Background For translational impact, both accurate drug response prediction and biological plausibility of predictive features are needed. We present drGT, a heterogeneous graph deep learning model over drugs, genes, and cell lines that couples prediction with mechanism-oriented interpretability via attention coefficients (ACs). Results We assess both predictive generalization (random, unseen-drug, unseen-cell, and zero-shot splits) and biological plausibility (use of text-mined PubMed gene-drug co-mentions and comparison to a structure-based DTI predictor) on GDSC, NCI60, and CTRP datasets. Across benchmarks, drGT consistently delivers top regression performance while maintaining competitive classification accuracy for drug sensitivity. Under random 5-fold cross-validation, drGT attains an AUROC of up to 0.945 (3rd overall) and an <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(R^2\)</EquationSource></InlineEquation> up to 0.690, outperforming all baselines on regression. In leave-one-out tests for unseen cell lines and drugs, drGT achieves AUROCs of 0.706 and 0.844, and <InlineEquation ID="IEq2"><EquationSource Format="TEX">\(R^2\)</EquationSource></InlineEquation> values of 0.692 and 0.022, the only model yielding positive <InlineEquation ID="IEq3"><EquationSource Format="TEX">\(R^2\)</EquationSource></InlineEquation> for unseen drugs. In zero-shot prediction, drGT achieves an AUROC of 0.786 and a regression <InlineEquation ID="IEq4"><EquationSource Format="TEX">\(R^2\)</EquationSource></InlineEquation> of 0.334, both representing the highest scores among all models. For interpretability, AC-derived drug-gene links recover known biology: among 976 drugs with known DTIs, 36.9% of predicted links match established DTIs, and 63.7% are supported by either PubMed abstracts or a structure-based predictive model. Enrichment analyses of AC-prioritized genes reveal drug-perturbed biological processes, providing pathway-level explanations. Conclusions drGT advances predictive generalization and mechanism-centered interpretability, offering state-of-the-art regression accuracy and literature-supported biological hypotheses that demonstrate the use of graph learning from heterogeneous input data for biological discovery. Code: <a href="https://github.com/sciluna/drGT">https://github.com/sciluna/drGT</a>.

drGT: Interpretable Drug Response Prediction with Attention-Guided Gene Attribution on a Drug-Cell-Gene Heterogeneous Graph

期刊论文
出版模式：

开放获取
发表日期：

2026年6月16日

查看全文

Yoshitaka Inoue,
Hunmin Lee,
Tianfan Fu,
Rui Kuang,
Augustin Luna

摘要

Background

For translational impact, both accurate drug response prediction and biological plausibility of predictive features are needed. We present drGT, a heterogeneous graph deep learning model over drugs, genes, and cell lines that couples prediction with mechanism-oriented interpretability via attention coefficients (ACs).

Results

We assess both predictive generalization (random, unseen-drug, unseen-cell, and zero-shot splits) and biological plausibility (use of text-mined PubMed gene-drug co-mentions and comparison to a structure-based DTI predictor) on GDSC, NCI60, and CTRP datasets. Across benchmarks, drGT consistently delivers top regression performance while maintaining competitive classification accuracy for drug sensitivity. Under random 5-fold cross-validation, drGT attains an AUROC of up to 0.945 (3rd overall) and an \(R^2\) up to 0.690, outperforming all baselines on regression. In leave-one-out tests for unseen cell lines and drugs, drGT achieves AUROCs of 0.706 and 0.844, and \(R^2\) values of 0.692 and 0.022, the only model yielding positive \(R^2\) for unseen drugs. In zero-shot prediction, drGT achieves an AUROC of 0.786 and a regression \(R^2\) of 0.334, both representing the highest scores among all models. For interpretability, AC-derived drug-gene links recover known biology: among 976 drugs with known DTIs, 36.9% of predicted links match established DTIs, and 63.7% are supported by either PubMed abstracts or a structure-based predictive model. Enrichment analyses of AC-prioritized genes reveal drug-perturbed biological processes, providing pathway-level explanations.

Conclusions

drGT advances predictive generalization and mechanism-centered interpretability, offering state-of-the-art regression accuracy and literature-supported biological hypotheses that demonstrate the use of graph learning from heterogeneous input data for biological discovery. Code: https://github.com/sciluna/drGT.