Year: 2020
Type: article
Abstract: OBJECTIVE: Drug combination screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that the accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues are more understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied tissues as a way of overcoming data scarcity problems. MATERIALS AND METHODS: We collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines. We developed a drug synergy prediction model based on multitask deep neural networks to integrate multimodal input and multiple output. We also utilized transfer learning from data-rich tissues to data-poor tissues. RESULTS: We showed improved accuracy in predicting synergy in both data-rich tissues and understudied tissues. In data-rich tissue, the prediction model accuracy was 0.9577 AUROC for binarized classification task and 174.3 mean squared error for regression task. We observed that an adequate transfer learning strategy significantly increases accuracy in the understudied tissues. CONCLUSIONS: Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help to prioritize future in-vitro experiments. Code is available at https://github.com/yejinjkim/synergy-transfer.
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Center for Clinical and Translational Sciences (CCTS), Privacy-preserving methods and tools for handling missing data in distributed health data networks, G1427963301, Open Health Natural Language Processing Collaboratory, Finding combinatorial drug repositioning therapy for Alzheimer's disease and related dementias, SHARE: Statistical Health Information Release with Differential Privacy, G6799826303
OpenAlex ID: W3092034553