Deep learning and multi-omics approach to predict drug responses in cancer

Abstract

Background Cancers are genetically heterogeneous, so anticancer drugs show varying degrees of effectiveness on patients due to their differing genetic profiles. Knowing patient’s responses to numerous cancer drugs are needed for personalized treatment for cancer. By using molecular profiles of cancer cell lines available from Cancer Cell Line Encyclopedia (CCLE) and anticancer drug responses available in the Genomics of Drug Sensitivity in Cancer (GDSC), we will build computational models to predict anticancer drug responses from molecular features. Results We propose a novel deep neural network model that integrates multi-omics data available as gene expressions, copy number variations, gene mutations, reverse phase protein array expressions, and metabolomics expressions, in order to predict cellular responses to known anti-cancer drugs. We employ a novel graph embedding layer that incorporates interactome data as prior information for prediction. Moreover, we propose a novel attention layer that effectively combines different omics features, taking their interactions into account. The network outperformed feedforward neural networks and reported 0.90 for $$R^2$$ R 2 values for prediction of drug responses from cancer cell lines data available in CCLE and GDSC. Conclusion The outstanding results of our experiments demonstrate that the proposed method is capable of capturing the interactions of genes and proteins, and integrating multi-omics features effectively. Furthermore, both the results of ablation studies and the investigations of the attention layer imply that gene mutation has a greater influence on the prediction of drug responses than other omics data types. Therefore, we conclude that our approach can not only predict the anti-cancer drug response precisely but also provides insights into reaction mechanisms of cancer cell lines and drugs as well.

Improving drug response prediction via integrating gene relationships with deep learning

“…In the rapidly evolving landscape of clinical practice, the frequent emergence of new cell lines and drugs presents a formidable challenge in therapeutic decision-making, particularly due to the absence of extant drug response data [ 49 , 50 ]. The capability to predict drug response for unseen cell lines and new pharmaceutical compounds could serve as a pivotal aid in optimizing therapy [ 51 , 52 ]. To assess the generalizability of our model in such scenarios, we conducted experiments involving cell lines and drugs that were previously unencountered by the model using the GDSC dataset.…”

Systematic omics analysis identifies CCR6 as a therapeutic target to overcome cancer resistance to EGFR inhibitors

“…Nevertheless, recent advances in computational methods leveraging large-scale omics data from CCLs have facilitated a deeper understanding of the diverse biological characteristics of cancers, as well as the prediction of drug responses. 22 , 61 , 62 However, despite the numerous reports of in silico predictions that establish novel associations between molecular targets and drug responses, subsequent in vitro or in vivo biochemical analysis to validate these predictive outcomes has been lacking except for a few studies. 63 …”

An Innovative Multi-Omics Model Integrating Latent Alignment and Attention Mechanism for Drug Response Prediction

“…We compared the performance of our model with that of other studies [7,12] that also utilized multiomics data for predicting drug response. To facilitate an unbiased comparison, we utilized consistent datasets and preprocessing methods while implementing the model architectures as detailed in the referenced studies.…”

“…Besides, to capture the correlation between different types of omics data, some studies have proposed using an attention mechanism. For example, Wang et al [12] proposed a model that integrates multiomics data to increase the richness of the input. An attention layer is introduced to capture the inter-omics correlation and assign importance weights to different features.…”