Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

BioServices Unified Bioinformatics Access

Query 40+ bioinformatics databases such as UniProt, KEGG, ChEMBL and Reactome through one consistent Python interface.

Data & AnalyticsIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Teaches Claude to drive the bioservices Python package, which wraps roughly 40 bioinformatics web services behind a single API and hides the REST/SOAP differences. You get protein sequences and annotations (UniProt, PDB, Pfam), pathway analysis (KEGG, Reactome), compound lookups (ChEBI, ChEMBL, PubChem), Gene Ontology queries (QuickGO) and protein–protein interactions (PSICQUIC, IntAct).

It shines at cross-database identifier mapping (UniProtKB↔KEGG↔Ensembl↔PDB) and multi-step pipelines that chain several services together. The skill also documents version-specific breakages (removed UniChem helpers, PSICQUIC missing in 1.16.0) plus safe fallbacks, which prevents a lot of silent failures.

Who it's for

  • Researchers and grad students who must merge data from several biological databases
  • Bioinformatics engineers doing bulk ID conversion for genes, proteins or compounds
  • Anyone building reproducible life-science analysis pipelines in Python
  • If you only need a quick single-database lookup, gget is lighter; for sequence file wrangling use biopython

Example uses

  1. "Look up ZAP70_HUMAN in UniProt, pull the FASTA, then report its KEGG pathways and interaction partners" → protein_analysis_workflow.py runs search → sequence → BLAST → pathways → interactions end to end.
  2. "Find the KEGG compound ID for Geldanamycin and cross-map it to ChEBI and ChEMBL" → UniChem-based compound cross-referencing.
  3. "Convert this file of 500 UniProt accessions into KEGG gene IDs" → batch conversion via batch_id_converter.py.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/bioservices folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/bioservices/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/bioservices ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm you have Python 3.9–3.12: python3 --version
  2. Clone the skill repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Copy the skill into your Claude Code skills folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/bioservices ~/.claude/skills/
  4. Install the library: uv pip install "bioservices==1.16.0" (or pip install "bioservices==1.16.0" if you don't use uv)
  5. If you plan to run NCBI BLAST, export a contact email: export NCBI_EMAIL=you@lab.org (add it to ~/.bashrc or ~/.zshrc to persist)
  6. Restart Claude Code and try a prompt such as "Use bioservices to fetch details for UniProt P43403".
  7. Every call hits external APIs, so verify internet access and that your firewall allows EBI/NCBI/KEGG domains; expect rate limits on heavy batches.
View source on GitHub ↗License: MIT