Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yuhan Zhao, Jacob Tennant, James Yang, Zhishan Guo, Young Whang, Ning Sui

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.

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

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.
Paper Structure (22 sections, 16 equations, 4 figures, 1 table)

This paper contains 22 sections, 16 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Overview of DeepDTF Framework
  4. Input Representation and Preprocessing
  5. Dual-Branch Feature Extractor
  6. Cell-line Branch: CNN with Attention + Transformer
  7. Drug Branch: GNN + Transformer
  8. Feature Fusion Joint Prediction Module
  9. Experiments and results
  10. Dataset and Pre-Processing
  11. Data sources
  12. Data preprocessing
  13. Evaluation Metrics
  14. Regression (IC50)
  15. Classification (Sensitivity)
  16. ...and 7 more sections

Figures (4)

  • Figure 1: Overall workflow of the DeepDTF, including (i) multi-omics and drug-structure inputs, (ii) transformer model (detailed in Fig. \ref{['fig:Detailed_architecture-CNN-transformer']}), (iii) dual task prediction (IC50 regression and sensitivity classification), and (iv) an interpretability module based on SHAP$\rightarrow$GSEA. SHAP produces a signed gene ranking, which is used for pre-ranked GSEA: The top panel illustrates a GSEA enrichment plot (running ES with pathway "hit" positions along the ranked list), and the bottom panel shows the corresponding null/random ES distribution for assessing enrichment direction and significance.
  • Figure 2: Detailed architecture of DeepDTF. The left block is a dual-branch feature extractor for multi-omics and drug structure. The right block is a feature fusion joint prediction module with a Fusion-Transformer and two task-specific heads for IC50 regression and sensitivity classification.
  • Figure 3: Ablation studies on omics integration and model components, where (a) and (c) show the regression performance under different combinations of omics inputs and model variants; while (b) and (d) report the classification metrics obtained from various omics integration strategies and model variants.
  • Figure 4: Cartesian-regime biological explanations via SHAP--GSEA. (a) Top genes with positive SHAP (sensitivity-associated). (b) Bottom genes with negative SHAP (resistance-associated). (c) Top enriched Hallmark pathways from signed-SHAP rankings (positive ES; sensitivity-associated programs). (d) Top enriched Hallmark pathways from negative signed-SHAP rankings (negative ES; resistance-associated programs)