Supplementary materials and datasets for 'Improving Genomic Classification via Pearson-Based SNP Selection: A Comparison of k-NN, SVM, and Random Forest'

Provides all supplementary datasets, analysis scripts, and extended figures referenced in the manuscript. Content is organized as ZIP packages per Section 4, with a root-level README.md, MANIFEST.tsv, and DATA_DICTIONARY.tsv. Figures include color-blind-safe ROC composites (Fig.5/7 variants) and accuracy heatmaps; all metrics and runtime traces are CPU-only and reproducible with the provided scripts.How to cite. Please cite this record as the repository [59] in the manuscript and via the DOI provided by Zenodo. Citation (IEEE): P. N. Basuki, J.P. Sri Yulianto, A. Setiawan, "Supplementary materials and datasets for 'Improving Genomic Classification via Pearson-Based SNP Selection: A Comparison of k-NN, SVM, and Random Forest'". Dataset. Zenodo, v2.1.0, 2025. doi:10.5281/zenodo.17271719. v2.1.0 — Add color-blind ROC & extended figures New: extended_figures_roc_colorblind_v1.zip with ROC composites (A7, A16, A25, B1, B10, B22) and AUC bootstrap tables. New: extended_figures_heatmaps_v1.zip (accuracy heatmaps DatasetA/B). Updated: scripts_v2.1.zip including 11_fig_maker_roc_bootstrap.py and requirements.txt. Documentation: refreshed README.md, MANIFEST.tsv, DATA_DICTIONARY.tsv. No changes to conclusions; layout/content re-organization for clarity and accessibility.