Biopython

If you're working with biological sequences, NCBI databases, or protein structures in Python, this is the standard library everyone uses. It handles the grunt work of parsing FASTA/GenBank/PDB files, running BLAST searches, pulling data from NCBI via Entrez, and doing sequence alignments without writing your own parsers. The documentation here is well organized by task: sequence I/O, alignments, database access, structural analysis, and phylogenetics. One thing to note is you need to set your email for NCBI queries (it's required) and grab an API key from your NCBI account if you want the higher rate limits. Good for batch processing and custom pipelines where you need programmatic control rather than clicking through web interfaces.

skills.sh installs: 2.1K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill biopython --agent claude-code

Installs into .claude/skills of the current project.

Files

Biopython: Computational Molecular Biology in Python

Overview

Biopython is a comprehensive set of freely available Python tools for biological computation. It provides functionality for sequence manipulation, file I/O, database access, structural bioinformatics, phylogenetics, and many other bioinformatics tasks. These examples target Biopython 1.88 (released 6 August 2026), tested here on Python 3.13. It requires Python 3.10+ and NumPy; Python 3.10 support is deprecated. Upgrade to 1.88 for its Bio.Nexus parser security fix, in addition to the Entrez XML fix in 1.87. See the release notes. Local example checks and external-service limits are recorded in references/review.md; examples requiring user files or external programs are illustrative unless listed there as exercised.