Additional file 7 of Machine learning-based classification of roses using 18 SNP markers for optimized genebank management

Supplementary Material 7. Confusion matrix displaying the classification performance of the svmRadial Model for roses bred before and after 1930. The matrix shows the proportion of correctly and incorrectly predicted samples per class (in percents). The reference (true) classes are shown on the vertical axis, and the predicted classes are shown on the horizontal axis. Darker shading indicates a higher proportion of predictions within a cell. The model’s ability to distinguish between cluster labels is reflected by high values along the diagonal (correct predictions) and minimal off-diagonal misclassifications.