DRPreter: Interpretable Anticancer Drug Response Prediction Using Knowledge-Guided Graph Neural Networks and Transformer

Abstract

Some of the recent studies on drug sensitivity prediction have applied graph neural networks to leverage prior knowledge on the drug structure or gene network, and other studies have focused on the interpretability of the model to delineate the mechanism governing the drug response. However, it is crucial to make a prediction model that is both knowledge-guided and interpretable, so that the prediction accuracy is improved and practical use of the model can be enhanced. We propose an interpretable model called DRPreter (drug response predictor and interpreter) that predicts the anticancer drug response. DRPreter learns cell line and drug information with graph neural networks; the cell-line graph is further divided into multiple subgraphs with domain knowledge on biological pathways. A type-aware transformer in DRPreter helps detect relationships between pathways and a drug, highlighting important pathways that are involved in the drug response. Extensive experiments on the GDSC (Genomics of Drug Sensitivity and Cancer) dataset demonstrate that the proposed method outperforms state-of-the-art graph-based models for drug response prediction. In addition, DRPreter detected putative key genes and pathways for specific drug–cell-line pairs with supporting evidence in the literature, implying that our model can help interpret the mechanism of action of the drug.

Attention is all you need: utilizing attention in AI-enabled drug discovery

“…Moreover, the Transformer can be trained as a generative model for de novo drug design, learning chemical space distributions and generating promising new molecules [ 64 , 66 ]. Its superior interpretability, through attention weights, allows researchers to more transparently understand the decision-making process, identifying key molecular structures or groups [ 67 ].…”

“…Both models demonstrate superior effectiveness in predicting DRs compared with existing methods, underscoring their potential value in precision medicine. Another strategy named DRPreter stands out as an interpretable drug-response prediction model that merges biological and chemical-domain knowledge with deep learning technologies [ 67 ]. By integrating cancer-related pathways and cell line networks, it provides detailed representations and insights into drug mechanisms.…”

Optimal fusion of genotype and drug embeddings in predicting cancer drug response

“…Recently, transformers have been proven to be incredibly powerful in a variety of different fields including natural language processing [ 13 ], computer vision [ 14 ], and even cancer drug response prediction. For instance, DRPreter[ 15 ] employs graph neural networks and a type-aware transformer to predict anticancer drug response, while DeepTTA [ 16 ] leverages two autoencoders to project drug and cell line features and then predict the sensitivity of the cell lines to drugs. DEERS [ 17 ] uses autoencoders and a feed-forward network to predict cell line sensitivity to drugs.…”

TransCDR: a deep learning model for enhancing the generalizability of drug activity prediction through transfer learning and multimodal data fusion

“…A thorough comparison of the state-of-the-art (SOTA) models demonstrated that GraphDRP and DeepCDR outperformed traditional machine learning methods (e.g., ENet and random forest) and 3 deep learning methods (i.e., CDRscan, tCNN and MOLI) [16]. Additionally, models such as TGSA [17] and DRPreter [18] were proposed to make better use of prior domain knowledge (e.g., protein-protein interaction). They applied GNN to extract cell line features from gene networks.…”