Virtual screening and repositioning of inconclusive molecules of beta-lactamase Bioassays—A data mining approach

• Published in: Computational biology and chemistry 2017-10, Vol.70, p.65-88
• Main Authors: Gad, Akshata, Manuel, Andrew Titus, K. R., Jinuraj, John, Lijo, R., Sajeev, V. G., Shanmuga Priya, U.C., Abdul Jaleel
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; beta-Lactamase Inhibitors - chemistry; beta-Lactamase Inhibitors - pharmacology; beta-Lactamases - analysis; beta-Lactamases - metabolism; Data Mining; Drug Evaluation, Preclinical; Drug Repositioning; Enzyme Assays; Inconclusive molecules; Mycobacterium tuberculosis; Mycobacterium tuberculosis - drug effects; Mycobacterium tuberculosis - metabolism; PubChem bioassays; Self organizing maps
• ISSN: 1476-9271; 1476-928X
• DOI: 10.1016/j.compbiolchem.2017.07.005

[Display omitted] •Alternate virtual screening method adopted for screening out of inconclusive bioassay molecule.•Artificial Neural Network based innovative ligand based screening method adopted for prioritization.•Inconclusive molecules are repositioned for downstream drug discovery activities.•SOM maps adopted for partitioning the Inconclusive data into active or inactive datasets. This study focuses on the best possible way forward in utilizing inconclusive molecules of PubChem bioassays AID 1332, AID 434987 and AID 434955, which are related to beta-lactamase inhibitors of Mycobacterium tuberculosis (Mtb). The inadequacy in the experimental methods that were observed during the invitro screening resulted in an inconclusive dataset. This could be due to certain moieties present within the molecules. In order to reconsider such molecules, insilico methods can be suggested in place of invitro methods For instance, datamining and medicinal chemistry methods: have been adopted to prioritise the inconclusive dataset into active or inactive molecules. These include the Random Forest algorithm for dataminning, Lilly MedChem rules for virtually screening out the promiscuity, and Self Organizing Maps (SOM) for clustering the active molecules and enlisting them for repositioning through the use of artificial neural networks. These repositioned molecules could then be prioritized for downstream drug discovery analysis.