Transformer-based deep learning integrates multi-omic data with cancer pathways

Abstract

AbstractMulti-omic data analysis incorporating machine learning has the potential to significantly improve cancer diagnosis and prognosis. Traditional machine learning methods are usually limited to omic measurements, omitting existing domain knowledge such as the biological networks that link molecular entities in various omic data types. We develop a Transformer-based explainable deep learning model, DeePathNet, which integrates cancer-specific pathway information into multi-omic data analysis. Using a variety of big datasets, including ProCan-DepMapSanger, CCLE and TCGA, we show that DeePathNet outperforms traditional methods for the prediction of drug response and classification of cancer type and subtype. Combining biomedical knowledge and state-of-the-art deep learning methods, DeePathNet enables biomarker discovery at the pathway level, maximising the power of data-driven approaches to cancer research. DeePathNet is available on GitHub athttps://github.com/CMRI-ProCan/DeePathNet.