What formats are supported for sequence data?

It supports standard formats like FASTA, FASTQ, BAM, CRAM, and EMBL flat files for annotated sequences, as well as XML/JSON for metadata.

Can I search for data by taxonomic name?

Yes, the skill supports searching for assemblies and samples using organism names or taxon IDs via the ENA Taxonomy REST API and Portal API.

What data can I retrieve from ENA using this skill?

You can retrieve DNA/RNA sequences, raw sequencing reads (FASTQ), genome assemblies, and detailed metadata for studies, samples, and experiments.

How does the skill handle ENA's rate limits?

The skill follows best practices for ENA's 50 requests per second limit, including implementation patterns for exponential backoff and batching requests.

Does this skill support bulk downloads?

Yes, while small files can be accessed via API, the skill provides patterns for bulk downloading via FTP and Aspera for large datasets exceeding 100MB.

European Nucleotide Archive (ENA) Database Access

Name: European Nucleotide Archive (ENA) Database Access
Author: K-Dense-AI

byK-Dense-AI

•

3,719

•

データサイエンスとML

Accesses the European Nucleotide Archive (ENA) to retrieve DNA/RNA sequences, raw reads, and genome assemblies for bioinformatics pipelines.

This skill enables Claude to interact directly with the European Nucleotide Archive (ENA), providing programmatic access to a vast repository of nucleotide sequence data and associated metadata. It facilitates the retrieval of raw sequencing reads (FASTQ), genome assemblies, and functional annotations through REST APIs and FTP. Ideal for genomics research and bioinformatics workflows, it supports complex metadata searches across studies, samples, and experiments, while offering specialized tools for taxonomic lookups and cross-database references.

主な機能

01Advanced metadata searching across Studies, Samples, Experiments, and Runs

02Integration with bulk download methods via FTP and Aspera for large datasets

033,719 GitHub stars

04Programmatic retrieval of raw sequencing reads (FASTQ) and genome assemblies

05Support for multiple data formats including XML, JSON, TSV, FASTA, and CRAM

06Comprehensive taxonomic information and lineage querying via the ENA Taxonomy API

ユースケース

01Automating the retrieval of specific datasets for bioinformatics analysis pipelines

02Searching for all genomic assemblies associated with a specific organism or taxonomic branch

03Extracting metadata and functional annotations for comparative genomics studies

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add k-dense-ai/claude-scientific-skills ena-database

For use in Claude.ai and ChatGPT

Download Skill