zamushwani

zamushwani/biomedical-ai-skills

Command Claude Code

Differential expression from a count matrix with DESeq2. Use when the user has bulk RNA-seq counts and wants DEGs, a volcano plot, or asks which genes differ between conditions.

zamushwani/biomedical-ai-skills

Command Claude Code

Spatial transcriptomics analysis: loading, spatial QC, spatially variable genes, deconvolution, domains. Use for Visium, Xenium, MERSCOPE, or CosMx data.

zamushwani/biomedical-ai-skills

Command Claude Code

Annotate and clinically interpret variants from a VCF. Use when the user has variant calls and wants functional annotation, ACMG classification, oncogenicity, or clinical tiers.

zamushwani/biomedical-ai-skills

Command Claude Code

Estimate immune cell composition from bulk RNA-seq. Use when the user asks about tumour microenvironment, immune infiltration, CIBERSORT/quanTIseq/xCell, or immune cell fractions.

zamushwani/biomedical-ai-skills

Command Claude Code

Fit dose-response curves and compute IC50/AUC. Use when the user has viability data across drug concentrations, or asks about IC50, EC50, or drug sensitivity.

zamushwani/biomedical-ai-skills

Command Claude Code

Kaplan-Meier curves and Cox models from clinical data. Use when the user asks about survival, prognosis, hazard ratios, or wants a KM plot.

zamushwani/biomedical-ai-skills

Command Claude Code

Quality control and filtering for single-cell RNA-seq. Use when the user has an h5ad/h5/10x matrix and wants QC, cell filtering, doublet detection, or asks why their cell count dropped.

zamushwani/biomedical-ai-skills

Command Claude Code

Query TCGA/GDC for projects, mutations, or clinical data. Use when the user asks for TCGA cohorts, mutation counts, or clinical variables from the Genomic Data Commons.

zamushwani/biomedical-ai-skills

Command Claude Code

Pathway enrichment on a ranked gene list (GSEA or ORA). Use when the user asks which pathways are enriched, wants GSEA/fgsea, or has DE results to interpret biologically.

zamushwani/biomedical-ai-skills

Command Claude Code

Tile a whole-slide image with tissue detection for downstream modelling. Use for .svs/.ndpi/.mrxs slides, OpenSlide, or when the user asks about patches, tiles, or WSI preprocessing.

zamushwani/biomedical-ai-skills

Cursor rule Cursor

Biomedical AI Skills — protocol files for cancer bioinformatics, and the rules for changing them.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Building Model Context Protocol servers that give AI agents structured, tested access to biomedical databases. Covers MCP server design, the GDC REST API behind TCGA, tool design for search and retrieval, pagination and caching, and the data-shape traps that make a naive wrapper wrong. Part 1 covers TCGA/GDC, Part 2…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Integrated analysis of expression, mutation, copy number, and methylation data from TCGA and GEO for solid tumor characterization.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Predictive biomarkers for immune checkpoint blockade: what PD-L1 IHC scores are and why expression data cannot produce them, tumour mutational burden, microsatellite instability, and the expression signatures (IFN-gamma, TIS, TIDE) that are computable from RNA. Written to keep the assay-derived biomarkers and the…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Information extraction from clinical free text. Covers note parsing and sectioning, biomedical named entity recognition, concept normalization to UMLS and ICD-10, assertion and negation detection, temporal relation extraction, adverse event identification, and de-identification. Written for public and credentialed…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Whole-slide image processing and slide-level modelling for cancer histopathology. Covers reading vendor formats with OpenSlide, the coordinate and resolution semantics that cause most WSI bugs, tissue detection, tile extraction, stain normalization, H&E colour deconvolution, pathology foundation models as tile…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Dose-response modeling and drug sensitivity prediction in cancer cell lines. Covers IC50 and AUC estimation from viability curves, retrieval and harmonization of GDSC, CTRP, and PRISM data through PharmacoGx, DepMap dependency and drug data, sensitivity prediction with regularized regression, and pharmacogenomic…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

ATAC-seq and ChIP-seq analysis for chromatin accessibility and transcription factor binding. Covers the filtering that precedes peak calling, ATAC-specific peak calling, differential binding and the DiffBind 3.x changes that silently alter results, motif enrichment, TF activity from accessibility, and assigning peaks…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

When to use scGPT, Geneformer, UCE, and the perturbation models, and when a linear baseline beats them. Covers zero-shot embedding extraction, fine-tuning for annotation, in-silico perturbation, and the benchmark evidence behind each recommendation.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Estimate immune and stromal cell composition from bulk RNA-seq using multiple algorithms. Wraps CIBERSORT, quanTIseq, EPIC, xCell, MCP-counter, TIMER, and ESTIMATE through the immunedeconv unified interface.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Systematic review and meta-analysis for clinical and preclinical evidence. Covers protocol registration, search strategy, screening, PRISMA 2020 flow diagrams, risk of bias, pooling with fixed and random effects models, small-study effects, sensitivity diagnostics, network meta-analysis, and GRADE/CINeMA certainty…

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Joint analysis of two or more molecular layers on the same samples. Covers method selection, the preprocessing that decides whether integration works at all, MOFA+ factor analysis, similarity network fusion, joint clustering for cancer subtyping, supervised integration, and survival models built on integrated features.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Genomic predictors of radiation response: DNA damage repair pathway profiling, the Radiosensitivity Index and the Genomic-Adjusted Radiation Dose built on it, post-irradiation immune activation signatures, and an honest account of what the abscopal effect can and cannot be predicted from.

zamushwani/biomedical-ai-skills

Skill Claude CodeCodex

Full single-cell RNA-seq pipeline from raw counts to biological interpretation. Covers QC, normalization, batch integration, clustering, annotation, pseudobulk DE, trajectory inference, cell-cell communication, and TF activity. Dual-language: Seurat v5 (R) and scanpy (Python).