Bioinformatics
- 30 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
bioinformatics is a Claude skill that guides bioinformatics analyses such as pathway enrichment, GO analysis, PPI networks, and multi-omics integration.
About
Guides bioinformatics analyses including pathway enrichment, gene ontology, protein-protein interaction networks, single-cell RNA-seq, and multi-omics integration. A researcher uses it when working with gene sets, biological pathways, functional annotation, or omics data and needs a rigorous methodology plus the right databases and tools. It enforces ID mapping, multiple-testing correction, and confidence thresholds.
- Guides pathway enrichment, GO analysis, PPI networks, and multi-omics integration
- References KEGG, Reactome, STRING, clusterProfiler, Seurat/Scanpy, Cytoscape
- Includes a 7-step methodology and a 9-item quality checklist
Bioinformatics by the numbers
- 30 all-time installs (skills.sh)
- Ranked #1,107 of 2,065 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
bioinformatics capabilities & compatibility
- Capabilities
- biopython · biostatistics · biopython bio
- Use cases
- research · data analysis
- Pricing
- Free
What bioinformatics says it does
Performs bioinformatics analyses including pathway enrichment, gene ontology analysis, protein-protein interaction networks, multi-omics integration, and biological sequence database querying
Build PPI networks from STRING (confidence > 0.7 for high confidence).
Dimensionality reduction (PCA, UMAP). Clustering (Leiden, Louvain).
npx skills add https://github.com/beita6969/scienceclaw --skill bioinformaticsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 30 |
|---|---|
| repo stars | ★ 869 |
| Last updated | June 8, 2026 |
| Repository | beita6969/scienceclaw ↗ |
What it does
Run pathway enrichment, GO analysis, PPI networks, and multi-omics integration on gene or omics data.
Who is it for?
Researchers analyzing gene sets, pathways, functional annotation, or single-cell and multi-omics data.
Skip if: Simple sequence manipulation (use biopython) or clinical survival statistics (use biostatistics).
When should I use this skill?
The user discusses gene sets, biological pathways, functional annotation, or omics data integration.
What you get
Enrichment tables, networks, volcano plots, and UMAPs produced with correct corrections and thresholds.
- Enrichment result tables
- PPI network figures
- Volcano plots, heatmaps, UMAP/tSNE plots
By the numbers
- 7-step methodology
- 9-item quality checklist
- STRING confidence > 0.7 for high-confidence PPI
Files
When to Trigger
Activate this skill when the user mentions:
- Pathway analysis, KEGG, Reactome, WikiPathways
- Gene Ontology (GO) enrichment, biological process, molecular function
- Protein-protein interaction (PPI) networks, STRING, BioGRID
- Multi-omics integration (transcriptomics + proteomics + metabolomics)
- Gene set enrichment analysis (GSEA), over-representation analysis (ORA)
- Sequence databases, UniProt, NCBI, Ensembl queries
- Single-cell RNA-seq analysis, clustering, trajectory inference
Step-by-Step Methodology
1. Data preparation - Standardize gene/protein identifiers (convert to Entrez, Ensembl, or UniProt IDs as needed). Remove duplicates and handle ambiguous mappings. Verify organism and genome build. 2. Differential analysis - For transcriptomics: DESeq2 or edgeR (count data), limma-voom (normalized). For proteomics: limma with appropriate normalization. Apply multiple testing correction (BH-FDR). Set thresholds (|log2FC| > 1, padj < 0.05 as defaults, adjustable). 3. Functional enrichment - Perform GO enrichment (BP, MF, CC) using clusterProfiler, g:Profiler, or DAVID. Run KEGG/Reactome pathway enrichment. Use GSEA for ranked gene lists (no arbitrary cutoff). Report enriched terms with gene ratio, p-value, adjusted p-value, and gene members. 4. Network analysis - Build PPI networks from STRING (confidence > 0.7 for high confidence). Identify hub genes (degree centrality), bottleneck nodes (betweenness centrality), and functional modules (MCODE, Louvain clustering). Overlay expression data on network. 5. Multi-omics integration - For paired omics: correlation analysis, canonical correlation (CCA), or MOFA/DIABLO. Map features across omics layers using shared identifiers or known biological connections. Identify convergent pathways. 6. Single-cell analysis - QC filtering (genes/cell, UMI/cell, mitochondrial %). Normalization (scran, SCTransform). Dimensionality reduction (PCA, UMAP). Clustering (Leiden, Louvain). Cell type annotation (SingleR, scType, marker genes). Trajectory inference (Monocle3, Slingshot). 7. Visualization - Generate volcano plots, heatmaps (with hierarchical clustering), dot plots (enrichment), network diagrams, UMAP/tSNE plots (single-cell), and circos plots (multi-omics).
Key Databases and Tools
- Gene Ontology (GO) - Functional annotations
- KEGG / Reactome / WikiPathways - Pathway databases
- STRING / BioGRID / IntAct - PPI databases
- Ensembl / NCBI / UniProt - Sequence and annotation databases
- clusterProfiler / g:Profiler / DAVID - Enrichment tools
- Seurat / Scanpy - Single-cell analysis frameworks
- Cytoscape - Network visualization
Output Format
- Enrichment results as tables: term, description, gene ratio, p-value, padj, gene list.
- Volcano plots with labeled significant genes and fold-change thresholds.
- Network figures with node coloring (expression), size (degree), and module highlighting.
- UMAP/tSNE plots with cluster labels and cell type annotations.
- Heatmaps with dendrograms and annotation bars.
Quality Checklist
- [ ] Gene ID mapping verified (conversion losses reported)
- [ ] Background gene set appropriate for enrichment analysis
- [ ] Multiple testing correction applied (BH-FDR or equivalent)
- [ ] Redundant GO terms handled (semantic similarity, REVIGO)
- [ ] Network confidence threshold specified and justified
- [ ] Single-cell QC thresholds documented
- [ ] Batch effects assessed and corrected if present
- [ ] Results cross-validated across databases or methods
- [ ] Biological interpretation grounded in literature
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511FAQ
Which enrichment tools does it use?
clusterProfiler, g:Profiler, and DAVID for GO and KEGG/Reactome enrichment, plus GSEA for ranked lists.
What confidence threshold for PPI networks?
It recommends STRING confidence > 0.7 for high-confidence interactions.