Additional file 4 of Machine learning-based classification of roses using 18 SNP markers for optimized genebank management

Supplementary Material 4. Cluster-specific SNP mean values across the five clustering algorithms. Heatmaps display the mean allele values for each SNP (rows) across clusters (columns) as determined by k-means, DBSCAN, HDBSCAN, hierarchical clustering, and spectral clustering. The color intensity reflects the mean allele score per SNP per cluster, from 0 (yellow) to 4 (red). DBSCAN and HDBSCAN include cluster “0”, which represents unassigned (noise) points.