Do I need an API key to use the Gene Database skill?

While not strictly required, using a free NCBI API key is recommended to increase rate limits from 3-5 requests per second to 10 requests per second for faster batch processing.

What formats can I retrieve gene data in?

Data can be retrieved in various formats including JSON for programmatic processing, XML for hierarchical metadata, and FASTA or GenBank for sequence analysis.

Which NCBI APIs does this skill support?

This skill supports both the traditional E-utilities (ESearch, ESummary, EFetch) for complex database queries and the modern NCBI Datasets API for streamlined metadata and sequence retrieval.

Can I search for genes by phenotype or disease?

Yes, the skill allows you to use biological context search patterns, such as searching for specific phenotypes or disease associations within the NCBI database.

NCBI Gene Database Skill

Name: NCBI Gene Database Skill
Author: jimmc414

byjimmc414

•

324

Data Science & ML

Queries the NCBI Gene database to retrieve comprehensive genetic information, sequences, and functional annotations for biological research.

About

The NCBI Gene Database skill integrates Claude with the National Center for Biotechnology Information (NCBI) to automate genomic data retrieval. It provides a robust interface for searching genes by symbol, ID, or biological context using both E-utilities and the modern NCBI Datasets API. Designed for bioinformaticians and researchers, this skill streamlines workflows for fetching RefSeqs, Gene Ontology (GO) annotations, chromosomal maps, and phenotypic data, making it an essential tool for autonomous scientific discovery and high-throughput gene analysis.

Key Features

Seamless integration with both E-utilities and the NCBI Datasets API
Support for high-throughput batch lookups with built-in rate limit management
324 GitHub stars
Search genes by symbol, ID, organism, chromosomal location, or disease association
Access sequence data via RefSeqs in JSON, XML, or FASTA formats
Retrieve detailed metadata including nomenclature, aliases, and functional pathways

Use Cases

Validating gene lists and cross-referencing identifiers across global genomic resources
Fetching sequences and phenotypic information for target genes in disease research
Automating gene annotation and metadata enrichment for large genomic datasets

About

Key Features

Seamless integration with both E-utilities and the NCBI Datasets API
Support for high-throughput batch lookups with built-in rate limit management
324 GitHub stars
Search genes by symbol, ID, organism, chromosomal location, or disease association
Access sequence data via RefSeqs in JSON, XML, or FASTA formats
Retrieve detailed metadata including nomenclature, aliases, and functional pathways

Use Cases

Validating gene lists and cross-referencing identifiers across global genomic resources
Fetching sequences and phenotypic information for target genes in disease research
Automating gene annotation and metadata enrichment for large genomic datasets