gget-genomic-databases
Unified CLI/Python interface to 20+ genomic databases. Gene lookups (Ensembl search/info/seq), BLAST/BLAT, AlphaFold, Enrichr enrichment, OpenTargets disease/drug, CELLxGENE single-cell, cBioPortal/COSMIC cancer, ARCHS4 expression. Spans genomics, proteomics, disease. For batch/advanced BLAST use biopython; for multi-DB Python SDK use bioservices.
npx skills add BioTender-max/awesome-bio-agent-skills --skill gget-genomic-databases --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
gget-genomic-databases offers a unified interface to access 20+ genomic databases and analysis methods through both a CLI and Python API. It supports gene searches, metadata, sequences, BLAST/BLAT, protein structure prediction with AlphaFold, enrichment analyses, OpenTargets disease/drug data, CELLxGENE single-cell data, cancer databases (cBioPortal, COSMIC), ARCHS4 expression, and related utilities. Outputs are DataFrames in Python or JSON/CSV in CLI, with options to save or request JSON.
How it works
The skill documents multiple modules under a common API pattern: import gget and call module-specific functions (e.g., gget.search, gget.info, gget.seq, gget.blast, gget.alphafold, gget.enrichr, gget.opentargets, gget.cbio_plot). It shows both Python usage and CLI-like actions, including rate-limiting notes and options such as species filtering, release pinning, and save modes. It describes usage for module families: Reference & Gene Search (ref, search, info, seq); Sequence Alignment (blast, blat, muscle, diamond); Protein Structure (pdb, alphafold, elm); Expression (archs4, cellxgene, bgee); Disease & Drug Associations (opentargets, enrichr); Cancer Genomics (cbio, cosmic); Mutation Utilities (mutate, setup).
When to use it
Use when you need: gene information across Ensembl, retrieving sequences, running remote/local alignment, predicting structures, enrichment analyses, CELLxGENE single-cell data, OpenTargets associations, ARCHS4 tissue expression and correlations, and cancer genomics data. It also advises workflow patterns and reproducibility practices like pinning versions ( ref with release, cellxgene census version) and rate-limiting between BLAST queries.
What it can touch
The skill references the following inputs and tools: CLI and Python interfaces under the gget package, modules such as search, info, seq, blast, blat, muscle, diamond, pdb, alphafold, elm, archs4, cellxgene, bgee, opentargets, enrichr, cbio, cosmic, mutate, setup. It notes usage of optional setups (gget setup <module>) and environment considerations. It mentions saving outputs (save), exporting JSON, and database pinning via release and census_version. It also includes rate-limiting with time.sleep and mentions Python package installation via pip.
Caveats
License: BSD-2-Clause. The skill notes require optional setups and environment preparation (e.g., alphafold, cellxgene, elm, gpt). Databases update biweekly; users are advised to keep gget updated. COSMIC usage requires account and local database download. Some modules have significant resource needs (e.g., AlphaFold ~4GB model).
# gget — Unified Genomic Database Access ## Overview gget is a command-line and Python package providing unified access to 20+ genomic databases and analysis methods. Query gene information, sequences, protein structures, expression data, and disease associations through a consistent interface. All modules work as both CLI tools and Python functions, returning DataFrames (Python) or JSON/CSV (CLI). ## When to Use - Looking up gene information (names, IDs, descriptions) across species from Ensembl - Retrieving nucleotide or protein sequences for Ensembl gene/transcript IDs - Running BLAST or BLAT searches against standard reference databases - Predicting protein 3D structures with AlphaFold2 from amino acid sequences - Performing gene set enrichment analysis (GO, KEGG, disease terms) via Enrichr - Querying single-cell RNA-seq datasets from CELLxGENE Census - Finding disease and drug associations for a gene target via OpenTargets - Downloading Ensembl reference genomes and annotations for a species - Finding cancer mutations and genomic alterations via cBioPortal or COSMIC - Getting tissue expression and correlated genes from ARCHS4 - For batch processing or advanced BLAST parameters
- Overview
- When to Use
- Prerequisites
- Quick Start
- Core API
- Module 1: Reference & Gene Search (ref, search, info, seq)
- Module 2: Sequence Alignment (blast, blat, muscle, diamond)
- Module 3: Protein Structure (pdb, alphafold, elm)
- Module 4: Expression & Correlation (archs4, cellxgene, bgee)
- Module 5: Disease & Drug Associations (opentargets, enrichr)
- Module 6: Cancer Genomics (cbio, cosmic)
- Module 7: Mutation Generation & Utilities (mutate, setup)
- Key Concepts
- Module Overview
pip install gget gget setup alphafold # ~4GB model parameters, requires OpenMM gget setup cellxgene # cellxgene-census package gget setup elm # local ELM database Download GTF and cDNA for human (specific release) gget ref -w gtf -w cdna -d -r 112 homo_sapiens Download genome DNA gget ref -w dna -d homo_sapiens
What does the gget-genomic-databases skill do?
Unified CLI/Python interface to 20+ genomic databases. Gene lookups (Ensembl search/info/seq), BLAST/BLAT, AlphaFold, Enrichr enrichment, OpenTargets disease/drug, CELLxGENE single-cell, cBioPortal/COSMIC cancer, ARCHS4 expression. Spans genomics, proteomics, disease. For batch/advanced BLAST use biopython; for multi-DB Python SDK use bioservices.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill gget-genomic-databases --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.