What is the ENA Database skill for Claude Code?

It is a specialized capability that enables Claude to interact with the European Nucleotide Archive to search, retrieve, and manage genomic data and metadata.

Can I search for data using taxonomic names?

Absolutely. The skill supports searching for assemblies and samples using taxonomic criteria and organism names via the ENA Taxonomy REST API.

Which genomic file formats are supported?

The skill supports various formats including FASTQ (raw reads), FASTA (assembled sequences), BAM/CRAM (aligned reads), and XML/JSON for metadata.

Can I use this skill for bulk data downloads?

Yes, while it uses REST APIs for queries, it also provides implementation patterns for bulk downloads via FTP and Aspera for large datasets.

Does it handle API rate limiting?

Yes, the skill includes best practices for handling the ENA's 50 requests per second limit, including exponential backoff and batching strategies.

European Nucleotide Archive (ENA) Access

Name: European Nucleotide Archive (ENA) Access
Author: Activer007

byActiver007

データサイエンスとML

Accesses and retrieves genomic data, nucleotide sequences, and metadata from the European Nucleotide Archive (ENA) via REST APIs and FTP.

概要

This skill provides Claude with specialized capabilities to interact with the European Nucleotide Archive (ENA), allowing for programmatic retrieval of DNA/RNA sequences, raw sequencing reads, and genome assemblies. It streamlines bioinformatics workflows by facilitating metadata searches across studies and samples, taxonomic lookups, and the integration of diverse file formats like FASTQ and FASTA into analysis pipelines. Whether searching for specific accessions or performing bulk downloads via API or FTP, this skill serves as a comprehensive bridge between AI-driven development and one of the world's primary nucleotide sequence repositories.

主な機能

Advanced metadata searching across ENA studies, samples, and experiments
Guidance for high-speed bulk data transfers using FTP and Aspera
Taxonomic information retrieval and lineage mapping via the Taxonomy API
Support for multiple data formats including FASTQ, FASTA, XML, and JSON
0 GitHub stars
Programmatic retrieval of sequences and raw reads by accession number

ユースケース

Automating the retrieval of FASTQ files and raw reads for bioinformatics pipelines
Extracting genome assemblies and functional annotations for comparative genomics
Searching for all genomic samples and studies associated with specific organisms

概要

主な機能

Advanced metadata searching across ENA studies, samples, and experiments
Guidance for high-speed bulk data transfers using FTP and Aspera
Taxonomic information retrieval and lineage mapping via the Taxonomy API
Support for multiple data formats including FASTQ, FASTA, XML, and JSON
0 GitHub stars
Programmatic retrieval of sequences and raw reads by accession number

ユースケース

Automating the retrieval of FASTQ files and raw reads for bioinformatics pipelines
Extracting genome assemblies and functional annotations for comparative genomics
Searching for all genomic samples and studies associated with specific organisms