_count": 824, "official_url": "https://www.uniprot.org/help/transmem", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/transmem.md", "source_path": "transmem.md", "sha256": "6d7b9e000d1e6eff773acb88be1ab12cbdf703dcdd8d68b7d9af5535077d9f88" }, { "slug": "unimes", "title": "DEPRECATED UniProt Metagenomic and Environmental Sequences (UniMES)", "type": "help", "categories": [ "About_UniProt", "help" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Search", "Taxonomy" ], "excerpt": "UniMES The obsoleted UniProt Metagenomic and Environmental Sequences (UniMES) database was developed as a repository for metagenomic and environmental data. UniProt has retired UniMES as there is now a resource at the EBI that is dedicated to serving metagenomic researchers. Henceforth, we recommend using the EBI Metagenomics portal (MGnify) instead. In addi...", "headings": [ { "level": 1, "title": "UniMES" } ], "word_count": 78, "official_url": "https://www.uniprot.org/help/unimes", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/unimes.md", "source_path": "unimes.md", "sha256": "f1afa639e96318768511a738e84d9c31a1e7f09eee9faeea62232126766958cb" }, { "slug": "uniparc", "title": "UniParc", "type": "help", "categories": [ "About_UniProt", "UniParc", "Sequence", "Cross-references", "help" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Download", "Taxonomy" ], "excerpt": "The UniProt Archive (UniParc) is a comprehensive and non-redundant database of protein sequences. These sequences are sourced from public sequence databases, and each unique sequence is stored in a UniParc entry with a stable unique identifier (UPI). A UPI is never removed, changed or reassigned to a different sequence. In addition to the protein sequence, a...", "headings": [ { "level": 1, "title": "Content of an entry" }, { "level": 1, "title": "Sequence comparison" }, { "level": 1, "title": "Sequence versions" }, { "level": 1, "title": "Database cross-references" }, { "level": 1, "title": "Download" }, { "level": 1, "title": "Data sources" } ], "word_count": 630, "official_url": "https://www.uniprot.org/help/uniparc", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniparc.md", "source_path": "uniparc.md", "sha256": "d9d2dc9e564c8a68dac3f109ea83f4b2e83e9aa1923c5439c4eda369fb5a44f5" }, { "slug": "uniparc_data_resources", "title": "What data resources are included in UniParc?", "type": "help", "categories": [ "UniParc", "Cross-references", "faq" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [], "excerpt": "UniParc contains protein sequences from many publicly available databases. A complete list of these databases (including discontinued resources) is available from the UniParc help page.", "headings": [], "word_count": 25, "official_url": "https://www.uniprot.org/help/uniparc_data_resources", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniparc_data_resources.md", "source_path": "uniparc_data_resources.md", "sha256": "7004691244733ff79327dbffd4d5c97adf53612efa2a8d7fa36d93ba6de02a32" }, { "slug": "uniparc_id", "title": "Uniparc Id", "type": "help", "categories": [], "module": "release", "module_label": "版本、提交与支持", "proteomics_topics": [], "excerpt": "title: UniParc identifier type: help categories: UniParc,manual The UniParc identifier (UPI) is the unique identifier assigned to a distinct protein sequence in UniParc. It consists of the characters “UPI” followed by 10 hexadecimal characters (0–9, A–F). A UPI is stable across releases, and can therefore be used to cite a protein sequence in UniParc. Exampl...", "headings": [], "word_count": 71, "official_url": "https://www.uniprot.org/help/uniparc_id", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniparc_id.md", "source_path": "uniparc_id.md", "sha256": "ea3cae4f10d6083030dce850e8d358338912e15ded01fe2411af7d8148d55aa2" }, { "slug": "uniparc_sequence_annotation_pages", "title": "UniParc Sequence Annotation Pages", "type": "help", "categories": [ "UniParc", "Cross-references", "Sequence", "Automatic_annotation" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Download", "Sequence tools", "Taxonomy" ], "excerpt": "The UniParc Sequence Annotation Page is a dedicated annotation page as an alternative for the deleted TrEMBL entries and for active entries from external source databases found within a UniParc entry. It shows the protein sequence data for a source-database record together with automatically predicted sequence annotations generated by UniRule and ARBA rules....", "headings": [ { "level": 1, "title": "How to navigate to a Sequence Annotation Page" }, { "level": 1, "title": "What is shown on a Sequence Annotation Page?" }, { "level": 2, "title": "Entry tab" }, { "level": 3, "title": "Summary information from UniParc" }, { "level": 3, "title": "UniProtKB-like sections" }, { "level": 4, "title": "Precomputed Annotation" }, { "level": 4, "title": "Annotation via UniFire" }, { "level": 2, "title": "Feature viewer tab" }, { "level": 1, "title": "Related help" } ], "word_count": 795, "official_url": "https://www.uniprot.org/help/uniparc_sequence_annotation_pages", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniparc_sequence_annotation_pages.md", "source_path": "uniparc_sequence_annotation_pages.md", "sha256": "1667d00dc6812ce0d947c036da6cb30314eb221e5dc2f3052efb1a0304b6ade6" }, { "slug": "uniprot_data", "title": "Where does UniProt data come from?", "type": "help", "categories": [ "Get_started", "faq" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Evidence", "Structure" ], "excerpt": "UniProt provides both sequence data and associated functional information, derived from a range of sources. More than 95% of the protein sequences provided by UniProtKB come from the translations of coding sequences (CDS) submitted to the ENA/GenBank/DDBJ nucleotide sequence resources of the International Nucleotide Sequence Database Collaboration (INSDC). T...", "headings": [ { "level": 1, "title": "UniParc" }, { "level": 1, "title": "UniRef" }, { "level": 1, "title": "UniProtKB" } ], "word_count": 465, "official_url": "https://www.uniprot.org/help/uniprot_data", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprot_data.md", "source_path": "uniprot_data.md", "sha256": "6a5ad9871c76b6deb1cf3c6e677e51bc3c9f51f1b028b3f4437fef29a31bbbd3" }, { "slug": "uniprot_rest_tutorial", "title": "UniProt REST Tutorial", "type": "help", "categories": [ "UniProtKB", "UniParc", "Programmatic_access", "Technical", "help" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "API" ], "excerpt": "A Jupyter notebook has been created which lists code examples for the paper \"The UniProt website API: facilitating programmatic access to protein knowledge\". There are two versions of this notebook: 1. Interactive Google Colab Notebook 2. Static ipynb file on github", "headings": [], "word_count": 41, "official_url": "https://www.uniprot.org/help/uniprot_rest_tutorial", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprot_rest_tutorial.md", "source_path": "uniprot_rest_tutorial.md", "sha256": "da573b176d62cce3f39b1c9e8f4d543655557b5af133e6337609f7c2b53ff01e" }, { "slug": "uniprot_staff", "title": "UniProt staff", "type": "help", "categories": [ "Staff", "help" ], "module": "reference", "module_label": "术语与数据标准", "proteomics_topics": [], "excerpt": "Principal investigators Alex Bateman Paul D. Thomas Cathy H. Wu Key staff Lionel Breuza Elisabeth Coudert Stephanie Lo Michele Magrane Maria J. Martin Peter McGarvey Darren Natale Sandra E. Orchard Ivo Pedruzzi Sylvain Poux Nicole Redaschi Karen Ross Yuqi Wang Friday Ojie Ehiguese Manuela Pruess Content / Curation Aduragbemi Adesina Lucila Aimo Ghislaine Arg...", "headings": [ { "level": 1, "title": "Principal investigators" }, { "level": 1, "title": "Key staff" }, { "level": 1, "title": "Content / Curation" }, { "level": 1, "title": "Development" } ], "word_count": 187, "official_url": "https://www.uniprot.org/help/uniprot_staff", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprot_staff.md", "source_path": "uniprot_staff.md", "sha256": "0461a7f0188ff485831c8e0ce6672062a9dbb2c1a183d292887f3e46cac15293" }, { "slug": "uniprotkb", "title": "UniProtKB", "type": "help", "categories": [ "UniProtKB", "About_UniProt", "Biocuration", "Automatic_annotation", "Sequence", "help" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "Taxonomy" ], "excerpt": "The UniProt Knowledgebase (UniProtKB) is the central hub for the collection of functional information on proteins, with accurate, consistent and rich annotation. In addition to capturing the core data mandatory for each UniProtKB entry (mainly, the amino acid sequence, protein name or description, taxonomic data and citation information), as much annotation ...", "headings": [ { "level": 1, "title": "Where do the protein sequences come from?" }, { "level": 1, "title": "What are the differences between UniProtKB/Swiss-Prot and UniProtKB/TrEMBL?" }, { "level": 1, "title": "How redundant are sequences in UniProtKB?" }, { "level": 1, "title": "What is manual annotation?" }, { "level": 1, "title": "How are entry versions archived?" }, { "level": 1, "title": "Further information" } ], "word_count": 502, "official_url": "https://www.uniprot.org/help/uniprotkb", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprotkb.md", "source_path": "uniprotkb.md", "sha256": "9acc45ccf2f834efab5a9ef29f96136181c82be04f91d434b81db32bc9d69e10" }, { "slug": "uniprotkb_coverage", "title": "Does UniProtKB contain all protein sequences?", "type": "help", "categories": [ "UniProtKB", "UniParc", "Sequence", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome" ], "excerpt": "The two sections of UniProtKB - UniProtKB/Swiss-Prot and UniProtKB/TrEMBL - give access to most protein sequences which are available to the public. However, UniProtKB excludes the following protein sequences: 1. Most non-germline immunoglobulins and T-cell receptors 2. Synthetic sequences 3. Most patent application sequences 4. Small fragments encoded from ...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 262, "official_url": "https://www.uniprot.org/help/uniprotkb_coverage", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprotkb_coverage.md", "source_path": "uniprotkb_coverage.md", "sha256": "4323fb8290a5e673ad808a82e4b45849b7f842de74647b1abb7adaf4f7fb5719" }, { "slug": "uniprotkb_manual", "title": "UniProtKB manual", "type": "help", "categories": [ "UniProtKB", "Website", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Structure", "Variant", "Taxonomy" ], "excerpt": "Annotations of a UniProtKB entry are structured into the following sections: Function Names & Taxonomy Subcellular location Disease/Phenotypes and variants PTM / Processing Expression Interaction Structure Family and Domains Sequence(s) Cross-references Publications Entry information Miscellaneous Similar Proteins User manual for the UniProtKB flat file form...", "headings": [], "word_count": 45, "official_url": "https://www.uniprot.org/help/uniprotkb_manual", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprotkb_manual.md", "source_path": "uniprotkb_manual.md", "sha256": "d0156389f1858fb80a07d090ae40ea0a1dd98d2b1ba32e46da9e202bec9e3e6e" }, { "slug": "uniprotkb_sections", "title": "Why is UniProtKB composed of 2 sections, UniProtKB/Swiss-Prot and UniProtKB/TrEMBL?", "type": "help", "categories": [ "UniProtKB", "Biocuration", "Automatic_annotation", "About_UniProt", "Entry_information", "faq" ], "module": "annotation", "module_label": "注释与证据", "proteomics_topics": [ "Evidence" ], "excerpt": "Swiss-Prot (created in 1986) is a high quality manually annotated and non-redundant protein sequence database, which brings together experimental results, computed features and scientific conclusions. UniProtKB/Swiss-Prot is now the reviewed section of the UniProt Knowledgebase. The TrEMBL section of UniProtKB was introduced in 1996 in response to the increa...", "headings": [ { "level": 1, "title": "See also" } ], "word_count": 163, "official_url": "https://www.uniprot.org/help/uniprotkb_sections", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniprotkb_sections.md", "source_path": "uniprotkb_sections.md", "sha256": "597e1d98c5b5af047ffffabce65209661a202a028076b7fd5bc09fdf116fdda4" }, { "slug": "uniref", "title": "UniRef", "type": "help", "categories": [ "About_UniProt", "UniRef", "Similar_proteins", "help" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Search", "Evidence", "Taxonomy" ], "excerpt": "The UniProt Reference Clusters (UniRef) provide clustered sets of sequences from the UniProt Knowledgebase (including isoforms) and selected UniParc records in order to obtain complete coverage of the sequence space at several resolutions while hiding redundant sequences (but not their descriptions) from view. Unlike in UniParc, sequence fragments are merged...", "headings": [ { "level": 1, "title": "UniRef100" }, { "level": 1, "title": "UniRef90" }, { "level": 1, "title": "UniRef50" }, { "level": 1, "title": "Gene Ontology (GO) annotations for UniRef90 and UniRef50 clusters" }, { "level": 2, "title": "Further information" } ], "word_count": 691, "official_url": "https://www.uniprot.org/help/uniref", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref.md", "source_path": "uniref.md", "sha256": "18a24709ad0672581b53ce6929864614ffe2b49c3b85c7fd7d8cf9b153d107d4" }, { "slug": "uniref_blast_use", "title": "Why can it make sense to use UniRef for BLAST searches?", "type": "help", "categories": [ "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Sequence tools" ], "excerpt": "UniRef, especially UniRef90 and UniRef50, decreases sequence redundancy compared to UniProtKB and UniParc, while maintaining complete coverage of the sequence space. This helps to minimize the time required for BLAST or other similarity search programs to run, and removes many redundant results, thus making the output more concise. Searching against UniRef h...", "headings": [ { "level": 1, "title": "What sequences are considered when running BLAST against a UniRef database?" } ], "word_count": 129, "official_url": "https://www.uniprot.org/help/uniref_blast_use", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_blast_use.md", "source_path": "uniref_blast_use.md", "sha256": "417026454fcf3c7abf9f5a2f7f2a83334f70e3bd6a4a25dc2a8cc9304e69c784" }, { "slug": "uniref_cluster", "title": "What is a UniRef cluster?", "type": "help", "categories": [ "UniRef", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Taxonomy" ], "excerpt": "A UniRef cluster is a set of UniProtKB plus selected UniParc sequences that have a specific minimum percent of sequence identity, and a minimum of 80% overlap with the longest sequence (a.k.a. seed sequence) of the cluster. One exception to the 80% rule is UniRef100 where identical substrings of 11 or more amino acids are merged. For example, UniRef50 contai...", "headings": [], "word_count": 140, "official_url": "https://www.uniprot.org/help/uniref_cluster", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_cluster.md", "source_path": "uniref_cluster.md", "sha256": "984d4486b03d17f8911f2bde65b38935606f4167f07731b42003c388da59402e" }, { "slug": "uniref_find_cluster", "title": "How do I check what UniRef cluster my entry belongs to from the UniProtKB entry page?", "type": "help", "categories": [ "faq" ], "module": "foundations", "module_label": "UniProt 数据体系", "proteomics_topics": [], "excerpt": "The section \"Similar proteins\" in a UniProt entry displays a table with tabs for the 3 different UniRef databases, UniRef100, UniRef90 and UniRef50. This table displays the sequences that belong to the same cluster as the entry, and a link to the UniRef cluster view is also provided. Please see P99999.", "headings": [], "word_count": 51, "official_url": "https://www.uniprot.org/help/uniref_find_cluster", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_find_cluster.md", "source_path": "uniref_find_cluster.md", "sha256": "05c52b6e8e7e4ccf8b5042891ef6cd95f5a81da4370ea6f845d1b5a673468121" }, { "slug": "uniref_organism_query", "title": "How do I find all UniRef clusters with UniProtKB sequence(s) from an organism I am interested in?", "type": "help", "categories": [ "UniRef", "Taxonomy", "faq" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Taxonomy" ], "excerpt": "You can specify the organism by taxonomy ID in the advanced search options. For example, the link below searches for UniRef90 clusters with one or more members from Chinese hamster: taxonomyid:10029 AND identity:0.9", "headings": [], "word_count": 36, "official_url": "https://www.uniprot.org/help/uniref_organism_query", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_organism_query.md", "source_path": "uniref_organism_query.md", "sha256": "ab1769f0e14482a065d34e259dec595b503bc869068efd3d8c911bb71cf4d517" }, { "slug": "uniref_seed", "title": "What is a UniRef seed sequence compared to a representative sequence?", "type": "help", "categories": [ "UniRef", "faq" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "Proteome", "Evidence", "Taxonomy" ], "excerpt": "A UniRef seed is the sequence that has been used as the template to recruit other sequences by the clustering algorithm. The seed sequence is the longest member of a cluster. However, the longest sequence is not always the most informative one. There is often more biologically relevant information (name, function, cross-references) available on other cluster...", "headings": [], "word_count": 217, "official_url": "https://www.uniprot.org/help/uniref_seed", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_seed.md", "source_path": "uniref_seed.md", "sha256": "a872519e594fc96281d76bb950ba16e9fac14cc27f6f27ae00fd66b8e2a902dd" }, { "slug": "uniref_use_cases", "title": "What are some of the advanced uses of UniRef?", "type": "help", "categories": [ "UniRef", "faq" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Structure", "Taxonomy" ], "excerpt": "UniRef is not limited to similarity searches only. The fact that UniRef representatives are distinct and members are consistent allows more extensive uses. A few examples are: UniRef can help with functional annotation and gene prediction. In particular UniRef90/50 clusters provide common Gene Ontology annotation that is consistent within the members and can...", "headings": [], "word_count": 220, "official_url": "https://www.uniprot.org/help/uniref_use_cases", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/uniref_use_cases.md", "source_path": "uniref_use_cases.md", "sha256": "dcb9ca2c613e311760edbe105e83362985b1eb7ded46d82ce7d017644ca5d854" }, { "slug": "unirule", "title": "Automatic annotation using UniRule", "type": "help", "categories": [ "Automatic_annotation", "Biocuration", "UniProtKB", "help" ], "module": "search", "module_label": "检索与结果整理", "proteomics_topics": [ "Search", "API", "Evidence", "PTM", "Taxonomy" ], "excerpt": "UniProt's Automatic Annotation pipeline enhances the unreviewed records in UniProtKB by enriching them with automatic classification and annotation. The Unified Rule (UniRule) system is one of the contributors to this pipeline, and rules are devised and tested by experienced curators using experimental data from manually annotated entries. UniRule has been d...", "headings": [ { "level": 1, "title": "Rule-based evidence for UniProtKB annotation" }, { "level": 1, "title": "Searching UniRule rules" }, { "level": 1, "title": "Exploring the UniRule rule pages" }, { "level": 1, "title": "See also" } ], "word_count": 695, "official_url": "https://www.uniprot.org/help/unirule", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/unirule.md", "source_path": "unirule.md", "sha256": "75c06610dc226e5d91d232a09a1227cccf16ee27e03e4d6c12e25ab5bd80d7ea" }, { "slug": "unsure", "title": "Sequence uncertainty", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA" ], "excerpt": "This subsection of the 'Sequences' section is used to describe region(s) of a sequence for which the authors are unsure about the sequence assignment. Example: P56576 When a protein belongs to a family, we display the most frequent amino acid found at that position in other family members. This is indicated in the 'description' field. Example: P00279 Related...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 91, "official_url": "https://www.uniprot.org/help/unsure", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/unsure.md", "source_path": "unsure.md", "sha256": "301b94246140edc5a928f82efb8055c2429caf8fefc9192581cb740fd38c3eb7" }, { "slug": "var_seq", "title": "Alternative sequence", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "Download", "Variant" ], "excerpt": "This subsection of the 'Sequence' section describes the sequence of naturally occurring alternative protein isoform(s). The changes in the amino acid sequence may be due to alternative splicing, alternative promoter usage, alternative initiation, or ribosomal frameshifting. The information stored in this subsection is used to automatically construct alternat...", "headings": [ { "level": 1, "title": "Related documents" } ], "word_count": 211, "official_url": "https://www.uniprot.org/help/var_seq", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/var_seq.md", "source_path": "var_seq.md", "sha256": "b08dc863ec0a5fb4f193a5fe29bf228fe88130809ddd23fc95ce21b65e454c44" }, { "slug": "variant", "title": "Natural variant", "type": "help", "categories": [ "Sequence", "manual" ], "module": "proteomes", "module_label": "Proteome 与 FASTA", "proteomics_topics": [ "FASTA", "API", "Variant", "Taxonomy" ], "excerpt": "This subsection of the 'Sequence' section describes natural variant(s) of the protein sequence. We annotate individual genetic variants, including disease-linked variants, variations between strains, isolates or cultivars, and RNA editing events. We report the nature of the amino acid change, the name of the variant (or allele), when available, and the effec...", "headings": [ { "level": 1, "title": "1. Variants not linked to diseases" }, { "level": 1, "title": "2. Disease-linked variants" }, { "level": 1, "title": "3. RNA editing" }, { "level": 1, "title": "4. Variations between strains, isolates or cultivars" }, { "level": 1, "title": "Related documents" } ], "word_count": 593, "official_url": "https://www.uniprot.org/help/variant", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/variant.md", "source_path": "variant.md", "sha256": "83839ef5a2b1232a22b07cb47c5fd97c76e7925468b631603273813eddec4f3d" }, { "slug": "variant_viewer", "title": "Variant viewer", "type": "help", "categories": [ "disease_phenotypes_variants", "manual" ], "module": "sequence-tools", "module_label": "序列与分析工具", "proteomics_topics": [ "Search", "Download", "API", "Variant" ], "excerpt": "The variant viewer is a graphical representation of natural variants that are mapped to a protein's amino acid sequence. In addition to the variants that have been expertly curated by the UniProt team, it includes variants from a range of external sources such as dbSNP, NCBI-TCGA, and gnomAD amongst others. The variant viewer facilitates understanding of the...", "headings": [ { "level": 2, "title": "Navigating the variant viewer" }, { "level": 2, "title": "Where to find the variant viewer" }, { "level": 2, "title": "Variants track in the feature viewer" }, { "level": 2, "title": "How to download the data found in the variant viewer" } ], "word_count": 586, "official_url": "https://www.uniprot.org/help/variant_viewer", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/variant_viewer.md", "source_path": "variant_viewer.md", "sha256": "b61c2611bb9e7de70e1fe7ad32481983a5007a92b86869c4b2f46d974ec8c85b" }, { "slug": "virus_host", "title": "Virus host", "type": "help", "categories": [ "Names_and_taxonomy", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "PTM", "Taxonomy" ], "excerpt": "This subsection of the Names and taxonomy section only exists in viral entries and indicates the host(s) either as a specific organism or taxonomic group of organisms that are susceptible to be infected by a virus. A virus being an inert particle outside its hosts, the virion has neither metabolism, nor replication capability, nor autonomous evolution. A vir...", "headings": [], "word_count": 125, "official_url": "https://www.uniprot.org/help/virus_host", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/virus_host.md", "source_path": "virus_host.md", "sha256": "56f8980974a8038250293733b369ad93bdd912cba8ff54deef43483b16114c71" }, { "slug": "Viruses", "title": "Viral protein annotation project", "type": "help", "categories": [ "Biocuration", "project" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Evidence", "PTM", "Structure", "Taxonomy" ], "excerpt": "The Viral protein annotation project focuses on the manual annotation of viral proteins, viral and host taxonomy and host interaction specificities. See: How do we manually annotate a UniProtKB entry? Each protein is annotated according to the quality standards of UniProtKB/Swiss-Prot providing a wealth of information that includes the description of the fun...", "headings": [], "word_count": 208, "official_url": "https://www.uniprot.org/help/Viruses", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/Viruses.md", "source_path": "Viruses.md", "sha256": "452b3d4ea591a69b0ed142eb58b17789891ba00598fdbf7bccebdf11221b079e" }, { "slug": "web_resource", "title": "Web resources", "type": "help", "categories": [ "Cross-references", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "Structure" ], "excerpt": "This subsection of the Cross-references section provides links to various web resources that are relevant for a specific protein. Example: Q9HC16 It complements the 'Cross-references' section by providing links to specific web pages or to databases whose scope is too specialized to legitimate the creation of specific cross-references. Please do not hesitate ...", "headings": [], "word_count": 107, "official_url": "https://www.uniprot.org/help/web_resource", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/web_resource.md", "source_path": "web_resource.md", "sha256": "13d881ed65f6c3cacd693b4064f44ce166aea5aed4fa5556981fc263b2c42878" }, { "slug": "where_to_buy", "title": "Where can I buy protein X? Which company sells protein Y? Where can I buy strain Z?", "type": "help", "categories": [ "UniProtKB", "disease_phenotypes_variants", "faq" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Variant", "Taxonomy" ], "excerpt": "The UniProt consortium does not sell any biological products, neither proteins nor organisms. To obtain additional commercial information you need to access the on-line catalogs of the many suppliers of biochemicals and reagents for the life sciences. To the best of our knowledge this information is not available in any exhaustive public compilation i.e. one...", "headings": [], "word_count": 314, "official_url": "https://www.uniprot.org/help/where_to_buy", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/where_to_buy.md", "source_path": "where_to_buy.md", "sha256": "b9a41e21926002d6139342d21542fd89448109da82677c2038a833c960d90066" }, { "slug": "wildcard", "title": "Searching with leading wildcards", "type": "help", "categories": [ "search", "Technical", "Text_search", "Programmatic_access", "solr" ], "module": "programmatic", "module_label": "API 与批量获取", "proteomics_topics": [ "Search", "API" ], "excerpt": "While it should be noted that our tokenisers make sure that search results are mature and diverse enough for the majority of searches without leading wildcards, the need for leading wildcards still exists for our users. Wildcard searches (, ?) can be very resource heavy and slow to run. Due to the vast amount of data that UniProt offers, searches with leadin...", "headings": [ { "level": 1, "title": "Query examples with leading wildcards:" } ], "word_count": 227, "official_url": "https://www.uniprot.org/help/wildcard", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/wildcard.md", "source_path": "wildcard.md", "sha256": "b58179a118fd192b44c7d19aa3edb4fa1721fac4db86cd724a1cbd72ffd8890f" }, { "slug": "zn_fing", "title": "Zinc finger", "type": "help", "categories": [ "Function", "manual" ], "module": "entry", "module_label": "UniProtKB 条目解读", "proteomics_topics": [ "API", "Structure" ], "excerpt": "This subsection of the Function section specifies the position(s) and type(s) of zinc fingers within the protein. A zinc finger is a small, functional, independently folded domain that coordinates one or more zinc ions to stabilize its structure through cysteine and/or histidine residues. Zinc fingers are structurally diverse and exhibit a wide range of func...", "headings": [ { "level": 1, "title": "1. Types of zinc finger" }, { "level": 1, "title": "2. Annotation of zinc fingers predicted using InterPro resources" }, { "level": 2, "title": "a) C2H2-type zinc fingers" }, { "level": 2, "title": "b) Atypical and degenerate zinc fingers" }, { "level": 1, "title": "3. Annotation of zinc fingers not represented in InterPro" }, { "level": 2, "title": "C4-type zinc fingers" }, { "level": 1, "title": "See also" } ], "word_count": 750, "official_url": "https://www.uniprot.org/help/zn_fing", "source_url": "https://github.com/ebi-uniprot/uniprot-manual/blob/main/help/zn_fing.md", "source_path": "zn_fing.md", "sha256": "bf3b489d16b071af8eac94fc217c78613280ae047855d5da6b88a28f7e24a770" } ] }