Gtex Database
Google DeepMindOfficialPublished by Google DeepMind
- Skill
- Tool integration
- Science and research
- Apache-2.0
- Low risk
- Has scripts
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The GTEx Database skill provides an interface to the GTEx Portal API V2, enabling researchers to retrieve baseline transcriptomics data and expression Quantitative Trait Loci (eQTLs). It facilitates the mapping of gene symbols to GENCODE IDs and allows for the extraction of median TPM expression values and significant eQTL associations across 54 non-diseased adult human tissues.
What it does
- Maps standard gene symbols to Versioned GENCODE IDs.
- Retrieves median TPM expression levels for genes across specified tissues.
- Identifies tissues with the highest expression levels for a given gene.
- Fetches significant eQTLs associated with specific genes.
- Queries significant single-tissue eQTLs within defined chromosomal regions.
When to use it
- When you need to analyze baseline gene expression in healthy adult human tissues.
- When investigating the relationship between genetic variants and gene expression levels.
- When contextualizing variants within GWAS loci using eQTL data.
- When you require programmatic access to GTEx Portal data via a CLI wrapper.
Advantages
- Provides direct access to standardized GTEx transcriptomics and eQTL datasets.
- Includes a CLI wrapper that manages API rate limits automatically.
- Supports targeted queries by tissue, gene, or chromosomal region.
- Facilitates reproducible research workflows by outputting results to JSON files.
Usage examples
- “Find the top 5 tissues where the GATA4 gene is most highly expressed.”
- The agent resolves the GATA4 gene symbol to its GENCODE ID and then queries the GTEx database to return the top 5 tissues by median TPM.
- “Get all significant eQTLs for the TNF gene in Whole Blood.”
- The agent retrieves the relevant GENCODE ID for TNF and fetches the associated eQTL data specifically for the Whole Blood tissue site.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/google-deepmind/gtex-database/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip gtex-database.zip -d .agents/skills
Documentation by Google DeepMind
GTEx Database Integration
This skill retrieves transcriptomics data (RNA expression baselines) and expression Quantitative Trait Loci (eQTLs) from the GTEx Portal API V2. It provides access to median TPM (Transcripts Per Million) values for genes and significant eQTLs for variants across 54 human tissue sites.
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.User Notification: If .licenses/gtex_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://gtexportal.org/home/license and https://gtexportal.org/home/documentationPage#gtexApi, then (2) create the file recording the notification text and timestamp.
When to Use
Use this skill when you need to:
Map a gene symbol to its Versioned GENCODE ID.
Retrieve the baseline median expression level (in TPM) of a gene across various tissues.
Find the top tissues where a particular gene is most highly expressed.
Fetch significant single-tissue eQTLs for a variant or within a chromosomal window.
Get all significant eQTLs associated with a specific gene.
Contextualise a variant within GWAS loci using eQTL data.
Do NOT use when you need to:
Query for protein-level expression or post-translational modifications (PTMs). GTEx only measures mRNA abundance.
Query gene expression in diseased tissues (e.g., tumor samples, cirrhosis). GTEx is a baseline atlas of normal, non-diseased tissues.
Query embryonic or fetal gene expression. GTEx donors are adults only.
Core Rules
CRITICAL: You MUST respect GTEx Portal API Terms of Use.
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.
Limit requests to maximum 250 items per page where applicable.
Notification: If this skill is used, ensure this is mentioned in the output.
Command Selection Guide
Pick the right command on the first try. Match the user's input to the correct subcommand below.
Map a gene symbol to GENCODE ID:
resolve-gencode-idGet median expression (TPM) for a gene:
get-median-expressionFind tissues with highest expression for a gene:
get-top-expressed-tissuesGet all eQTLs for a specific gene:
get-gene-eqtlsFind eQTLs within a chromosomal region:
get-eqtls-in-region
Quick Start
# Map the TNF gene symbol to its GENCODE ID
uv run scripts/gtex_cli.py resolve-gencode-id TNF --output /tmp/tnf_id.json
# Get median expression of a gene by GENCODE ID
uv run scripts/gtex_cli.py get-median-expression ENSG00000232810.2 --output /tmp/tnf_expr.jsonAll subcommands write JSON to disk. Always save output in the /tmp/ directory.
The default output file is /tmp/gtex_output.json if --output is not
specified.
Commands
1. resolve-gencode-id — Gene Symbol → GENCODE ID
Maps a standard gene symbol (e.g., "JUN", "TNF") to its Versioned GENCODE ID. This ID is required for all other expression and eQTL calls.
uv run scripts/gtex_cli.py resolve-gencode-id TNF --output /tmp/tnf_id.jsonArguments:
gene_symbol(positional): The standard gene symbol (e.g., "TNF").--output: Output file path (default:/tmp/gtex_output.json).
2. get-median-expression — Get Median Expression (TPM)
Retrieves the median TPM for a gene across all 54 GTEx tissue sites or specified tissues.
uv run scripts/gtex_cli.py get-median-expression ENSG00000232810.2 \
--tissues "Whole Blood,Spleen" --output /tmp/expr.jsonArguments:
gencode_id(positional): The Versioned GENCODE ID.--tissues: Comma-separated list of tissue IDs (optional, defaults to all 54 tissues).--output: Output file path (default:/tmp/gtex_output.json).
3. get-top-expressed-tissues — Get Top Expressed Tissues
Returns the n tissues with the highest median expression for the target gene.
uv run scripts/gtex_cli.py get-top-expressed-tissues ENSG00000232810.2 \
--n 5 --output /tmp/top_tissues.jsonArguments:
gencode_id(positional): The Versioned GENCODE ID.--n: Number of top tissues to return (default: 5).--output: Output file path.
4. get-gene-eqtls — Get All eQTLs for a Gene
Returns every significant eQTL associated with the gene across specified tissues.
uv run scripts/gtex_cli.py get-gene-eqtls ENSG00000232810.2 \
--tissues "Whole Blood" --output /tmp/eqtls.jsonArguments:
gencode_id(positional): The Versioned GENCODE ID.--tissues: Comma-separated list of tissue IDs (optional, defaults to all).--output: Output file path.
5. get-eqtls-in-region — Get eQTLs in Chromosomal Region
Returns all significant single-tissue eQTLs within a chromosomal window (up to 8Mb).
uv run scripts/gtex_cli.py get-eqtls-in-region chr17 7000000 7100000 "Esophagus - Muscularis" \
--output /tmp/region_eqtls.jsonArguments:
chromosome(positional): Chromosome name (e.g.,chr17).start(positional): Start position.end(positional): End position (max 8Mb from start).tissue_id(positional): The target tissue ID.--output: Output file path.
Typical Workflows
Identify highest expressing tissues for a gene
# Step 1: Map symbol to GENCODE ID
uv run scripts/gtex_cli.py resolve-gencode-id GATA4 --output /tmp/gata4_id.json
# Step 2: Query for top tissues using the resolved ID
uv run scripts/gtex_cli.py get-top-expressed-tissues <gencode_id> --n 5 \
--output /tmp/gata4_top.jsonFiles
- ATTRIBUTION.mdAdded by AutoGineer908 B
- LICENSELicence file added by AutoGineer11.1 KiB
- SKILL.md5.9 KiB
- references/citation.bib5.7 KiB
- scripts/gtex_cli.pyScript8.7 KiB
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/gtex_database · commit 4de6786
- Licence
- Apache License 2.0 (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Google DeepMind or Google DeepMind.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download gtex-database.zip