What databases can gget access?

gget provides access to over 20 databases including Ensembl, UniProt, AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, and the RCSB Protein Data Bank.

Can I use gget for protein structure prediction?

Yes, gget includes integrated modules for AlphaFold structure prediction and downloading existing structures from the Protein Data Bank (PDB).

What format are the results returned in?

Results are typically returned as JSON or CSV when used via the command line, and as pandas DataFrames or dictionaries when used within Python scripts.

Does gget support sequence alignment?

Yes, it supports several alignment methods including BLAST, BLAT, and Multiple Sequence Alignment (MSA) using Muscle5, as well as fast local alignment with DIAMOND.

Is gget suitable for batch processing genomic data?

While gget is optimized for rapid queries and supports some batching (up to ~1000 IDs for certain modules), the documentation recommends tools like Biopython for highly advanced or massive-scale batch processing.

Bioinformatics & Genomic Data Toolkit

Name: Bioinformatics & Genomic Data Toolkit
Author: jimmc414

byjimmc414

•

324

•

Data Science & ML

Retrieves genomic, proteomic, and structural data from over 20 biological databases using a unified interface.

The gget skill empowers Claude with a comprehensive bioinformatics utility for performing rapid queries across a vast ecosystem of scientific databases. It streamlines complex research workflows such as sequence alignment via BLAST or BLAT, protein structure prediction with AlphaFold, and gene metadata retrieval from sources like Ensembl and UniProt. By integrating these capabilities into Claude's environment, researchers and developers can automate data collection, perform comparative genomics, and analyze gene expression patterns without manually navigating multiple web portals or disparate APIs.

Key Features

01Unified access to 20+ genomic databases including Ensembl, UniProt, and NCBI

02Sequence analysis tools for BLAST, BLAT, and Multiple Sequence Alignment (Muscle5)

03Single-cell RNA-seq data querying from CZ CELLxGENE Discover Census

04Functional enrichment and gene correlation analysis using Enrichr and ARCHS4

05Protein structure prediction via AlphaFold and direct PDB structure retrieval

06324 GitHub stars

Use Cases

01Predicting 3D protein structures and linear motifs for molecular biology research

02Automating the retrieval of FASTA sequences and metadata for specific gene lists

03Performing rapid BLAST searches to identify homologous sequences and genomic locations

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jimmc414/kosmos gget

For use in Claude.ai and ChatGPT

Download Skill