Prediction of QcrB Inhibition as a Measure of Antitubercular Activity with Machine Learning Protocols.

It has always been a challenge to develop interventional therapies for Mycobacterium tuberculosis. Over the years, several attempts at developing such therapies have hit a dead-end owing to rapid mutation rates of the tubercular bacilli and their ability to lay dormant for years. Recently, cytochrome bcc complex (QcrB) has shown some promise as a novel target against the tubercular bacilli, with Q203 being the first molecule acting on this target. In this paper, we report the deployment of several ML-based approaches to design molecules against QcrB. Machine learning (ML) models were developed based on a data set of 350 molecules using three different sets of molecular features, i.e., MACCS keys, ECFP6 fingerprints, and Mordred descriptors. Each feature set was trained on eight ML classifier algorithms and optimized to classify molecules accurately. The support vector machine-based classifier using the ECFP6 feature set was found to be the best classifier in this study. Further, screening of the known imidazopyridine amide inhibitors demonstrated that the model correctly classified the most potent molecules as actives, hence validating the model for future applications.

Discovery of new leads against Mycobacterium tuberculosis using scaffold hopping and shape based similarity.

BM212 [1,5-diaryl-2-methyl-3-(4-methylpiperazin-1-yl)-methyl-pyrrole] is a pyrrole derivative with strong inhibitory activity against drug resistant Mycobacterium tuberculosis and mycobacteria residing in macrophages. However, it was not pursued because of its poor pharmacokinetics and toxicity profile. Our goal was to design and synthesize new antimycobacterial BM212 analogs with lower toxicity and better pharmacokinetic profile. Using the scaffold hopping approach, three structurally diverse heterocycles - 2,3-disubstituted imidazopyridines, 2,3-disubstituted benzimidazoles and 1,2,4-trisubstituted imidazoles emerged as promising antitubercular agents. All compounds were synthesized through easy and convenient methods and their structures confirmed by IR, 1H NMR, 13C NMR and MS. In-vitro cytotoxicity studies on normal kidney monkey cell lines and HepG2 cell lines, as well as metabolic stability studies on rat liver microsomes for some of the most active compounds, established that these compounds have negligible cytotoxicity and are metabolically stable. Interestingly the benzimidazole compound (4a) is as potent as the parent molecule BM212 (MIC 2.3µg/ml vs 0.7-1.5µg/ml), but is devoid of the toxicity against HepG2 cell lines (IC50 203.10µM vs 7.8µM).

Quantifying ligand-receptor interactions for gorge-spanning acetylcholinesterase inhibitors for the treatment of Alzheimer's disease.

There is a need for continued development of acetylcholinesterase (AChE) inhibitors that could prolong the life of acetylcholine in the synaptic cleft and also prevent the aggregation of amyloid peptides associated with Alzheimer's disease. The lack of a 3D-QSAR model which specifically deconvulates the type of interactions and quantifies them in terms of energies has motivated us to report a CoRIA model vis-à-vis the standard 3D-QSAR methods, CoMFA and CoMSIA. The CoRIA model was found to be statistically superior to the CoMFA and CoMSIA models and it could efficiently extract key residues involved in ligand recognition and binding to AChE. These interactions were quantified to gauge the magnitude of their contribution to the biological activity. In order to validate the CoRIA model, a pharmacophore map was first constructed and then used to virtually screen public databases, from which novel scaffolds were cherry picked that were not present in the training set. The biological activities of these novel molecules were then predicted by the CoRIA, CoMFA, and CoMSIA models. The hits identified were purchased and their biological activities were measured by the Ellman's method for AChE inhibition. The predicted activities are in unison with the experimentally measured biological activities.