DeepDTF: Dual-Branch Transformer Fusion for Multi-Omics Anticancer Drug Response Prediction

TL;DR

DeepDTF is a novel dual-branch Transformer model that effectively integrates multi-omics data and drug molecular graphs to improve anticancer drug response prediction, offering both high accuracy and biological interpretability.

Contribution

The paper introduces DeepDTF, a dual-branch Transformer framework that aligns multi-omics and drug data for enhanced predictive performance in cancer drug response modeling.

Findings

Outperforms existing models on pharmacogenomic benchmarks

Achieves up to RMSE=1.248 and AUC=0.987 with full multi-omics data

Provides biologically meaningful explanations via gene attribution and pathway analysis

Abstract

Cancer drug response varies widely across tumors due to multi-layer molecular heterogeneity, motivating computational decision support for precision oncology. Despite recent progress in deep CDR models, robust alignment between high-dimensional multi-omics and chemically structured drugs remains challenging due to cross-modal misalignment and limited inductive bias. We present DeepDTF, an end-to-end dual-branch Transformer fusion framework for joint log(IC50) regression and drug sensitivity classification. The cell-line branch uses modality-specific encoders for multi-omics profiles with Transformer blocks to capture long-range dependencies, while the drug branch represents compounds as molecular graphs and encodes them with a GNN-Transformer to integrate local topology with global context. Omics and drug representations are fused by a Transformer-based module that models cross-modal interactions and mitigates feature misalignment. On public pharmacogenomic benchmarks under 5-fold cold-start cell-line evaluation, DeepDTF consistently outperforms strong baselines across omics settings, achieving up to RMSE=1.248, R^2=0.875, and AUC=0.987 with full multi-omics inputs, while reducing classification error (1-ACC) by 9.5%. Beyond accuracy, DeepDTF provides biologically grounded explanations via SHAP-based gene attributions and pathway enrichment with pre-ranked GSEA.