Data and code for: A selectivity-aware machine-learning workflow for prioritizing CDK2-biased kinase inhibitor candidates

This record contains the curated data tables, figure source data, final manuscript figures, supplementary figure files, and Jupyter notebooks supporting the manuscript “A selectivity-aware machine-learning workflow for prioritizing CDK2-biased kinase inhibitor candidates.” The workflow integrates curated CDK bioactivity data, molecular standardization, RDKit descriptors, Morgan fingerprints, target-specific Extra Trees models, retrospective and scaffold-held-out enrichment analysis, analog generation, applicability-domain filtering, medicinal-chemistry triage, control-compound benchmarking, molecular docking summaries, and MM-GBSA prioritization. The package is intended to support reproducibility of the computational analyses, tables, and figures reported in the manuscript.