Open access
Aug 2026
Sparse sampling and rare-variant depletion distort PCA visualizations of population structure: recovery with objective-guided manifold learning
An objective-guided manifold-learning framework is developed that searches across genotype normalization, PCA representation and dimensionality, distance metrics, and UMAP, densMAP and PHATE parameters, and establishes optimized manifold learning as a hypothesis-generating approach.
Jan Kočí, Olga Flegontova, Piya Changmai et al.
· bioRxiv · 0 citations