How does this skill handle ENA API rate limits?

The skill is designed to respect ENA's limit of 50 requests per second by recommending exponential backoff and batching strategies for large-scale queries.

Can I use this for bulk data downloads?

Yes, the skill can identify and extract FTP or Aspera URLs for bulk datasets, which can then be used with command-line tools like enaBrowserTools for efficient transfer.

Do I need special credentials to access the ENA?

No, the European Nucleotide Archive is a public repository. This skill helps you navigate the public REST APIs and FTP servers without requiring private API keys.

What data formats does the ENA Database skill support?

The skill facilitates the retrieval of metadata in XML, JSON, and TSV formats, as well as sequence data in FASTQ, FASTA, CRAM, and EMBL flat file formats.

ENA Database Explorer

Name: ENA Database Explorer
Author: Yezez9

byYezez9

0•

データサイエンスとML

Integrates the European Nucleotide Archive (ENA) into bioinformatics workflows to programmatically retrieve genomic sequences, raw reads, and metadata.

The ENA Database skill provides a specialized interface for Claude to interact with the European Nucleotide Archive, one of the world's primary repositories for nucleotide sequence data. It enables researchers and bioinformaticians to automate the retrieval of DNA/RNA sequences, FASTQ raw reads, and genome assemblies using ENA's Portal and Browser APIs. By bridging the gap between natural language queries and complex bioinformatics API endpoints, this skill simplifies data discovery, taxonomic filtering, and the integration of public genomic datasets into analysis pipelines.

主な機能

01Advanced metadata searching across studies, samples, and experiments

02Support for high-speed data transfer via FTP and Aspera links

03Programmatic retrieval of DNA/RNA sequences and raw reads (FASTQ/BAM/CRAM)

04Integration with ENA Portal API for complex Rulespace queries

05Automated querying of taxonomic records and lineage information

060 GitHub stars

ユースケース

01Filtering and retrieving genome assemblies for specific organisms via taxonomy searches

02Automating the download of raw sequencing data for specific PRJNA accessions

03Generating metadata summaries for large-scale comparative genomics studies

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yezez9/research-agent ena-database

For use in Claude.ai and ChatGPT