Abstract 5235:In vitrovalidation of drug-target interactions revealedin silicoby Comprehensive Resource of Biomedical Relations with Network Representations and Deep Learning (CROssBAR) in HCC

Computational methods are more commonly employed for our understanding of cellular signaling mechanisms with the aim to develop cures for diseases including cancer. Identification of disease specific targeted drugs requires systems level analysis of cellular networks. Our research group developed a comprehensive resource, called CROssBAR, which connects various biological data sources in order to provide a well-connected resource with a focus on drug discovery and precision medicine. CROssBAR aims to predict and reveal novel drug-target interactions using deep learning algorithms. CROssBAR predictions were validated on hepatocellular carcinoma cells which is the 5th most prevalent and 3th deadliest cancer worldwide. We have selected 2 new small molecule kinase inhibitors Lenvatinib, Sunitinib along with Sorafenib and Regorafenib which are currently used in clinics. CROssBAR identifies novel and known gene targets for Lenvatinib, Sunitinib in comparison with Sorafenib and Regorafenib. Genes from SAPK/JNK and PI3K/Akt pathway that were not previously associated with hepatocellular carcinoma therapeutics were determined. All selected small molecules were bioactive on Huh7 and Mahlavu cells by SRB assay. Cell death was characterized by Annexin V which was due to G1/S cell cycle arrest. Further analysis of proteins involved in the SAPK/JNK, PI3K/Akt pathways and apoptotic markers such as PARP and Caspases were examined with immunoblotting upon treatment. As a result, cellular stress mechanisms activated PI3K/Akt and SAPK/JNK pathways which caused programmed cell death in HCC. With our deep learning approach, we were able to demonstrate a correlation between Lenvatinib and Sunitinib and their novel targets in HCC. Our validation results have illustrated that the comprehensive CROssBAR tool developed by our research group achieved in vitro significant predictions of new drugs and their targets against HCC that were not previously reported. Hence with this study we were able to demonstrate the use and validity of the CROssBAR tool along with new targets for primary liver cancer therapeutics. Citation Format: Esra Nalbat, Ahmet Sureyya Rifaioglu, Tunca Dogan, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay. In vitro validation of drug-target interactions revealed in silico by Comprehensive Resource of Biomedical Relations with Network Representations and Deep Learning (CROssBAR) in HCC [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 5235.