google-deepmind/science-skills

quickgo-database

Query the QuickGO and Evidence & Conclusion Ontology (ECO) REST API.

Ver código fuente

Cómo usar

  1. Copia el comando y revisa el paquete antes de instalarlo en tu entorno de agente.
  2. Consulta las herramientas, credenciales y entornos necesarios en el documento original.
  3. Describe las entradas y el resultado deseado; contrasta la salida con las fuentes.
npx skills add https://github.com/google-deepmind/science-skills --skill quickgo-database

Antes de empezar

  • La instalación no incluye suscripción al modelo, cuota API ni permisos sobre tus archivos.
  • Las estrellas e instalaciones reflejan actividad, no una prueba independiente de calidad o seguridad.
Documento original del Skill

Contenido del repositorio de origen con títulos, ejemplos, código, tablas, enlaces e imágenes preservados.

QuickGO Database Skill

GO (Gene Ontology) annotations are one of the main ways to label a gene's function. QuickGO is a fast, web-based browser for the GO and Evidence & Conclusion Ontology (ECO), maintained by the Gene Ontology Annotation (GOA) group at EMBL-EBI.

It provides a centralised resource to explore the functional attributes of gene products (proteins, RNA, and complexes). It is a primary tool for functional annotation mapping since it allows you to link a gene (e.g., USH2A) to its specific biological processes (e.g. sensory perception of light stimulus), molecular functions, and cellular components.

Prerequisites

  1. `uv`: Read the uv skill and follow its Setup instructions to ensure

uv is installed and on PATH.

  1. User Notification: If .licenses/quickgodatabaseLICENSE.txt does not

already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/QuickGO/ and https://www.ebi.ac.uk/QuickGO/api/index.html, then (2) create the file recording the notification text and timestamp.

Usage

This skill provides a Python CLI wrapper scripts/quickgo_tool.py that queries the QuickGO REST API. It handles formatting the requests, respecting rate limits, and safely storing the potentially large JSON responses.

Core Rules

  • Use the Wrapper: ALWAYS execute the provided helper scripts to query the

database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully.

  • Pagination & Limits: Restrict endpoints to a maximum of 100 results per

page using --limit 100 and the --page parameter for larger datasets.

  • Output Files: Always use the --output flag to save responses to a file

incrementally or parse via jq.

  • Evidence Codes: Prioritize experimental evidence (ECO:0000269) over

electronic (ECO:0000501) to avoid noisy predictions.

  • Taxon Filtering: Use --taxonId 9606 to restrict results to Human when

analysing clinical or human genomic data.

  • Notification: If this skill is used, ensure this is mentioned in the

output.

The tool has four main subcommands:

  1. `go`: For retrieving information about GO terms (e.g. definitions,

ancestors, descendants, and slims). See references/go_terms.md.

  1. `annotation`: For finding functional annotations linking gene products

to GO terms. This is your primary functional mapper. See references/annotations.md.

  1. `geneproduct`: For resolving gene symbols (like PROC) to their formal

database identifiers. See references/gene_products.md.

  1. `eco`: For Evidence & Conclusion Ontology terms (used in annotations to

indicate how an annotation was derived, e.g. experimental vs electronic). See references/eco_terms.md.

Common Workflows

1. Map a gene to its functions (Annotations)

To find out what a gene does, you must first resolve its symbol to a UniProtKB ID, and then query its annotations. Often it is best to filter for experimental evidence (e.g. ECO:0000269 for EXP, or others like IDA, IMP) to avoid noisy electronic predictions.

bash
# Step 1: Find the UniProtKB ID for human (9606) gene PROC
uv run scripts/quickgo_tool.py geneproduct search --query "PROC" --taxonId 9606 --limit 5 --output proc_id.json
# (Look at proc_id.json, observe the ID is e.g., UniProtKB:P04070)

# Step 2: Find experimental GO annotations for that ID
uv run scripts/quickgo_tool.py annotation search --geneProductId "UniProtKB:P04070" --taxonId 9606 --evidenceCode "ECO:0000269" --limit 50 --output proc_annotations.json

2. Find all genes in a pathway

To find all genes annotated to a specific GO term (e.g., GO:0003700 for "transcription factor activity"):

bash
# Find human genes with this specific molecular function
uv run scripts/quickgo_tool.py annotation search --goId "GO:0003700" --taxonId 9606 --limit 50 --output tf_genes.json

3. Explore the GO Hierarchy

To check if a specific GO term is a descendant of a broader category, or to fetch its definition:

bash
# Fetch term details (definitions, synonyms)
uv run scripts/quickgo_tool.py go terms --ids "GO:0003150" --output term_details.json

# Check ancestry (e.g., is GO:0001917 a child of something?)
uv run scripts/quickgo_tool.py go terms --ids "GO:0001917" --relation ancestors --output term_ancestors.json

4. Create a GO Slim Summary

If you have a list of candidate genes and want a high-level functional summary, you can map them up to a predefined GO Slim. First, fetch the annotations for the genes to extract their GO IDs, then pass those IDs to the slim endpoint:

bash
# Step 1: Find GO IDs for candidate genes (e.g., via their UniProt IDs, fetching their annotations)
# ... (output yields e.g., GO:0006915,GO:0008219)

# Step 2: Create a slim summary from those specific GO IDs
uv run scripts/quickgo_tool.py go slim --slimsToIds "GO:0005575,GO:0008150,GO:0003674" --slimsFromIds "GO:0006915,GO:0008219" --output my_slim.json
del mismo repositorio

Más Skills

Todos los Skills
google-deepmind
Comunidad

clinical-trials-database

Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.

Instalaciones / 1h
1
GitHub Stars
3,5 mil
Actualizado
10 nov
google-deepmind
Comunidad

opentargets-database

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

Instalaciones / 1h
1
GitHub Stars
3,5 mil
Actualizado
10 nov
google-deepmind
Comunidad

pubchem-database

Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. Use when a user asks about a specific chemical, drug, or molecule.

Instalaciones / 1h
1
GitHub Stars
3,5 mil
Actualizado
10 nov
google-deepmind
Comunidad

alphagenome-atlas-website-links

Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based VCF-style coordinates), genomic locus views (1-based closed chr:start-end), candidate summary tables, and AlphaGenome reference vs. alternate predictions. Use when visualizing, exploring, charting, or linking genetic variants and genomic loci on the AlphaGenome Atlas, or when asked to inspect, view, or link predictions for a genomic variant. Don't use for computing raw

Instalaciones / 1h
1
GitHub Stars
3,5 mil
Actualizado
10 nov