Network-based machine-learning to predict drug efficacy in cancer patients
Abstract
Cancer patient classification using predictive biomarkers for anti-cancer drug and immunotherapy responses is essential for improving therapeutic outcomes. However, current machine-learning-based predictions of drug response often fail to identify robust translational biomarkers from preclinical models. Furthermore, immune checkpoint inhibitors (ICIs) have improved the survival of cancer patients over the past several years. However, the minority of patients respond to ICI treatment (~30% in solid tumors), and current ICI-response-associated biomarkers often fail to predict the ICI treatment response. We have developed a network-based machine-learning framework to predict drug efficacy and to identify ICI treatment biomarkers in cancer patients. The biomarkers identified by our approach accurately predict the drug responses of 114 colorectal cancer patients treated with 5-fluorouracil and 77 bladder cancer patients treated with cisplatin. Moreover, network-based predictions accurately predict ICI treatment responses in three different cancer types—melanoma, gastric cancer, and bladder cancer. Compared with other conventional biomarkers, our network-based predictions showed improved performance in response predictions for cancer therapies including chemo and immunotherapy.
Room 307, Seoul National University Medical School, 103, Daehak-ro, Jongno-gu, Seoul, Republic of Korea
Phone: (+82)2-393-8328 E-mail : admin@khupo.org Homepage : http://www.khupo.org
Official Secretariat: The Plan B
Room B10, 55, APEC-ro, Haeundae-gu, Busan, Republic of Korea
FAX: +82-51-745-8407 Phone: (+82)2-393-8328 Homepage : https://www.planbgroup.org/