Scholarlink

Background <p>Accurate prediction of cancer drug responses is essential for advancing cancer treatment strategies and drug development. With the increasing availability of large-scale pharmacogenomic datasets, many deep learning models have been proposed to predict cancer drug responses. However, many existing models lack the capacity to offer critical biomedical insights, such as providing interpretability regarding the potential mechanism of action.</p> Methods <p>We propose DR.DEGMON (Drug Response prediction using Differentially Expressed Genes with Multi-layer perceptron integrating gene Ontology Network), a self-explainable deep neural network designed to predict the viability of pan-cancer cell lines in response to drug treatments by utilizing differentially expressed genes. DR.DEGMON leverages prior biological knowledge by incorporating Gene Ontology (GO) into the hierarchical structure of a multi-layer perceptron. The architecture of DR.DEGMON highlights key genes and GO terms that contribute to drug responses through layer-wise relevance propagation (LRP), suggesting potential biological pathways associated with specific drugs.</p> Results <p>DR.DEGMON achieved a Pearson correlation coefficient of 0.8568 for cell viability prediction, outperforming all baseline models. The model also showed robust generalization performance on external datasets, including GDSC, PRISM, and CCLE. In addition, we employed layer-wise relevance propagation (LRP) to obtain relevance scores for input genes and nodes representing GO terms.</p> Conclusion <p>DR.DEGMON shows high performance in predicting drug responses and provides interpretable results. The integration of GO and LRP enabled the model to suggest the underlying biological processes involved in drug responses, making it a valuable tool for predicting outcomes and discovering new biomedical knowledge in cancer pharmacogenomics. This approach offers both practical utility in drug development and a method for improving the understanding of cancer biology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DR.DEGMON: self-explainable deep neural network for drug-induced cell viability prediction incorporating differentially expressed genes and gene ontology

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月21日

查看全文
  • Wootaek Lim,
  • Jitae Kim,
  • Songhyeon Kim,
  • Hyunsu Bong,
  • Kwang-Su Park,
  • Minji Jeon

摘要

Background

Accurate prediction of cancer drug responses is essential for advancing cancer treatment strategies and drug development. With the increasing availability of large-scale pharmacogenomic datasets, many deep learning models have been proposed to predict cancer drug responses. However, many existing models lack the capacity to offer critical biomedical insights, such as providing interpretability regarding the potential mechanism of action.

Methods

We propose DR.DEGMON (Drug Response prediction using Differentially Expressed Genes with Multi-layer perceptron integrating gene Ontology Network), a self-explainable deep neural network designed to predict the viability of pan-cancer cell lines in response to drug treatments by utilizing differentially expressed genes. DR.DEGMON leverages prior biological knowledge by incorporating Gene Ontology (GO) into the hierarchical structure of a multi-layer perceptron. The architecture of DR.DEGMON highlights key genes and GO terms that contribute to drug responses through layer-wise relevance propagation (LRP), suggesting potential biological pathways associated with specific drugs.

Results

DR.DEGMON achieved a Pearson correlation coefficient of 0.8568 for cell viability prediction, outperforming all baseline models. The model also showed robust generalization performance on external datasets, including GDSC, PRISM, and CCLE. In addition, we employed layer-wise relevance propagation (LRP) to obtain relevance scores for input genes and nodes representing GO terms.

Conclusion

DR.DEGMON shows high performance in predicting drug responses and provides interpretable results. The integration of GO and LRP enabled the model to suggest the underlying biological processes involved in drug responses, making it a valuable tool for predicting outcomes and discovering new biomedical knowledge in cancer pharmacogenomics. This approach offers both practical utility in drug development and a method for improving the understanding of cancer biology.