Machine Learning-Based Drug Repositioning of Novel Janus Kinase 2 Inhibitors Utilizing Molecular Docking and Molecular Dynamic Simulation

• DOI: 10.1021/acs.jcim.3c01090
• Publication Date: 2023-10-31T18:57:40Z
• Authors: Muhammad Yasir; Jinyoung Park; Eun-Taek Han; Won Sun Park; Jin-Hee Han; Yong-Soo Kwon; Hee-Jae Lee; Wanjoo Chun
• Keywords: Docking (animal); Molecular descriptor; Drug repositioning; Cheminformatics; IC50

Machine learning algorithms have been increasingly applied in drug development due to their efficiency and effectiveness. learning-based repurposing can contribute the identification of novel therapeutic applications for drugs with other indications. The current study used a trained machine model screen vast chemical library new JAK2 inhibitors, biological activities which were reported. Reference comprising 1911 compounds, experimentally determined IC50 values. To generate input model, reference compounds subjected RDKit, cheminformatic toolkit, extract molecular descriptors. A Random Forest Regression from Scikit-learn was obtain predictive regression analyze each descriptor's role determining values data set. Then, comprised 1,576,903 predicted using generated model. Interestingly, some that exhibit high prediction reported possess JAK inhibition activity, indicates limitations confirm activity docking dynamics simulation carried out inhibitor compound, tofacitinib. binding affinity docked active region also analyzed by gmxMMPBSA approach. Furthermore, experimental validation confirmed results computational analysis. Results showed highly comparable outcomes concerning Conclusively, efficiently improve virtual screening development.