Machine Learning Models Identify Inhibitors of New Delhi Metallo-β-lactamase

  • J Chem Inf Model. 2024 May 10. doi: 10.1021/acs.jcim.3c02015.
Zishuo Cheng  1 ,  Mahesh Aitha  2 ,  Caitlyn A Thomas  1 ,  Aidan Sturgill  1 ,  Mitch Fairweather  1 ,  Amy Hu  1 ,  Christopher R Bethel  3 ,  Dann D Rivera  4 ,  Patricia Dranchak  2 ,  Pei W Thomas  4 ,  Han Li  1 ,  Qi Feng  1 ,  Kaicheng Tao  1 ,  Minshuai Song  1 ,  Na Sun  1 ,  Shuo Wang  1 ,  Surendra Bikram Silwal  1 ,  Richard C Page  1 ,  Walt Fast  4 ,  Robert A Bonomo  3  5  6  7 ,  Maria Weese  1 ,  Waldyn Martinez  1 ,  James Inglese  2  8 ,  Michael W Crowder  1
Affiliations
  • 1. Department of Chemistry and Biochemistry, Miami University, Oxford ,Ohio 45056, United States.
  • 2. Division of Preclinical Innovation, National Center for Advancing Translational Sciences, National Institutes of Health, Rockville ,Maryland 20850, United States.
  • 3. Research Service, Louis Stokes Cleveland Department of Veterans Affairs Medical Center, Cleveland ,Ohio 44106, United States.
  • 4. Division of Chemical Biology and Medicinal Chemistry, College of Pharmacy, University of Texas, Austin ,Texas 78712, United States.
  • 5. Departments of Medicine, Biochemistry, Molecular Biology and Microbiology, Pharmacology, and Proteomics and Bioinformatics, Case Western Reserve University School of Medicine, Cleveland ,Ohio 44106, United States.
  • 6. Clinician Scientist Investigator, Louis Stokes Cleveland Department of Veterans Affairs Medical Center, Cleveland ,Ohio 44106, United States.
  • 7. CWRU-Cleveland VAMC Center for Antimicrobial Resistance and Epidemiology (Case VA CARES) ,Cleveland ,Ohio 44106, United States.
  • 8. Metabolic Medicine Branch, National Human Genome Research Institute, National Institutes of Health, Bethesda ,Maryland 20817, United States.
PMID: 38727192 DOI: 10.1021/acs.jcim.3c02015
Abstract

The worldwide spread of the metallo-β-lactamases (MBL), especially New Delhi metallo-β-lactamase-1 (NDM-1), is threatening the efficacy of β-lactams, which are the most potent and prescribed class of Antibiotics in the clinic. Currently, FDA-approved MBL inhibitors are lacking in the clinic even though many strategies have been used in inhibitor development, including quantitative high-throughput screening (qHTS), fragment-based drug discovery (FBDD), and molecular docking. Herein, a machine learning-based prediction tool is described, which was generated using results from HTS of a large chemical library and previously published inhibition data. The prediction tool was then used for virtual screening of the NIH Genesis library, which was subsequently screened using qHTS. A novel MBL inhibitor was identified and shown to lower minimum inhibitory concentrations (MICs) of Meropenem for a panel of E. coli and K. pneumoniae clinical isolates expressing NDM-1. The mechanism of inhibition of this novel scaffold was probed utilizing equilibrium dialyses with metal analyses, native state electrospray ionization mass spectrometry, UV-vis spectrophotometry, and molecular docking. The uncovered inhibitor, compound 72922413, was shown to be 9-hydroxy-3-[(5-hydroxy-1-oxa-9-azaspiro[5.5]undec-9-yl)carbonyl]-4H-pyrido[1,2-a]pyrimidin-4-one.

Products