Cancer Drug Response Prediction Via Cross-Modal Multilevel Homogeneous and Heterogeneous Feature Learning

Accurately predicting cancer drug response (CDR) is crucial for personalized cancer therapies and drug repositioning. Efficient CDR prediction requires to integrate multimodal data including sequences, structures, multilevel omics, and diverse biological networks of drugs and cell lines, to capture intricate underlying patterns. So we proposed TransGCDR, a novel method that integrates cross-modal multilevel homogeneous and heterogeneous features to derive highly discriminative embeddings, thereby enhancing CDR prediction. TransGCDR first learns structural representations of drugs using a Transformer from fingerprint substructures and Graph Convolutional Networks for molecular graphs. Meanwhile, it utilizes a Graph Attention Network to extract cell line representations from graphs integrating multilevel omics data, including gene expression, copy number variation, and somatic mutations. Next, it generates homogeneous embeddings for drugs and cell lines from these cross-modal representations while extracting drug- and cell linecentric heterogeneous contextual embeddings from prior CDRs. These embeddings are then integrated using a Residual Attention Graph Convolutional Network to obtain comprehensive representations. Finally, an MLP-based model is trained on the learned embeddings to predict CDRs. Extensive evaluations demonstrate that TransGCDR outperforms state-of-the-art methods in CDR prediction across various metrics. Ablation studies confirm that every module enhances the precise CDR characterization from the multimodal and multilevel data, which is key to the success of TransGCDR. Moreover, case studies highlight the significant clinical potential of TransGCDR to predict CDRs.