Query multiple genomic databases via a unified CLI and Python interface.
npx skills add https://github.com/rubensliv/k-dense-ai --skill gget-rubensliv
Please help me install this Agent Skill. Skill: gget Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/gget Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill gget-rubensliv
Complex genomic research often requires querying numerous databases (Ensembl, UniProt, NCBI, ARCHS4, OpenTargets, COSMIC, PDB) and stitching results across disparate tools. gget provides a single, coherent CLI and Python API to access 20+ genomic databases and analysis methods, streamlining discovery and analysis workflows.
Run a full workflow by searching for a gene, retrieving its metadata, sequences, expression data, and enrichment results in one command.
High-intent search queries and answers about installing and using this skill.
You can query multiple genomic databases from a single Python script by using a unified CLI and Python API that consolidates access to Ensembl, UniProt, NCBI, and COSMIC. This allows you to retrieve sequences, metadata, and expression data in one reproducible workflow.
The best way to retrieve gene sequences and run enrichment analysis programmatically is using a unified CLI that integrates sequence retrieval and enrichment modules. You can search for a gene and automatically retrieve its sequence, expression data, and enrichment results in a single command.
Yes, this genomic data querying approach supports batch processing and scriptable workflows for scalable research. It applies modular data access to handle multiple queries across 20+ genomic databases, ensuring reproducibility in large-scale genomics studies.
Yes, you can use pandas with this bioinformatics CLI since pandas is a core dependency. The unified interface outputs query results from databases like ARCHS4 and OpenTargets in formats that pandas can directly process for downstream analysis.
To fetch gene expression profiling data from ARCHS4 and OpenTargets, you use the unified CLI's dedicated expression and disease association modules. It applies a consistent Python interface to pull and structure expression results across these platforms.
You should use a unified CLI instead of separate tools when your bioinformatics workflow requires stitching results across disparate genomic databases. A unified interface streamlines gene discovery, sequence analysis, and cross-database disease exploration while maintaining reproducibility.
robotlearning123Query and download COSMIC cancer mutation data in TSV, CSV, and VCF formats.
zongtingweiNormalize and quality-check bulk RNA-seq count matrices with Python.
robotlearning123Generate protein sequences, structures, and functions using ESM3 and ESM C models.
robinbarvaagQuery over 20 genomic databases for gene, sequence, and expression data.
