Home▸AI & Machine Learning▸Gene Expression PCA Lab: Eigendecomposition & Clustering (2D)

🧬 Gene Expression PCA Lab: Eigendecomposition & Clustering (2D)

2D PCA lab: a synthetic gene-expression matrix is generated from adjustable clusters, its real covariance matrix is diagonalized with a from-scratch Jacobi eigenvalue solver, and samples are projected onto the top-2 principal components live.

AI & Machine Learning2DAdvanced60 FPS📱 Mobile-adapted⇄ 3D version

This 2D companion runs the same statistical machinery as the 3D version through a plain canvas view built for reading the linear algebra rather than orbiting a scene: a synthetic gene-expression matrix is regenerated from adjustable cluster count, separation and noise, its real covariance matrix is diagonalized with a from-scratch Jacobi eigenvalue solver, and every sample is projected onto the top-2 principal components and plotted live, alongside an explained-variance readout and a scree-plot bar chart, so the effect of each parameter on the eigendecomposition is directly visible instead of implied.

⚙ Under the hood

2D PCA lab with a from-scratch Jacobi eigenvalue solver diagonalizing the real covariance matrix of a synthetic gene-expression dataset, live explained-variance readout and scree plot.

principal component analysiseigendecompositioncovariance matrixjacobi eigenvalue algorithmgene expressiondimensionality reduction

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install