skills.rest
MDhewei
MDheweiCOMMUNITY
Explore all skills by this author →
Website𝕏@hwkobeGitHub

clustering-analysis

Partition omics samples or features into clusters based on expression similarity.

64|12|Updated Apr 7, 2026
Search Tags:#visualization#consensus#omics#cluster#clustering#kmeans#dbscan
One-click install
npx skills add https://github.com/MDhewei/bioinfor-claw --skill clustering-analysis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: clustering-analysis
Source: https://github.com/MDhewei/bioinfor-claw/tree/main/machine-learning-and-deep-learning/clustering-analysis
Command: npx skills add https://github.com/MDhewei/bioinfor-claw --skill clustering-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, matplotlib, scipy, and includes scripts (resource) components.

What problem does it solve?

Partitions omics samples or features into coherent clusters based on expression similarity, enabling discovery of cell types, disease subtypes, and gene modules while providing robustness metrics.

Core Features & Use Cases

  • Supports K-means, hierarchical clustering, DBSCAN, and consensus clustering with auto k-selection and multiple distance/linkage options.
  • Generates cluster labels, quality metrics (silhouette), and visualizations (heatmaps, dendrograms, consensus matrices).
  • Use Case: Researchers can compare clustering robustness across methods to identify stable cell populations.

Quick Start

Run the clustering_analysis.py script on your expression_matrix.tsv to generate cluster labels and visualizations.

Frequently Asked Questions about clustering-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I cluster omics expression data to discover cell types and gene modules?▼

You can cluster omics data using K-means, hierarchical clustering, DBSCAN, and consensus clustering. The analysis provides auto k-selection, multiple distance and linkage options, and generates cluster labels with silhouette quality metrics.

What clustering methods work best for single-cell omics robustness assessment?▼

Consensus clustering evaluates robustness across multiple clustering strategies to identify stable cell populations. It generates consensus matrices and silhouette scores, allowing researchers to compare clustering stability and select the most reliable cluster assignments.

Can I use pandas and scipy for hierarchical clustering of bulk omics data?▼

Yes, bulk omics clustering requires standard Python libraries including pandas, numpy, scipy, and matplotlib. The clustering_analysis.py script processes your expression_matrix.tsv to generate cluster labels, silhouette metrics, and visualizations like dendrograms and heatmaps.

How do I run clustering analysis on an expression matrix TSV file?▼

Run the clustering_analysis.py script on your expression_matrix.tsv to generate cluster labels and visualizations. The script supports K-means, hierarchical, DBSCAN, and consensus clustering with auto k-selection and produces heatmaps, dendrograms, and consensus matrices.

What visualizations are generated for consensus clustering results?▼

The analysis generates heatmaps, dendrograms, and consensus matrices for visualization. These outputs help evaluate clustering quality and robustness across methods, with silhouette scores providing quantitative assessment of cluster separation.

When should I use DBSCAN instead of K-means for omics data clustering?▼

DBSCAN identifies density-based clusters without requiring a predefined k value, unlike K-means which needs the number of clusters specified upfront. The analysis supports both methods with auto k-selection, allowing comparison of clustering robustness across density-based and centroid-based approaches.

Related Skills

Explore More Data & Analytics Skills→
ya-wayya-way

bio-spatial-transcriptomics-spatial-preprocessing

Preprocess spatial transcriptomics data with Squidpy and Scanpy into PCA-ready .h5ad files.

Community
Intermediate
anthropicsanthropics
568

single-cell-rna-qc

Filter low-quality cells from single-cell RNA-seq data using MAD-based QC.

Official
Intermediate
MDheweiMDhewei
64

dimensionality-reduction

Reduce high-dimensional omics matrices to 2D/3D projections with PCA, UMAP, and t-SNE.

Community
Intermediate
chenyhvvvvchenyhvvvv
3

celltype-annotation-fast

Annotate cell types in spatial transcriptomics data using clustering, marker analysis, and LLM labeling.

Community
Intermediate