Unified Python interface to 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome, PSICQUIC). Best for cross-database analysis, ID mapping, and multi-service workflows. For quick single-database lookups use gget.
npx claudepluginhub joshuarweaver/cascade-ai-ml-engineering --plugin delphine-l-claude-globalThis skill is limited to using the following tools:
Python package providing programmatic access to ~40 bioinformatics web services. Handles REST and SOAP protocols transparently.
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.
Python package providing programmatic access to ~40 bioinformatics web services. Handles REST and SOAP protocols transparently.
uv pip install bioservices
For quick single-database lookups, prefer gget.
scripts/protein_analysis_workflow.py - End-to-end protein characterizationscripts/pathway_analysis.py - KEGG pathway network extractionscripts/compound_cross_reference.py - Multi-database compound searchscripts/batch_id_converter.py - Bulk identifier mappingfrom bioservices import UniProt
u = UniProt(verbose=False)
# Search by name
results = u.search("ZAP70_HUMAN", frmt="tab", columns="id,genes,organism")
# Retrieve FASTA
sequence = u.retrieve("P43403", "fasta")
# Map identifiers
kegg_ids = u.mapping(fr="UniProtKB_AC-ID", to="KEGG", query="P43403")
Supported mappings: UniProtKB ↔ KEGG, Ensembl, PDB, RefSeq, and many more.
from bioservices import KEGG
k = KEGG()
k.organism = "hsa"
# Find pathways containing a gene
pathways = k.get_pathway_by_gene("7535", "hsa") # ZAP70
# Parse pathway data
data = k.get("hsa04660")
parsed = k.parse(data)
# Extract interactions
interactions = k.parse_kgml_pathway("hsa04660")
sif_data = k.pathway2sif("hsa04660") # Simple Interaction Format
from bioservices import KEGG, UniChem
k = KEGG()
results = k.find("compound", "Geldanamycin") # → cpd:C11222
# KEGG → ChEMBL via UniChem
u = UniChem()
chembl_id = u.get_compound_id_from_kegg("C11222")
from bioservices import NCBIblast
s = NCBIblast(verbose=False)
jobid = s.run(program="blastp", sequence=protein_sequence,
stype="protein", database="uniprotkb",
email="your.email@example.com")
s.getStatus(jobid) # Async - check status first
results = s.getResult(jobid, "out")
from bioservices import QuickGO
g = QuickGO(verbose=False)
term_info = g.Term("GO:0003824", frmt="obo")
annotations = g.Annotation(protein="P43403", format="tsv")
from bioservices import PSICQUIC
s = PSICQUIC(verbose=False)
interactions = s.query("mint", "ZAP70 AND species:9606")
databases = s.activeDBs # 30+ databases
verbose=False to suppress HTTP request detailsk.TIMEOUT = 30hsa (human), mmu (mouse), dme (fly), sce (yeast). List all: k.list("organism")Adapted from K-Dense-AI/claude-scientific-skills (GPLv3). Docs: https://bioservices.readthedocs.io/ | Source: https://github.com/cokelaer/bioservices