Can I use this skill for bulk data downloads?

Yes, while small files can be fetched via API, the skill provides patterns for using FTP, Aspera, or the enaBrowserTools utility for high-speed bulk transfers.

What types of records can I search for?

You can search for Studies/Projects, Samples, Raw Reads (Experiments/Runs), Genome Assemblies, and Taxonomic records.

How does this skill handle ENA API rate limits?

It follows best practices by implementing exponential backoff for HTTP 429 responses and batching requests to stay within the 50 requests per second limit.

What data formats are supported by the ENA Database skill?

The skill supports a wide range of formats including FASTQ (raw reads), FASTA (sequences), BAM/CRAM (aligned reads), and EMBL flat files for annotated sequences.

ENA Database Access

Name: ENA Database Access
Author: Activer007

byActiver007

0•

数据科学与机器学习

Access and retrieve DNA/RNA sequences, raw reads, and genome assemblies from the European Nucleotide Archive via API and FTP.

This skill enables Claude to interact seamlessly with the European Nucleotide Archive (ENA), providing a gateway to one of the world's most comprehensive repositories of nucleotide sequence data and metadata. It simplifies the process of querying studies, samples, and raw sequencing reads (FASTQ) while supporting complex searches via the ENA Portal and Browser APIs. Ideal for bioinformaticians and researchers, the skill facilitates the integration of genomic data into automated pipelines, ensures adherence to rate limits, and provides best practices for data citation and bulk retrieval.

主要功能

01Cross-reference functionality to link ENA records with external databases

02Direct retrieval of nucleotide sequences in FASTQ, FASTA, and EMBL formats

03Support for bulk data transfer protocols including FTP and Aspera

040 GitHub stars

05Advanced metadata search across studies, samples, and experiments via Portal API

06Taxonomic lineage and rank querying for specific organisms

使用场景

01Searching for all genome assemblies and associated metadata for a specific taxonomic group

02Integrating public genomic datasets into computational biology research workflows

03Automating the retrieval of raw sequencing reads for specific accession numbers in bioinformatics pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills ena-database

For use in Claude.ai and ChatGPT

Download Skill