Supplementary Tables S2, S4 and S5 for "Machine Learning–Driven Integration of Cancer Cell Phenotypes Predicts Cisplatin Sensitivity"

Overview - Figure_S1_v1.0_2025-08-15.jpg, Result_of_hierarchical_clustering. A dendrogram of hierarchical clustering is shown. Using a cutoff distance of 8, 190 cancer cell lines were divided into four clusters. - Table_S2_List_of_cell_lines_v1.0_2025-08-10.xlsx, List of cell lines included in the analyses. -Table_S4_Results_of_DEG_analysis_between_cluster_2_(Resistant)_and_cluster_4_(Sensitive)_using_pyDESeq2_v1.0_2025-08-10.xlsx, Differential expression analysis results between cluster 2 (resistant) and cluster 4 (sensitive) using pyDESeq2. - Table_S5_List_of_SHAP_values_for_each_gene_based_on_machine_learning_model_v1.0_2025-08-10.xlsx, SHAP values per gene derived from the machine learning model. Keywords cisplatin, machine learning, omics, RNAseq, SHAP, LightGBM, TCGA