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

2026-03-25

AI Summary

This work proposes an end-to-end dual-branch Transformer fusion framework to address the challenge of cross-modal alignment between multi-omics data and drug structures for improved anticancer drug response prediction. The architecture employs modality-specific encoders: one processes cell line multi-omics features, while the other handles molecular graphs of drugs via a hybrid GNN-Transformer model. A cross-modal Transformer module then integrates information from both branches, jointly optimizing sensitivity regression and classification objectives. This design effectively mitigates feature misalignment and enhances biological interpretability through integrated SHAP and GSEA analyses. Under cold-start evaluation settings, the model achieves an RMSE of 1.248, an R² of 0.875, and an AUC of 0.987, reducing classification error by 9.5%.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• multi-omics
• drug response prediction
• cross-modal alignment
• precision oncology
• molecular heterogeneity

Innovation

• Dual-Branch Transformer
• Multi-Omics Integration
• GNN-Transformer Fusion
• Cross-Modal Alignment
• Drug Response Prediction