Fast CLI/Python queries to 20+ bioinformatics databases. Gene info, BLAST, AlphaFold structures, enrichment analysis, single-cell data, disease associations. Best for interactive exploration and quick lookups. For batch/multi-database Python workflows use bioservices.
npx claudepluginhub joshuarweaver/cascade-ai-ml-engineering --plugin delphine-l-claude-globalThis skill is limited to using the following tools:
Unified CLI and Python access to 20+ genomic databases. All modules work as both command-line tools and Python functions.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Unified CLI and Python access to 20+ genomic databases. All modules work as both command-line tools and Python functions.
uv pip install --upgrade gget
Some modules require setup: gget setup alphafold|cellxgene|elm|gpt
# CLI: gget <module> [arguments]
gget search -s human BRCA1
gget info ENSG00000012048
gget seq ENSG00000012048 -t # protein sequence
# Python: gget.module(arguments)
import gget
gget.search(["BRCA1"], species="homo_sapiens")
gget.info(["ENSG00000012048"])
Common flags: -o (save to file), -csv (CSV output), -q (quiet)
scripts/gene_analysis.py - Gene discovery to sequence analysis pipelinescripts/enrichment_pipeline.py - Gene list enrichment workflowscripts/batch_sequence_analysis.py - Batch BLAST/alignment processing| Module | What it does | Example |
|---|---|---|
ref | Download reference genomes (Ensembl) | gget ref -w gtf -d human |
search | Find genes by name/description | gget search -s human "GABA receptor" |
info | Gene/transcript metadata (Ensembl+UniProt+NCBI) | gget info ENSG00000012048 |
seq | Nucleotide/protein sequences | gget seq -t ENSG00000012048 |
| Module | What it does | Example |
|---|---|---|
blast | NCBI BLAST searches | gget blast MKWMFK... -db swissprot |
blat | UCSC BLAT genomic mapping | gget blat ATCGATCG -a human |
muscle | Multiple sequence alignment | gget muscle sequences.fasta |
diamond | Fast local alignment | gget diamond query.fa -ref ref.fa |
| Module | What it does | Example |
|---|---|---|
pdb | Query Protein Data Bank | gget pdb 7S7U |
alphafold | Predict 3D structure (setup required) | gget alphafold MKWMFK... |
elm | Eukaryotic linear motifs (setup required) | gget elm LIAQSIGQASFV |
| Module | What it does | Example |
|---|---|---|
archs4 | Correlated genes / tissue expression | gget archs4 -w tissue ACE2 |
cellxgene | Single-cell RNA-seq data (setup required) | gget cellxgene --gene ACE2 --tissue lung |
enrichr | GO/pathway enrichment analysis | gget enrichr -db ontology ACE2 AGT |
bgee | Orthologs / expression across species | gget bgee ENSG00000169194 |
opentargets | Disease & drug associations | gget opentargets ENSG00000169194 |
cbio | Cancer genomics (cBioPortal) | gget cbio search breast |
cosmic | Somatic mutations (requires account) | gget cosmic EGFR |
| Module | What it does |
|---|---|
mutate | Generate mutated sequences from annotations |
setup | Install module-specific dependencies |
# Search → info → sequence → BLAST
results = gget.search(["GABA", "receptor"], species="homo_sapiens")
info = gget.info(results["ensembl_id"].tolist()[:5])
sequences = gget.seq(results["ensembl_id"].tolist()[:5], translate=True)
blast_hits = gget.blast(my_sequence, database="swissprot", limit=10)
# Tissue expression → correlated genes → enrichment
tissue_expr = gget.archs4("ACE2", which="tissue")
correlated = gget.archs4("ACE2", which="correlation")
enrichment = gget.enrichr(correlated["gene_symbol"].tolist()[:50], database="ontology", plot=True)
| Shortcut | Database |
|---|---|
pathway | KEGG_2021_Human |
transcription | ChEA_2016 |
ontology | GO_Biological_Process_2021 |
diseases_drugs | GWAS_Catalog_2019 |
celltypes | PanglaoDB_Augmented_2021 |
# Gene symbols are case-sensitive: 'PAX7' (human), 'Pax7' (mouse)
adata = gget.cellxgene(gene=["ACE2", "ABCA1"], tissue="lung", cell_type="epithelial cell")
# Filters: disease, development_stage, sex, assay, donor_id, ethnicity
orthologs = gget.bgee("ENSG00000169194", type="orthologs")
human_seq = gget.seq("ENSG00000169194", translate=True)
alignment = gget.muscle([human_seq, mouse_seq])
--limit to control result sizes-o for reproducibilitygget infogget diamond with --threads for faster local alignment; save DB with --diamond_dbgget muscle, use -s5 (Super5) for large datasets-mr 20 for accuracy, -r for AMBER relaxationuv pip install --upgrade gget (databases change structure)Adapted from K-Dense-AI/claude-scientific-skills (BSD-2-Clause). Citation: Luebbert & Pachter (2023) Bioinformatics. https://doi.org/10.1093/bioinformatics/btac836