Skip to content
Get packs

BioServices Bioinformatics Lookup

Query UniProt, KEGG, ChEMBL-linked compound IDs, QuickGO and Reactome data from Python

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
8 files

What it does

This skill gives an AI agent a detailed guide to the BioServices Python library, which opens up many public biology databases such as UniProt (proteins), KEGG (pathways), UniChem (compound identifiers) and QuickGO (gene function annotations). Once installed, the agent knows the correct method names, response formats and common pitfalls, so it can write working code to link protein, gene, pathway and compound identifiers. It also includes helper scripts for batch ID conversion, compound cross-referencing, KEGG pathway network analysis and a multi-step protein workflow.

Great for

  • Bioinformatics students learning to pull annotations across databases
  • Researchers who need to map UniProt, KEGG or ChEBI identifiers in bulk
  • Developers building Python pipelines against these public biology APIs

Skip it if

  • Clinical or diagnostic decisions, since the outputs are database annotations that may be incomplete or outdated and pathway membership is not proof of function
  • Users without Python or without internet access, since the skill depends on live web services
  • Workflows needing unchecked identifier merges, because ambiguous compound or gene names can silently map to the wrong entity if results are not reviewed

Try asking

  • “Map these UniProt accessions to KEGG gene IDs and tell me which ones failed to map: P43403, P04637”
  • “List the KEGG pathways that contain human gene 7535 and summarize them”
  • “Find the ChEMBL IDs linked to aspirin (CHEBI:15365) using UniChem”
  • “Get GO annotations with evidence codes for UniProt P43403 across all result pages”
Step-by-step guide: how to use BioServices Bioinformatics LookupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 8 original files, the MIT licence and an attribution note.

    bioservices.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip bioservices.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip bioservices.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review the scripts before running them, since they execute Python and make outbound web requests; run them in a virtual environment first.
  • Set NCBI_EMAIL to a real address only if you use the BLAST step, and avoid putting other credentials into prompts.
  • Ask the agent to report failed identifiers and one-to-many mappings explicitly rather than accepting the first match.

What's inside

  • references/identifier_mapping.md
  • references/services_reference.md
  • references/workflow_patterns.md
  • scripts/batch_id_converter.py
  • scripts/compound_cross_reference.py
  • scripts/pathway_analysis.py
  • scripts/protein_analysis_workflow.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.