ncbi-sequence-fetch

Official

Fetch protein & nucleotide sequences from NCBI

Authorgoogle-deepmind
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It eliminates the manual, error-prone work of finding, translating, and downloading biological sequences from NCBI when you only have accessions, gene names, locus tags, PubMed IDs, or patent numbers.

Core Features & Use Cases

  • NCBI E-utilities sequence retrieval: Pulls protein and nucleotide FASTA from NCBI using efetch/esearch and returns structured JSON results.
  • CDS translation workflows: Converts CDS or nucleotide records into protein sequences via pre-translated CDS, GenBank XML CDS extraction, or 6-frame ORF translation.
  • Flexible search entry points: Supports gene+organism, locus tag, PubMed-linked proteins, patent protein extraction, and a last-resort organism+length lookup.
  • Rate-limit and API-key support: Uses graceful throttling at 3 req/s (10 req/s with NCBI_API_KEY) and avoids asking users to paste secrets into chat.

Quick Start

Use the skill to fetch the protein FASTA for accession XP_022033624 by asking for a JSON output file location.

Dependency Matrix

Required Modules

python-dotenvscienceskillscommon

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ncbi-sequence-fetch
Download link: https://github.com/google-deepmind/science-skills/archive/main.zip#ncbi-sequence-fetch

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.