Biologically Interpretable Deep Learning To Predict Response to Immunotherapy In Advanced Melanoma Using Mutations and Copy Number Variations

Abstract

Only 30-40% of advanced melanoma patients respond effectively to immunotherapy in clinical practice, so it is necessary to accurately identify the response of patients to immunotherapy pre-clinically. Here, we develop KP-NET, a deep learning model that is sparse on KEGG pathways, and combine it with transferlearning to accurately predict the response of advanced melanomas to immunotherapy using KEGG pathway-level information enriched from gene mutation and copy number variation data. The KP-NET demonstrates best performance with AUROC of 0.886 on testing set and 0.803 on an unseen evaluation set when predicting responders (CR/PR/SD with PFS ≥ 6 mo) versus non-responders (PD/SD with PFS <6 mo) in anti-CTLA-4 treated melanoma patients. The model also achieves an AUROC of 0.917 and 0.833 in predicting CR/PR versus PD, respectively. Meanwhile, the AUROC is 0.913 when predicting responders versus non-responders in anti-PD-1/PD-L1 melanomas. Moreover, the KP-NET reveals some genes and pathways associated with response to anti-CTLA-4 treatment, such as genes PIK3CA, AOX1 and CBLB, and ErbB signaling pathway, T cell receptor signaling pathway, et al. In conclusion, the KP-NET can accurately predict the response of melanomas to immunotherapy and screen related biomarkers preclinically, which can contribute to precision medicine of melanoma.