Automated identification of small drug molecules for Hepatitis C virus through a novel programmatic tool and extensive Molecular Dynamics studies of select drug candidates

Abstract

<jats:title>Abstract</jats:title><jats:p>We report a novel python based programmatic tool that automates the dry lab drug discovery workflow for Hepatitis C virus. Firstly, the python program is written to automate the process of data mining PubChem database to collect data required to perform a machine learning based AutoQSAR algorithm through which drug leads for Hepatitis C virus is generated. The workflow of the machine learning based AutoQSAR involves feature learning and descriptor selection, QSAR modelling, validation and prediction. The drug leads generated by the program are required to satisfy the Lipinski’s drug likeness criteria. 50 of the drug leads generated by the program are fed as programmatic inputs to an In Silico modelling package by the program for fast virtual screening and computer modelling of the interaction of the compounds generated as drug leads and the drug target, a viral Helicase of Hepatitis C. The results are stored automatically in the working folder of the user by the program. The program also generates protein-ligand interaction profiling and stores the visualized images in the working folder of the user. Select protein-ligand complexes associated with structurally diverse ligands having lowest binding energy were selected for extensive molecular dynamics simulation studies and subsequently for molecular mechanics generalized-born surface area (MMGBSA) with pairwise decomposition calculations. The molecular mechanics studies predict In Silico that the compounds generated by the program inhibit the viral helicase of Hepatitis C and prevent the replication of the virus. Thus our programmatic tool ushers in the new age of automatic ease in drug identification for Hepatitis C virus through a programmatic tool that completely automates the dry lab drug discovery workflow. The program is hosted, maintained and supported at the GitHub repository link given below <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/bengeof/Automated-drug-identification-programmatic-tool-for-Hepatitis-C-virus">https://github.com/bengeof/Automated-drug-identification-programmatic-tool-for-Hepatitis-C-virus</jats:ext-link></jats:p>

QPowered Compound2DeNovoDrugPropMax –A Novel Programmatic Tool Incorporating Deep Learning and In Silico Methods for Automated In Silico Bio- Activity Discovery for any Compound of Interest

“…networks have also been carried out using Deep Learning techniques by different groups [19,20]. The previous works of our research group has involved incorporating machine/deep learning techniques for automation in screening PubChem compound library and identifying the best small drug molecules for a particular drug target [21][22][23]. In keeping with our research focus, the present work presents a complimentary approach to drug screening, wherein, given a particular PubChem compound ID for a particular compound, the developed tool predicts the most likely pharmaceutical activity of the compound and followingly performs an automated…”

Compound2DeNovoDrugPropMax –a novel programmatic tool incorporating deep learning and in silico methods for automated bio-activity discovery for any compound of interest

“…Similarly advances in understanding differential gene expression from gene expression networks have also been carried out using Deep Learning techniques by different groups [19,20]. The previous works of our research group has involved incorporating machine/deep learning techniques for automation in screening PubChem compound library and identifying the best small drug molecules for a particular drug target [21][22][23]. In keeping with our research focus, the present work presents a complimentary approach to drug screening, wherein, given a particular PubChem compound ID for a particular compound, the developed tool predicts the most likely pharmaceutical activity of the compound and followingly performs an automated In Silico modelling to uncover the molecular details of its pharmaceutical activity.…”

QPowered Compound2DeNovoDrugPropMax –A Novel Programmatic Tool Incorporating Deep Learning and In Silico Methods for Automated In Silico Bio- Activity Discovery for any Compound of Interest

“…Similarly advances in understanding differential gene expression from gene expression networks have also been carried out using Deep Learning techniques by different groups [19,20]. The previous works of our research group have involved incorporating machine/deep learning techniques for automation in screening PubChem compound library and identifying the best small drug molecules for a particular drug target [21][22][23]. In keeping with our research focus, the present work presents a complementary approach to drug screening, wherein, given a particular PubChem compound ID for a particular compound, the developed tool predicts the most likely pharmaceutical activity of the compound and followingly performs an automated In Silico modelling to uncover the molecular details of its pharmaceutical activity.…”