Identifying potential therapeutic molecules for hepatocellular carcinoma through machine learning-based drug repurposing

2024-9-06
Başer, Tuğçe
Hepatocellular carcinoma (HCC) is the most common primary liver cancer with a high mortality rate due to limited treatment options. Systemic drug treatments increase patient survival and often extend life by several months. The development of new small molecule chemotherapeutics is both time consuming and costly. Therefore, drug repurposing is being used as an effective strategy to identify and implement new treatment options for this mortal disease. The aim of this study is to identify potential drug candidates for the treatment of HCC through reuse of existing compounds using the machine learning tool MDeePred. The open target platform, UniProt, ChEMBL, and Expasy databases were used to create a dataset for MDeePred to predict drug- target interactions (DTIs). Enrichment analyses of DTIs were conducted, leading to the selection of 6 out of 380 DTIs identified by MDeePred for further analyses. The physicochemical properties, lipophilicity, water solubility, drug-likeness and medicinal chemistry properties of the drug candidates and approved drugs for advanced stage HCC (lenvatinib, regorafenib, and sorafenib) were meticulously and curated. The majority of drug candidates fell within conventional ranges in terms of drug properties and demonstrated target docking abilities. Our findings revealed the binding efficiency of selected drug compounds to identified targets associated with HCC. As a result, small molecules were identified that can be further evaluated experimentally as potential drug candidates in HCC. This study also highlights the importance of the MDeePred deep learning tool in in silico drug repurposing studies in cancer treatment.
Citation Formats
T. Başer, “Identifying potential therapeutic molecules for hepatocellular carcinoma through machine learning-based drug repurposing,” Ph.D. - Doctoral Program, Middle East Technical University, 2024.