Identification of Antituberculars with Favorable Potency and Pharmacokinetics through Structure-Based and Ligand-Based Modeling
Waradpande, V.; Meng, F.; Bozan, A.; Graff, D. E.; Fromer, J. C.; Mughal, K.; Mohideen, F. K.; Shivangi, F.; Paruchuri, S.; Johnston, M. L.; Sharma, P.; Crea, T. R.; Rudraraju, R.; George, A.; Folvar, C.; Nelson, A. M.; Neiditch, M. B.; Zimmerman, M. D.; Coley, C. W.; Freundlich, J. S.
Show abstract
Drug discovery is inherently challenged by a multiple criteria decision making problem. The arduous path from hit discovery through lead optimization and preclinical candidate selection necessitates the evolution of a plethora of molecular properties. In this study, we focus on the hit discovery phase while beginning to address multiple criteria critical to the development of novel therapeutics to treat Mycobacterium tuberculosis infection. We develop a hybrid structure- and ligand-based pipeline for nominating diverse inhibitors targeting the {beta}-ketoacyl synthase KasA by employing a Bayesian optimization-guided docking method and an ensemble model for compound nominations based on machine learning models for in vitro antibacterial efficacy, as characterized by minimum inhibitory concentration (MIC), and mouse pharmacokinetic (PK) plasma exposure. The application of our pipeline to the Enamine HTS library of 2.1M molecules resulted in the selection of 93 compounds, the experimental validation of which revealed exceptional PK (41%) and MIC (19%) success rates. Twelve compounds meet hit-like criteria in terms of MIC and PK profile and represent promising seeds for future drug discovery programs.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development of a chemical probe to enable characterization of the casein kinase 1γ subfamily 98%
- CRCM5484: A BET- BDII Selective Compound With Differential Anti-Leukemic Drug Modulation 97%
- benzothiazole scaffold as versatile nicotinamide mimic allowing nanomolar inhibition of different PARP enzymes 97%
Similar papers in this journal
Similar papers in this journal
- Shifting the selectivity of pyridopyrimidin-7(8H)-one inhibitors towards the salt-inducible kinase (SIK) subfamily 97%
- Automated design and optimization of multitarget schizophrenia drug candidates by deep learning 97%
- Synergistic Cytotoxicity Between Cold Atmospheric Plasma and Pyrazolopyrimidinones Against Glioblastoma Cells 96%
Similar papers in this journal
- Transfer learning enables discovery of sub-micromolar antibacterials for ESKAPE pathogens from ultra-large chemical spaces 95%
- Delineation of the Complete Reaction Cycle of a Natural Diels-Alderase 95%
- Exploiting the inherent promiscuity of the acyl transferase of the stambomycin polyketide synthase for the mutasynthesis of analogues 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.