Uniprot Database

Google DeepMindOfficialPublished by Google DeepMind

Skill
Tool integration
Science and research
Apache-2.0
Low risk
Has scripts

From the author

Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).

— the description by Google DeepMind

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The UniProt Database skill provides a robust interface for interacting with the UniProt Knowledgebase (UniProtKB), UniParc, and UniRef. It enables researchers and developers to perform protein discovery, retrieve curated biological annotations, map identifiers across numerous external databases, and conduct bulk data retrieval. The skill is designed for programmatic access, ensuring reliable data extraction for bioinformatics workflows while adhering to UniProt's licensing and usage guidelines.

What it does

Retrieves detailed protein metadata, functional annotations, and sequences.
Maps protein identifiers between UniProt and over 100 external biological databases.
Performs complex queries and data discovery using SPARQL.
Supports bulk data retrieval through streaming for large datasets.
Provides access to historical data entries via UniSave.
Enables exploration of protein-organism relationships and taxonomy.

When to use it

When you need to fetch specific protein information by accession number.
When performing large-scale analysis requiring bulk retrieval of protein data.
When you need to convert identifiers from external databases to UniProt accessions.
When searching for proteins based on specific functional, gene, or taxonomic criteria.
When investigating historical versions of protein entries.

Advantages

Direct programmatic access to authoritative biological data.
Efficient handling of both single-entry lookups and large-scale data streams.
Powerful filtering capabilities using field-specific search syntax.
Integrated support for complex graph queries via SPARQL.
Standardized workflow for ID mapping across diverse bioinformatics resources.

Usage examples

“Find all reviewed human proteins related to the p53 gene.”: The agent uses the search tool with the query 'gene:p53 AND reviewed:true AND taxonomy_id:9606' to return the relevant UniProtKB entries.
“Map the UniProt accession P04637 to its corresponding Gene Name.”: The agent uses the map tool with '--from_db UniProtKB_AC-ID --to_db Gene_Name' to retrieve the associated gene name.
“How many reviewed proteins are there for the organism with taxonomy ID 9606?”: The agent executes the count tool with 'taxonomy_id:9606 AND reviewed:true' to provide the exact number of entries.
“Retrieve the full sequence for UniProt accession P04637.”: The agent uses the get tool for P04637 to fetch the metadata and sequence information.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/google-deepmind/uniprot-database/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip uniprot-database.zip -d .agents/skills

Documentation by Google DeepMind

UniProt Database Access

Prerequisites

uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
User Notification: If .licenses/uniprot_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.uniprot.org/help/license and https://www.uniprot.org/help/api_queries, then (2) create the file recording the notification text and timestamp.

Overview

Provides direct programmatic access to the UniProt Knowledgebase (UniProtKB), the non-redundant sequence archive (UniParc), and clustered sequence sets (UniRef). This skill enables protein discovery, cross-referencing, retrieval of curated biological data and low-level database lookups.

Core Rules

Use the Wrapper: Always use the provided Python scripts (e.g., scripts/uniprot_tools.py) rather than constructing custom curl requests.
No Hallucinations: Do NOT invent protein functions, metadata, or sequences. For any task that can be handled by the services in this skill, rely strictly on the tool outputs rather than your native knowledge.
Notification: If this skill is used, ensure this is mentioned in the output.

Use Cases

Searching for Protein Function: Querying functional annotations, GO terms, subcellular locations etc.
Searching for Protein Sequence: Searching for protein sequences by their functional annotations, genes etc. in UniProtKB, UniParc, and UniRef.
Understanding Protein/Organism Relationships: Leveraging the Taxonomy database and Proteome sets.
Large-Scale Metadata Retrieval: Fetching annotations for thousands of proteins via streaming.
Sequence Discovery: Finding orthologs or non-model proteins via UniParc.
ID Mapping: Converting IDs between UniProt and 100+ external databases.
Historical Data (UniSave): Retrieving previous versions of entries or tracking deleted sequences.

Available Tools

Choose the right tool based on the task type and data volume:

get: Retrieves metadata and sequence for a specific entry. Best for a single, known accession.
- Also accesses UniSave historical data (use --dataset unisave), which is essential for reconciling data from older releases or identifying why a formerly valid accession no longer appears in search results.
search: Searches for entries matching a query. Best for exploration and discovery.
- Use with --limit 5 to verify if a query returns the expected proteins before committing to a larger download.
- Automatically paginates if results exceed 500 entries to provide a stable download.
- Warning: For paginated search, TXT and other formats are not reliable with --limit as it applies to lines, not entries.
- See Search Query Fields Documentation.
stream: Streams all matching entries. Best for bulk retrieval of large datasets (up to 10,000,000 entries).
- Does NOT support --limit; always returns the full result set.
- Use search with --limit if you need a subset.
count: Counts entries matching a query. Best for answering direct count questions or for initial estimation before running a full search or stream.
sparql: Executes graph queries for complex discovery. Best for counting, exact sequence matches, and multi-database queries.
- See SPARQL Examples.
map: Converts IDs between UniProt and 100+ databases. Best for ID mapping tasks.
- See ID Mapping Documentation.
- search vs. map: Try search first before resorting to map if not explicitly requested by the user. E.g., an external ID might be searchable in UniParc but fail to map to UniProtKB.

Workflows

Typical Protein Research Workflow

Copy this checklist and track progress:

[ ] Step 1: Identify target protein(s) and organism(s).
[ ] Step 2: Search UniProtKB for reviewed entries (reviewed:true).
[ ] Step 3: If no reviewed entries, search unreviewed or use UniParc for sequence discovery.
[ ] Step 4: Map external IDs (e.g., Ensembl, PDB) to UniProt Accessions if necessary.
[ ] Step 5: Retrieve functional metadata or sequence in desired format (JSON, FASTA).

Handling Search Misses (e.g. Gene Search in Non-Model Organisms)

If a direct query (e.g., gene:SYMBOL) fails:

Pivot to Protein Name: Search for the common protein name (e.g., protein_name:Alpha-crystallin A).
Use UniParc: Search the UniParc dataset, which integrates sequences from across all of life, even if they aren't fully annotated in UniProtKB.
Check Orthologs/Canonical: Resolve the Human/Mouse ortholog first to find the correct naming/mnemonic.

Bulk Retrieval Priorities

[!IMPORTANT] Always prefer stream or sparql for bulk data. search is suitable for exploration; if results exceed 500 entries, it automatically paginates to provide a stable download.

Priority 0: count: ALWAYS check the result count before running a search or stream.
Priority 1: stream: The primary method for bulk data retrieval (up to 10M entries). Does NOT support --limit; always returns all results.
Priority 2: sparql: Best for complex filtering and exact matching during retrieval.

Sequence-Based Search (Exact Match)

[!IMPORTANT] Use SPARQL when searching for a protein by its full amino acid sequence. The REST API /search endpoint does not support direct sequence-string lookups. For any non-exact match use specialized sequence similarity search skills. Use UniParc if you cannot find query in UniProt.

SPARQL Query Pattern (UniProt):

PREFIX up: <http://purl.uniprot.org/core/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
SELECT ?protein ?name WHERE {
  ?protein a up:Protein ;
           up:sequence/rdf:value "SEQUENCE_HERE" .
  OPTIONAL {
    ?protein up:recommendedName/up:fullName ?name .
  }
}

SPARQL Query Pattern (UniParc):

PREFIX up: <http://purl.uniprot.org/core/>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>

SELECT ?uniparc ?val WHERE {
  GRAPH <http://sparql.uniprot.org/uniparc> {
    ?uniparc a up:Sequence ;
             rdf:value ?val .
    FILTER (?val = "SEQUENCE_HERE")
  }
}

Counting Entries Efficiently

[!IMPORTANT] Use count or SPARQL for counting entries (e.g., "How many proteins in Human?").

Counting Pattern (Proteins per Organism):

PREFIX up: <http://purl.uniprot.org/core/>
PREFIX taxon: <http://purl.uniprot.org/taxonomy/>
SELECT (COUNT(?protein) AS ?count) WHERE {
  ?protein a up:Protein ;
           up:reviewed true ;
           up:organism taxon:9606 .
}

REST Search Syntax

No Commas in Lists: Commas are treated as literals. Use capitalized OR to separate items.
- Grouped: accession:(P12345 OR P67890)
- Repeated: accession:P12345 OR accession:P67890
Space = AND: E.g., gene:p53 human searches for both.

Example Commands

Below are example commands for each mode of uniprot_tools.py.

Count total number of entries for a given query.

uv run scripts/uniprot_tools.py count "taxonomy_id:9606"

Search for entries.

uv run scripts/uniprot_tools.py search "gene:p53 AND reviewed:true" --limit 5

Retrieve a single entry by accession.

uv run scripts/uniprot_tools.py get P04637

Retrieve Historical/Deleted Entry (UniSave).

uv run scripts/uniprot_tools.py get P04637 --dataset unisave

Stream large result sets for bulk retrieval (returns ALL matched entries, no --limit support).

uv run scripts/uniprot_tools.py stream "taxonomy_id:9606 AND reviewed:true" --format tsv --fields accession,gene_names > human_reviewed.tsv

Map IDs from one database to another.

uv run scripts/uniprot_tools.py map "P04637" --from_db UniProtKB_AC-ID --to_db Gene_Name

Execute graph queries with SPARQL.

uv run scripts/uniprot_tools.py sparql 'PREFIX up: <http://purl.uniprot.org/core/> SELECT ?protein WHERE { ?protein a up:Protein ; up:reviewed true . } LIMIT 5'

Common Mistakes

Using name: instead of protein_name:: name: is not a supported query term, use protein_name: instead.
Ignoring UniParc: Non-model organisms might only exist in UniParc.
Confusing Accession with UPI: UniProtKB Accessions (e.g., P04637) are linked to functional metadata; UniParc IDs (UPI...) are for sequences only. You can find cross-references from UniParc IDs to UniProtKB Accessions using the ID Mapping tool.
Using UniProtKB-AC as Target in ID Mapping: Use UniProtKB instead.
Giving up on Complex Queries: If a complex search query fails, try to use SPARQL instead of giving up.
Using IDs Without Verifying Meaning: NEVER assume you know the meaning of an ID (e.g. keyword, GO term, Pfam ID etc.). ALWAYS look up the natural language description/meaning of an ID in UniProt before using it for search to ensure it matches your intended search term.
Ignoring Citation Noise in Broad Searches: Broad text searches (search "term") frequently return false positives (e.g., common maintenance proteins) because UniProt searches full metadata, including publication titles. ALWAYS prefer field-specific filters like cc_function: or protein_name: for functional discovery.
Forgetting to Quote Short Search Terms: Short, unquoted terms (e.g., lanM) can match substrings in organism names (e.g., Lancefieldella) or other fields. Use quotes and field prefixes (e.g., gene:lanM) to isolate true hits.
Manipulating Protein Sequences Directly: Always use code and tools for sequence-based operations. Do not attempt to edit, truncate, or modify protein sequences manually.
Over-using Search for Bulk Data: DO NOT use search for retrieving millions of entries if stream or sparql can do the job. Streaming is more efficient for very large datasets. Note that stream has a hard limit of 10,000,000 outputs and does NOT support --limit.
Forgetting to Check Data Volume: ALWAYS perform a count before running a search without --limit or before using stream. Unlimited queries can take a long time and consume significant resources if millions of entries are returned.
Using --limit with stream: The stream command does NOT support --limit. If you need a limited number of results, use search with --limit instead.
Forgetting the License Notice: Do not neglect to state that the UniProt Database was used and to advise the user to review the licensing terms when presenting results for the first time. Even if the task is concise, this attribution is required in the first response containing UniProt data.

Reference Materials

SPARQL Examples
Search Query Fields Documentation
ID Mapping Documentation
UniProt Evidence Docs
Underlying API Endpoints (Used by scripts/uniprot_tools.py):
- get, search, stream, count -> rest.uniprot.org/{dataset}/
- map -> rest.uniprot.org/idmapping/
- sparql -> sparql.uniprot.org/sparql
- get --dataset unisave -> rest.uniprot.org/unisave/

Files

ATTRIBUTION.mdAdded by AutoGineer914 B
LICENSELicence file added by AutoGineer11.1 KiB
SKILL.md12.0 KiB
references/citation.bib1.4 KiB
references/id_mapping_databases.md7.1 KiB
references/search_query_fields.md18.0 KiB
references/sparql_examples.md2.8 KiB
scripts/uniprot_tools.pyScript14.1 KiB

references/search_query_fields.md

UniProt REST Query Fields Reference

This document lists the available query fields for searching UniProt databases via the REST API.

Fields marked with (Experimental Evidence) are used to filter for entries where the annotation has experimental support.

UniProtKB (UniProt Knowledgebase)

UniProtKB AC: accession
Entry Name [ID]: id
Secondary Accession: sec_acc
Protein Name [DE]: protein_name
Gene Name [GN]: gene
Organism [OS]: organism_name
Taxonomy [OC]: taxonomy_name
Virus host: virus_host_name
Protein Existence [PE]: existence
Function
- Enzyme classification [EC]: ec
- Cofactors
  - ChEBI term
    - Chebi: cc_cofactor_chebi
    - Exp (Experimental Evidence): cc_cofactor_chebi_exp
  - Note
    - Note: cc_cofactor_note
    - Exp (Experimental Evidence): cc_cofactor_note_exp
- Biophysicochemical properties
  - Any
    - Bpcp: cc_bpcp
    - Exp (Experimental Evidence): cc_bpcp_exp
  - Absorption
    - Absorption: cc_bpcp_absorption
    - Exp (Experimental Evidence): cc_bpcp_absorption_exp
  - Kinetics
    - Kinetics: cc_bpcp_kinetics
    - Exp (Experimental Evidence): cc_bpcp_kinetics_exp
  - pH dependence
    - Dependence: cc_bpcp_ph_dependence
    - Exp (Experimental Evidence): cc_bpcp_ph_dependence_exp
  - Redox potential
    - Potential: cc_bpcp_redox_potential
    - Exp (Experimental Evidence): cc_bpcp_redox_potential_exp
  - Temperature dependence
    - Dependence: cc_bpcp_temp_dependence
    - Exp (Experimental Evidence): cc_bpcp_temp_dependence_exp
- Catalytic Activity
  - Activity: cc_catalytic_activity
  - Exp (Experimental Evidence): cc_catalytic_activity_exp
- Activity regulation
  - Regulation: cc_activity_regulation
  - Exp (Experimental Evidence): cc_activity_regulation_exp
- Function [CC]
  - Function: cc_function
  - Exp (Experimental Evidence): cc_function_exp
- Caution
  - Caution: cc_caution
  - Exp (Experimental Evidence): cc_caution_exp
- Sites
  - Any
    - Sites: ft_sites
    - Exp (Experimental Evidence): ft_sites_exp
  - Active site
    - Site: ft_act_site
    - Exp (Experimental Evidence): ft_act_site_exp
  - Binding site
    - Binding: ft_binding
    - Exp (Experimental Evidence): ft_binding_exp
  - Other
    - Site: ft_site
    - Exp (Experimental Evidence): ft_site_exp
- DNA binding
  - Bind: ft_dna_bind
  - Exp (Experimental Evidence): ft_dna_bind_exp
- Pathway
  - Pathway: cc_pathway
  - Exp (Experimental Evidence): cc_pathway_exp
- Miscellaneous [CC]
  - Miscellaneous: cc_miscellaneous
  - Exp (Experimental Evidence): cc_miscellaneous_exp
Subcellular location
- Subcellular location [CC]
  - Subcellular location term
    - Term: cc_scl_term
    - Exp (Experimental Evidence): cc_scl_term_exp
  - Subcellular location note
    - Note: cc_scl_note
    - Exp (Experimental Evidence): cc_scl_note_exp
- Transmembrane
  - Transmem: ft_transmem
  - Exp (Experimental Evidence): ft_transmem_exp
- Topological domain
  - Dom: ft_topo_dom
  - Exp (Experimental Evidence): ft_topo_dom_exp
- Intramembrane
  - Intramem: ft_intramem
  - Exp (Experimental Evidence): ft_intramem_exp
Pathology & Biotech
- Disease
  - Disease: cc_disease
  - Exp (Experimental Evidence): cc_disease_exp
- Allergenic properties
  - Allergen: cc_allergen
  - Exp (Experimental Evidence): cc_allergen_exp
- Toxic dose
  - Dose: cc_toxic_dose
  - Exp (Experimental Evidence): cc_toxic_dose_exp
- Biotechnological use
  - Biotechnology: cc_biotechnology
  - Exp (Experimental Evidence): cc_biotechnology_exp
- Pharmaceutical use
  - Pharmaceutical: cc_pharmaceutical
  - Exp (Experimental Evidence): cc_pharmaceutical_exp
- Disruption phenotype
  - Phenotype: cc_disruption_phenotype
  - Exp (Experimental Evidence): cc_disruption_phenotype_exp
- Mutagenesis
  - Mutagen: ft_mutagen
  - Exp (Experimental Evidence): ft_mutagen_exp
PTM/Processing
- Post-translational modification [CC]
  - Ptm: cc_ptm
  - Exp (Experimental Evidence): cc_ptm_exp
- Modified residue [FT]
  - Res: ft_mod_res
  - Exp (Experimental Evidence): ft_mod_res_exp
- Lipidation [FT]
  - Lipid: ft_lipid
  - Exp (Experimental Evidence): ft_lipid_exp
- Glycosylation [FT]
  - Carbohyd: ft_carbohyd
  - Exp (Experimental Evidence): ft_carbohyd_exp
- Disulfide bond [FT]
  - Disulfid: ft_disulfid
  - Exp (Experimental Evidence): ft_disulfid_exp
- Cross-link [FT]
  - Crosslnk: ft_crosslnk
  - Exp (Experimental Evidence): ft_crosslnk_exp
- Molecule Processing [FT]
  - Any molecule processing
    - Processing: ft_molecule_processing
    - Exp (Experimental Evidence): ft_molecule_processing_exp
  - Chain
    - Chain: ft_chain
    - Exp (Experimental Evidence): ft_chain_exp
  - Initiator methionine
    - Met: ft_init_met
    - Exp (Experimental Evidence): ft_init_met_exp
  - Peptide
    - Peptide: ft_peptide
    - Exp (Experimental Evidence): ft_peptide_exp
  - Signal Peptide
    - Signal: ft_signal
    - Exp (Experimental Evidence): ft_signal_exp
  - Propeptide
    - Propep: ft_propep
    - Exp (Experimental Evidence): ft_propep_exp
  - Transit Peptide
    - Transit: ft_transit
    - Exp (Experimental Evidence): ft_transit_exp
Expression
- Developmental stage
  - Stage: cc_developmental_stage
  - Exp (Experimental Evidence): cc_developmental_stage_exp
- Induction
  - Induction: cc_induction
  - Exp (Experimental Evidence): cc_induction_exp
- Tissue specificity
  - Specificity: cc_tissue_specificity
  - Exp (Experimental Evidence): cc_tissue_specificity_exp
Interaction
- Binary Interaction: interactor
- Subunit structure
  - Subunit: cc_subunit
  - Exp (Experimental Evidence): cc_subunit_exp
Structure
- 3D Structure: structure_3d
- Secondary structure
  - Any
    - Secstruct: ft_secstruct
    - Exp (Experimental Evidence): ft_secstruct_exp
  - Helix
    - Helix: ft_helix
    - Exp (Experimental Evidence): ft_helix_exp
  - Turn
    - Turn: ft_turn
    - Exp (Experimental Evidence): ft_turn_exp
  - Beta strand
    - Strand: ft_strand
    - Exp (Experimental Evidence): ft_strand_exp
Sequence
- Mass(Da): mass
- Checksum (CRC64/MD5): checksum
- Sequence length: length
- Alternative products (isoforms)
  - Any
    - Ap: cc_ap
    - Exp (Experimental Evidence): cc_ap_exp
  - Alternative promoter usage
    - Apu: cc_ap_apu
    - Exp (Experimental Evidence): cc_ap_apu_exp
  - Alternative splicing
    - As: cc_ap_as
    - Exp (Experimental Evidence): cc_ap_as_exp
  - Alternative initiation
    - Ai: cc_ap_ai
    - Exp (Experimental Evidence): cc_ap_ai_exp
  - Ribosomal frameshifting
    - Rf: cc_ap_rf
    - Exp (Experimental Evidence): cc_ap_rf_exp
- Sequence caution
  - Any
    - Caution: cc_sequence_caution
    - Exp (Experimental Evidence): cc_sequence_caution_exp
  - Frameshift: cc_sc_framesh
  - Erroneous initiation: cc_sc_einit
  - Erroneous termination: cc_sc_eterm
  - Erroneous gene model prediction: cc_sc_epred
  - Erroneous translation: cc_sc_etran
  - Miscellaneous Discrepancy
    - Misc: cc_sc_misc
    - Exp (Experimental Evidence): cc_sc_misc_exp
- Mass Spectrometry
  - Spectrometry: cc_mass_spectrometry
  - Exp (Experimental Evidence): cc_mass_spectrometry_exp
- Polymorphism
  - Polymorphism: cc_polymorphism
  - Exp (Experimental Evidence): cc_polymorphism_exp
- RNA Editing
  - Editing: cc_rna_editing
  - Exp (Experimental Evidence): cc_rna_editing_exp
- Natural Variations
  - Any
    - Variants: ft_variants
    - Exp (Experimental Evidence): ft_variants_exp
  - Natural variant
    - Variant: ft_variant
    - Exp (Experimental Evidence): ft_variant_exp
  - Alternative sequence
    - Seq: ft_var_seq
    - Exp (Experimental Evidence): ft_var_seq_exp
- Non-standard residue
  - Std: ft_non_std
  - Exp (Experimental Evidence): ft_non_std_exp
- Non-terminal residue
  - Ter: ft_non_ter
  - Exp (Experimental Evidence): ft_non_ter_exp
- Non-adjacent residue
  - Cons: ft_non_cons
  - Exp (Experimental Evidence): ft_non_cons_exp
- Sequence conflict
  - Conflict: ft_conflict
  - Exp (Experimental Evidence): ft_conflict_exp
- Sequence uncertainty
  - Unsure: ft_unsure
  - Exp (Experimental Evidence): ft_unsure_exp
- Sequence features [FT]
  - Positional: ft_positional
  - Exp (Experimental Evidence): ft_positional_exp
- Fragment: fragment
- Encoded in: encoded_in
- Precursor: precursor
- Sequence from ... [RC]
  - Tissue: tissue
  - Strain: strain
  - Plasmid: plasmid
  - Transposon: transposon
Family and Domains
- Domain [FT]
  - Domain: ft_domain
  - Exp (Experimental Evidence): ft_domain_exp
- Domain Comments [CC]
  - Domain: cc_domain
  - Exp (Experimental Evidence): cc_domain_exp
- Protein family: family
- Coiled-coil
  - Coiled: ft_coiled
  - Exp (Experimental Evidence): ft_coiled_exp
- Compositional bias
  - Compbias: ft_compbias
  - Exp (Experimental Evidence): ft_compbias_exp
- Motif
  - Motif: ft_motif
  - Exp (Experimental Evidence): ft_motif_exp
- Region
  - Region: ft_region
  - Exp (Experimental Evidence): ft_region_exp
- Repeat
  - Repeat: ft_repeat
  - Exp (Experimental Evidence): ft_repeat_exp
- Sequence similarity
  - Similarity: cc_similarity
  - Exp (Experimental Evidence): cc_similarity_exp
- Zinc finger
  - Fing: ft_zn_fing
  - Exp (Experimental Evidence): ft_zn_fing_exp
Cross-references
- Source: source
- Any
  - Any cross-reference: xref
- Sequence databases
  - EMBL: xref
  - CCDS: xref
  - PIR: xref
  - RefSeq: xref
- 3D structure databases
  - PDB: xref
  - PDBsum: xref
  - PCDDB: xref
  - SASBDB: xref
  - BMRB: xref
  - SMR: xref
  - AlphaFoldDB: xref
  - EMDB: xref
- Protein-protein interaction databases
  - BioGRID: xref
  - ComplexPortal: xref
  - CORUM: xref
  - DIP: xref
  - ELM: xref
  - IntAct: xref
  - MINT: xref
  - STRING: xref
  - FunCoup: xref
- Chemistry
  - BindingDB: xref
  - ChEMBL: xref
  - DrugBank: xref
  - GuidetoPHARMACOLOGY: xref
  - SwissLipids: xref
  - DrugCentral: xref
- Protein family/group databases
  - Allergome: xref
  - CAZy: xref
  - ESTHER: xref
  - IMGT_GENE-DB: xref
  - MEROPS: xref
  - MoonDB: xref
  - MoonProt: xref
  - PeroxiBase: xref
  - REBASE: xref
  - TCDB: xref
  - UniLectin: xref
  - CARD: xref
- PTM databases
  - CarbonylDB: xref
  - DEPOD: xref
  - GlyConnect: xref
  - GlyCosmos: xref
  - GlyGen: xref
  - iPTMnet: xref
  - PhosphoSitePlus: xref
  - SwissPalm: xref
  - UniCarbKB: xref
  - MetOSite: xref
- Genetic variation databases
  - BioMuta: xref
  - DMDM: xref
  - dbSNP: xref
- 2D gel databases
  - OGP: xref
  - REPRODUCTION-2DPAGE: xref
- Proteomic databases
  - CPTAC: xref
  - PaxDb: xref
  - PeptideAtlas: xref
  - PRIDE: xref
  - ProMEX: xref
  - ProteomicsDB: xref
  - Pumba: xref
  - TopDownProteomics: xref
  - jPOST: xref
  - MassIVE: xref
- Protocols and materials databases
  - DNASU: xref
  - ABCD: xref
  - Antibodypedia: xref
  - CPTC: xref
  - YCharOS: xref
- Genome annotation databases
  - Ensembl: xref
  - EnsemblBacteria: xref
  - EnsemblFungi: xref
  - EnsemblMetazoa: xref
  - EnsemblPlants: xref
  - EnsemblProtists: xref
  - GeneID: xref
  - Gramene: xref
  - KEGG: xref
  - MANE-Select: xref
  - PATRIC: xref
  - UCSC: xref
  - VectorBase: xref
  - WBParaSite: xref
- Organism-specific databases
  - ArachnoServer: xref
  - Araport: xref
  - CGD: xref
  - ConoServer: xref
  - CTD: xref
  - dictyBase: xref
  - DisGeNET: xref
  - EchoBASE: xref
  - euHCVdb: xref
  - VEuPathDB: xref
  - FlyBase: xref
  - GeneCards: xref
  - GeneReviews: xref
  - HGNC: xref
  - AGR: xref
  - HPA: xref
  - LegioList: xref
  - Leproma: xref
  - MaizeGDB: xref
  - MalaCards: xref
  - MGI: xref
  - MIM: xref
  - NIAGADS: xref
  - OpenTargets: xref
  - Orphanet: xref
  - ClinPGx: xref
  - PomBase: xref
  - PseudoCAP: xref
  - RGD: xref
  - SGD: xref
  - TAIR: xref
  - TubercuList: xref
  - VGNC: xref
  - WormBase: xref
  - Xenbase: xref
  - ZFIN: xref
  - JaponicusDB: xref
  - CIViC: xref
- Phylogenomic databases
  - eggNOG: xref
  - GeneTree: xref
  - HOGENOM: xref
  - InParanoid: xref
  - OMA: xref
  - OrthoDB: xref
  - PhylomeDB: xref
  - PAN-GO: xref
- Enzyme and pathway databases
  - BioCyc: xref
  - BRENDA: xref
  - Reactome: xref
  - SABIO-RK: xref
  - SignaLink: xref
  - SIGNOR: xref
  - UniPathway: xref
  - PlantReactome: xref
  - PathwayCommons: xref
  - STRENDA-DB: xref
- Miscellaneous
  - ChiTaRS: xref
  - EvolutionaryTrace: xref
  - Agora: xref
  - GeneWiki: xref
  - GenomeRNAi: xref
  - PHI-base: xref
  - PRO: xref
  - Pharos: xref
  - RNAct: xref
  - BioGRID-ORCS: xref
  - CD-CODE: xref
- Gene expression databases
  - Bgee: xref
  - CleanEx: xref
  - CollecTF: xref
  - ExpressionAtlas: xref
- Family and domain databases
  - AntiFam: xref
  - CDD: xref
  - FunFam: xref
  - Gene3D: xref
  - HAMAP: xref
  - IDEAL: xref
  - InterPro: xref
  - PANTHER: xref
  - Pfam: xref
  - PIRSF: xref
  - PRINTS: xref
  - SFLD: xref
  - SMART: xref
  - SUPFAM: xref
  - NCBIfam: xref
  - PROSITE: xref
  - DisProt: xref
- Proteomes databases
  - Proteomes: xref
- Database: database
Web Resources
- Webresource: cc_webresource
- Exp (Experimental Evidence): cc_webresource_exp
Date Of
- Date Of Creation: date_created
- Date of last entry modification: date_modified
- Date of last sequence modification: date_sequence_modified
Gene Ontology [GO]
- Go: go
Small molecule
- Name or ID (CHEBI): chebi
- InChIKey: inchikey
Keyword [KW]: keyword
Literature Citation
- Author: lit_author
- Journal: lit_journal
- Published: lit_pubdate
- PubMed ID: lit_pubmed
- Title: lit_title
- Citation ID: lit_citation_id
- Computational PubMed ID: computational_pubmed_id
- Community PubMed ID: community_pubmed_id
Proteomes
- Proteome ID: proteome
- Proteome Component: proteomecomponent
Cited for: scope
Reviewed: reviewed
Active: active
UniRef ID
- UniRef50: uniref_cluster_50
- UniRef90: uniref_cluster_90
- UniRef100: uniref_cluster_100
UniParc ID: uniparc

UniRef (UniProt Reference Clusters)

UniRef ID: id
Cluster name: name
Sequence identity: identity
Cluster size: count
Sequence length: length
Date of last modification: date_modified
UniProtKB ID/AC: uniprotkb
UniParc ID: uniparc
Taxonomy [OC]: taxonomy_name
Related clusters: cluster

UniParc (UniProt Archive)

UniParc ID: upi
UniProtKB AC (active only): uniprotkb
UniProtKB isoform ID: isoform
Proteome ID: proteome
Organism: organism_id
Taxonomy [OC]: taxonomy_name
Gene name [GN]: gene
Protein name: protein_name
Database: database
Active: active
Checksum (CRC64/MD5): checksum
Sequence length: length
Database ID: dbid
Feature ID: feature_id
Proteome Component: proteomecomponent

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

What our scanner noticed· Low risk

Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by

Google DeepMind

Publisher

Google DeepMind (Official)

Source

google-deepmind/science-skills · skills/uniprot_database · commit 4de6786

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-08

AutoGineer is not affiliated with or endorsed by Google DeepMind.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download uniprot-database.zip