
jaechang-hits/SciAgent-Skills
Life sciences computational skills for scientific AI agents
ensembl-database
@jaechang-hits/sciagent-skills
Query Ensembl REST API for gene/transcript/variant annotations across 300+ species. Retrieve gene info by symbol/ID, sequence, cross-references (HGNC, RefSeq, UniProt), variants, regulatory features, comparative genomics. For bulk local access use pyensembl; for pathway lookups use kegg-database or reactome-database.
spikeinterface-electrophysiology
@jaechang-hits/sciagent-skills
Unified Python framework for extracellular electrophysiology. Load recordings from 20+ formats (SpikeGLX, OpenEphys, NWB, Intan, Maxwell, Blackrock), preprocess signals, run 10+ spike sorters (Kilosort4, SpykingCircus2, Tridesclous, MountainSort5) with a single API, compute quality metrics (SNR, ISI violations, firing rate, amplitude cutoff), compare sorter outputs, and export to NWB or Phy. Use for format-agnostic and multi-sorter workflows. For a Neuropixels-specific Kilosort4 pipeline with PSTH and population decoding, use neuropixels-analysis instead.
cbioportal-database
@jaechang-hits/sciagent-skills
Access TCGA and other cancer genomics datasets via cBioPortal REST API. Retrieve somatic mutations, copy number alterations, gene expression profiles, and clinical data (survival, stage, treatment) for thousands of cancer studies. Use for tumor mutation burden analysis, oncoprint queries, and survival analysis. For population variant frequencies use gnomad-database; for drug-gene interactions use dgidb-database.
