Uniprot Tools

Configuration File: uniprot_tools.json Tool Type: Local Tools Count: 18

This page contains all tools defined in the uniprot_tools.json configuration file.

Available Tools

UniProt_get_alternative_names_by_accession (Type: UniProtRESTTool)

Extract all alternative names (alternativeNames) from UniProtKB entry.

UniProt_get_alternative_names_by_accession tool specification

Tool Information:

• Name: UniProt_get_alternative_names_by_accession

• Type: UniProtRESTTool

• Description: Extract all alternative names (alternativeNames) from UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_alternative_names_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_disease_variants_by_accession (Type: UniProtRESTTool)

Extract all variants (feature type = VARIANT) and their related annotations from UniProtKB entry.

UniProt_get_disease_variants_by_accession tool specification

Tool Information:

• Name: UniProt_get_disease_variants_by_accession

• Type: UniProtRESTTool

• Description: Extract all variants (feature type = VARIANT) and their related annotations from UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_disease_variants_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_entry_by_accession (Type: UniProtRESTTool)

Get a UniProtKB entry plus its separate Publications-view bibliography. By default this returns e…

UniProt_get_entry_by_accession tool specification

Tool Information:

• Name: UniProt_get_entry_by_accession

• Type: UniProtRESTTool

• Description: Get a UniProtKB entry plus its separate Publications-view bibliography. By default this returns explicitly pageable comments, features, references, and computationally mapped publications with true totals and continuation offsets/cursors. Returned feature and reference records preserve their complete nested evidence and qualifiers. Set compact=false for the complete raw UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB entry accession, e.g., P05067.

• compact (boolean) (optional) Return a bounded summary instead of the complete UniProtKB JSON entry. Defaults to true to avoid oversized LLM outputs. Set compact=false only when you explicitly need the raw UniProtKB JSON.

• include_publications (boolean) (optional) Also query UniProt’s per-entry publications endpoint, which includes computationally mapped and community-curated literature absent from the entry JSON.

• publication_source (string) (optional) Publication source filter. Default: computational, the bibliography class omitted from UniProtKB entry JSON.

• publication_limit (integer) (optional) Maximum additional publications per page.

• publication_cursor ([‘string’, ‘null’]) (optional) Opaque cursor from metadata.next_publication_cursor. Omit for the first page.

• comment_limit (integer) (optional) Maximum compact-view comments to return.

• comment_offset (integer) (optional) Zero-based offset into all entry comments.

• feature_limit (integer) (optional) Maximum compact-view features to return; each feature retains its complete nested fields.

• feature_offset (integer) (optional) Zero-based offset into all entry features.

• reference_limit (integer) (optional) Maximum compact-view curated entry references to return.

• reference_offset (integer) (optional) Zero-based offset into all curated entry references.

Example Usage:

query = {
    "name": "UniProt_get_entry_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_features_by_accession (Type: UniProtRESTTool)

Extract all sequence features (domains, active/binding sites, motifs, modified residues, signal p…

UniProt_get_features_by_accession tool specification

Tool Information:

• Name: UniProt_get_features_by_accession

• Type: UniProtRESTTool

• Description: Extract all sequence features (domains, active/binding sites, motifs, modified residues, signal peptides, transmembrane regions, etc.) from a UniProtKB entry. Returns each feature’s type, start/end positions, and description. Use to map functional/structural regions of a protein or to see what is annotated at a residue of interest. Example: P04637 (TP53) returns binding sites, the DNA-binding domain, modified residues, and more.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., ‘P04637’ (TP53) or ‘P05067’ (APP).

Example Usage:

query = {
    "name": "UniProt_get_features_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_function_by_accession (Type: UniProtRESTTool)

Extract structured functional annotations from a UniProtKB entry, preserving the ECO, PubMed, and…

UniProt_get_function_by_accession tool specification

Tool Information:

• Name: UniProt_get_function_by_accession

• Type: UniProtRESTTool

• Description: Extract structured functional annotations from a UniProtKB entry, preserving the ECO, PubMed, and cross-entry evidence attached to each FUNCTION text.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

• format (string) (optional) Output shape. ‘structured’ (default) returns one object per functional paragraph with its evidence list. ‘values’ returns the historical flat list of paragraph strings for callers that depend on it, and drops the evidence.

Example Usage:

query = {
    "name": "UniProt_get_function_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_isoform_ids_by_accession (Type: UniProtRESTTool)

Extract all splice isoform IDs from UniProtKB entry (isoformNames).

UniProt_get_isoform_ids_by_accession tool specification

Tool Information:

• Name: UniProt_get_isoform_ids_by_accession

• Type: UniProtRESTTool

• Description: Extract all splice isoform IDs from UniProtKB entry (isoformNames).

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_isoform_ids_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_organism_by_accession (Type: UniProtRESTTool)

Extract the organism scientific name from UniProtKB entry.

UniProt_get_organism_by_accession tool specification

Tool Information:

• Name: UniProt_get_organism_by_accession

• Type: UniProtRESTTool

• Description: Extract the organism scientific name from UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_organism_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_proteome (Type: UniProtRESTTool)

Get proteome information by proteome ID. Returns comprehensive proteome data including taxonomy, …

UniProt_get_proteome tool specification

Tool Information:

• Name: UniProt_get_proteome

• Type: UniProtRESTTool

• Description: Get proteome information by proteome ID. Returns comprehensive proteome data including taxonomy, components, gene/protein counts, and annotation scores. Proteome IDs are typically in format UP000005640 (human), UP000000589 (mouse), etc. Use UniProt search with proteome filters to find proteome IDs for specific organisms.

Parameters:

• proteome_id (string) (required) UniProt proteome ID (e.g., ‘UP000005640’ for human, ‘UP000000589’ for mouse). Find proteome IDs using UniProt search with proteome filters or by querying organism-specific proteomes.

Example Usage:

query = {
    "name": "UniProt_get_proteome",
    "arguments": {
        "proteome_id": "example_value"
    }
}
result = tu.run(query)

UniProt_get_ptm_processing_by_accession (Type: UniProtRESTTool)

Extract all UniProtKB post-translational modification and chain-processing features: modified res…

UniProt_get_ptm_processing_by_accession tool specification

Tool Information:

• Name: UniProt_get_ptm_processing_by_accession

• Type: UniProtRESTTool

• Description: Extract all UniProtKB post-translational modification and chain-processing features: modified residues, glycosylation, lipidation, disulfide bonds, cross-links, signal/transit peptides, propeptides, peptides, chains, and initiator-methionine processing.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_ptm_processing_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_recommended_name_by_accession (Type: UniProtRESTTool)

Extract the recommended protein name (recommendedName) from UniProtKB entry.

UniProt_get_recommended_name_by_accession tool specification

Tool Information:

• Name: UniProt_get_recommended_name_by_accession

• Type: UniProtRESTTool

• Description: Extract the recommended protein name (recommendedName) from UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_recommended_name_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_sequence_by_accession (Type: UniProtRESTTool)

Extract the canonical sequence from UniProtKB entry.

UniProt_get_sequence_by_accession tool specification

Tool Information:

• Name: UniProt_get_sequence_by_accession

• Type: UniProtRESTTool

• Description: Extract the canonical sequence from UniProtKB entry.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

Example Usage:

query = {
    "name": "UniProt_get_sequence_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_subcellular_location_by_accession (Type: UniProtRESTTool)

Extract structured subcellular localization annotations from a UniProtKB entry, preserving eviden…

UniProt_get_subcellular_location_by_accession tool specification

Tool Information:

• Name: UniProt_get_subcellular_location_by_accession

• Type: UniProtRESTTool

• Description: Extract structured subcellular localization annotations from a UniProtKB entry, preserving evidence, isoform/molecule specificity, topology, orientation, and notes.

Parameters:

• accession (string) (required) UniProtKB accession, e.g., P05067.

• format (string) (optional) Output shape. ‘structured’ (default) returns one object per localization with evidence, isoform/molecule specificity, topology, orientation, and notes. ‘values’ returns the historical flat list of location strings for callers that depend on it, and drops those qualifiers.

Example Usage:

query = {
    "name": "UniProt_get_subcellular_location_by_accession",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

UniProt_get_uniparc_entry (Type: UniProtRESTTool)

Get UniParc entry by UniParc ID (UPI). UniParc is a non-redundant archive of all publicly availab…

UniProt_get_uniparc_entry tool specification

Tool Information:

• Name: UniProt_get_uniparc_entry

• Type: UniProtRESTTool

• Description: Get UniParc entry by UniParc ID (UPI). UniParc is a non-redundant archive of all publicly available protein sequences. Returns sequence, cross-references, and sequence features. UniParc IDs are in format UPI000002ED67. Use UniProt_get_entry_by_accession to find the UniParc ID for a UniProt entry (in extraAttributes.uniParcId).

Parameters:

• upi (string) (required) UniParc ID (UPI) in format UPI000002ED67. Find UPI from UniProt entry (extraAttributes.uniParcId) or use UniProt_search_uniparc.

Example Usage:

query = {
    "name": "UniProt_get_uniparc_entry",
    "arguments": {
        "upi": "example_value"
    }
}
result = tu.run(query)

UniProt_get_uniref_cluster (Type: UniProtRESTTool)

Get UniRef cluster information by cluster ID. UniRef clusters group proteins that share 100% (Uni…

UniProt_get_uniref_cluster tool specification

Tool Information:

• Name: UniProt_get_uniref_cluster

• Type: UniProtRESTTool

• Description: Get UniRef cluster information by cluster ID. UniRef clusters group proteins that share 100% (UniRef100), 90% (UniRef90), or 50% (UniRef50) sequence identity. Returns cluster metadata, representative member, member count, and member list. Cluster IDs are in format UniRef100_P04637, UniRef90_P04637, or UniRef50_P04637.

Parameters:

• cluster_id (string) (required) UniRef cluster ID (e.g., ‘UniRef50_P04637’, ‘UniRef90_P04637’, ‘UniRef100_P04637’). Use UniProt_search_uniref to find cluster IDs.

Example Usage:

query = {
    "name": "UniProt_get_uniref_cluster",
    "arguments": {
        "cluster_id": "example_value"
    }
}
result = tu.run(query)

UniProt_id_mapping (Type: UniProtRESTTool)

Map IDs between databases using UniProt’s asynchronous service. Fetches every upstream result pag…

UniProt_id_mapping tool specification

Tool Information:

• Name: UniProt_id_mapping

• Type: UniProtRESTTool

• Description: Map IDs between databases using UniProt’s asynchronous service. Fetches every upstream result page before applying explicit local result_offset/result_limit pagination; mapped_count is always the true complete mapping count.

Parameters:

• ids (unknown) (required) ID(s) to map. Can be single string or array of strings, e.g., ‘ENSG00000141510’ or [‘MEIOB’, ‘TP53’]

• from_db (string) (required) Source database. Examples: ‘Ensembl’, ‘Gene_Name’, ‘RefSeq_Protein’, ‘PDB’, ‘EMBL’

• to_db (string) (optional) Target database (default: ‘UniProtKB’)

• max_wait_time (integer) (optional) Maximum time to wait for async task completion in seconds (default: 30)

• result_offset (integer) (optional) Zero-based offset within the complete mapping result set.

• result_limit (integer) (optional) Maximum mapped records returned in this response. mapped_count remains the complete total.

Example Usage:

query = {
    "name": "UniProt_id_mapping",
    "arguments": {
        "ids": "example_value",
        "from_db": "example_value"
    }
}
result = tu.run(query)

UniProt_search (Type: UniProtRESTTool)

Search UniProtKB database with flexible query syntax. Returns protein entries with accession numb…

UniProt_search tool specification

Tool Information:

• Name: UniProt_search

• Type: UniProtRESTTool

• Description: Search UniProtKB database with flexible query syntax. Returns protein entries with accession numbers and metadata. Query syntax supports: field searches (gene:TP53, taxonomy_id:9606, reviewed:true), ranges (length:[100 TO 500], mass:[20000 TO 50000]), wildcards (gene:MEIOB*), boolean operators (AND/OR/NOT), and parentheses for grouping. Examples: ‘gene:TP53 AND taxonomy_id:9606’, ‘length:[400 TO 500] AND reviewed:true’, ‘tissue:brain NOT taxonomy_id:10090’. Scope by taxon with taxonomy_id (lineage match, ‘Taxonomy [OC]’) rather than organism_id (‘Organism [OS]’, exact organism node only): most bacterial entries are annotated at strain level, so a species-level organism_id silently returns 0 or an undercount (gene:gyrA AND organism_id:1423 -> 0 hits; taxonomy_id:1423 -> 1). A caller-supplied organism_id:<taxid> is rewritten to taxonomy_id:<taxid> and the change is reported in data.normalization_note. Pagination is cursor-based: the response reports the true total_results, returned, has_more/truncated, and next_cursor from UniProt’s Link header; pass that cursor back for the next page.

Parameters:

• query (string) (required) Search query using UniProt syntax. Simple: ‘MEIOB’, ‘insulin’. Field searches: ‘gene:TP53’, ‘protein_name:insulin’, ‘taxonomy_id:9606’, ‘reviewed:true’. Ranges: ‘length:[100 TO 500]’, ‘mass:[20000 TO 50000]’. Wildcards: ‘gene:MEIOB*’. Boolean: ‘gene:TP53 AND taxonomy_id:9606’, ‘tissue:brain OR tissue:liver’, ‘reviewed:true NOT fragment:true’. Use parentheses for grouping: ‘(taxonomy_id:9606 OR taxonomy_id:10090) AND gene:TP53’. Taxon scoping: use ‘taxonomy_id:<taxid>’ (matches the whole lineage, so strain-level entries under a species taxid are included) or ‘organism_name:”…”’. A bare ‘organism:’ auto-converts, and ‘organism_id:<taxid>’ is rewritten to ‘taxonomy_id:<taxid>’ with a note in data.normalization_note, because organism_id matches only the exact organism node and misses strain-level entries.

• organism (string) (optional) Optional organism filter. Use common names (‘human’, ‘mouse’, ‘rat’, ‘yeast’) or taxonomy ID (‘9606’). Automatically combined with query using AND. Will not duplicate if organism is already in query.

• limit (integer) (optional) Maximum number of results to return (default: 25, max: 500). Accepts string or integer.

• min_length (integer) (optional) Minimum sequence length. Auto-converts to an open-ended length range query (min to unbounded).

• max_length (integer) (optional) Maximum sequence length. Auto-converts to an open-ended length range query (unbounded to max).

• fields (array) (optional) List of field names to return (e.g., [‘accession’,’gene_primary’,’length’,’organism_name’]). When specified, returns raw API response with requested fields. Common fields: accession, id, gene_names, gene_primary, protein_name, organism_name, organism_id, length, mass, sequence, reviewed, cc_function. See UniProt API docs for full list. Default (no fields): returns formatted response with accession, id, protein_name, gene_names, organism, length.

• cursor ([‘string’, ‘null’]) (optional) Opaque cursor from data.next_cursor. Omit for the first page; cursors must not be synthesized.

Example Usage:

query = {
    "name": "UniProt_search",
    "arguments": {
        "query": "example_value"
    }
}
result = tu.run(query)

UniProt_search_uniparc (Type: UniProtRESTTool)

Search UniParc entries with explicit cursor pagination. data.next_cursor comes from the official …

UniProt_search_uniparc tool specification

Tool Information:

• Name: UniProt_search_uniparc

• Type: UniProtRESTTool

• Description: Search UniParc entries with explicit cursor pagination. data.next_cursor comes from the official Link header and retrieves the next distinct page.

Parameters:

• query (string) (required) Search query. Examples: ‘P04637’ (protein accession), ‘name:TP53’, ‘organism_id:9606’ (human). Supports UniProt query syntax.

• limit (integer) (optional) Maximum number of results to return (default: 25, max: 500)

• cursor ([‘string’, ‘null’]) (optional) Opaque cursor from data.next_cursor. Omit for the first page.

Example Usage:

query = {
    "name": "UniProt_search_uniparc",
    "arguments": {
        "query": "example_value"
    }
}
result = tu.run(query)

UniProt_search_uniref (Type: UniProtRESTTool)

Search UniRef clusters with explicit cursor pagination. data.next_cursor comes from the official …

UniProt_search_uniref tool specification

Tool Information:

• Name: UniProt_search_uniref

• Type: UniProtRESTTool

• Description: Search UniRef clusters with explicit cursor pagination. data.next_cursor comes from the official Link header and retrieves the next distinct page.

Parameters:

• query (string) (required) Search query. Examples: ‘P04637’ (protein accession), ‘name:TP53’, ‘organism_id:9606’ (human). Supports UniProt query syntax.

• cluster_type (string) (optional) UniRef cluster type: UniRef100 (100% identity), UniRef90 (90% identity), UniRef50 (50% identity)

• limit (integer) (optional) Maximum number of results to return (default: 25, max: 500)

• cursor ([‘string’, ‘null’]) (optional) Opaque cursor from data.next_cursor. Omit for the first page.

Example Usage:

query = {
    "name": "UniProt_search_uniref",
    "arguments": {
        "query": "example_value"
    }
}
result = tu.run(query)

Navigation

• Available Tools - Back to Tools Overview

• Tool Loading Tutorial - Loading Local Tools