clustering-analysis

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.