dimensionality-reduction

What problem does it solve?

Reduce high-dimensional omics data to 2D/3D visualizations to reveal sample structure, clusters, batch effects, and outliers, enabling intuitive exploration of complex datasets.

Core Features & Use Cases

• PCA, UMAP, and t-SNE visualizations of gene expression, proteomics, methylation, and other omics matrices for dimensionality reduction.
• Publication-quality plots with explained variance, loadings, and metadata-based coloring to highlight patterns across samples.
• Use Case: Compare treatment vs. control groups to identify clustering and identify potential batch effects in multi-omics experiments.

Quick Start

Run dimensionality reduction on a numeric expression matrix to generate 2D or 3D scatter plots and associated projection files.