{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T21:47:43Z","timestamp":1776548863861,"version":"3.51.2"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1010613","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000}}],"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"crossref","award":["No 169121"],"award-info":[{"award-number":["No 169121"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000082","name":"Cystic Fibrosis Canada","doi-asserted-by":"publisher","award":["No 321858"],"award-info":[{"award-number":["No 321858"]}],"id":[{"id":"10.13039\/501100000082","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000897","name":"Cystic Fibrosis Foundation","doi-asserted-by":"crossref","award":["Pilot and Feasibility Grant No CARDON1810"],"award-info":[{"award-number":["Pilot and Feasibility Grant No CARDON1810"]}],"id":[{"id":"10.13039\/100000897","id-type":"DOI","asserted-by":"crossref"}]},{"name":"University of Manitoba Graduate Fellowship"},{"DOI":"10.13039\/501100000023","name":"Government of Canada","doi-asserted-by":"publisher","award":["Vanier Canada Graduate Scholarship"],"award-info":[{"award-number":["Vanier Canada Graduate Scholarship"]}],"id":[{"id":"10.13039\/501100000023","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010318","name":"University of Manitoba","doi-asserted-by":"publisher","award":["GETS program"],"award-info":[{"award-number":["GETS program"]}],"id":[{"id":"10.13039\/100010318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Screening for novel antibacterial compounds in small molecule libraries has a low success rate. We applied machine learning (ML)-based virtual screening for antibacterial activity and evaluated its predictive power by experimental validation. We first binarized 29,537 compounds according to their growth inhibitory activity (hit rate 0.87%) against the antibiotic-resistant bacterium <jats:italic>Burkholderia cenocepacia<\/jats:italic> and described their molecular features with a directed-message passing neural network (D-MPNN). Then, we used the data to train an ML model that achieved a receiver operating characteristic (ROC) score of 0.823 on the test set. Finally, we predicted antibacterial activity in virtual libraries corresponding to 1,614 compounds from the Food and Drug Administration (FDA)-approved list and 224,205 natural products. Hit rates of 26% and 12%, respectively, were obtained when we tested the top-ranked predicted compounds for growth inhibitory activity against <jats:italic>B<\/jats:italic>. <jats:italic>cenocepacia<\/jats:italic>, which represents at least a 14-fold increase from the previous hit rate. In addition, more than 51% of the predicted antibacterial natural compounds inhibited ESKAPE pathogens showing that predictions expand beyond the organism-specific dataset to a broad range of bacteria. Overall, the developed ML approach can be used for compound prioritization before screening, increasing the typical hit rate of drug discovery.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1010613","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T18:02:22Z","timestamp":1665684142000},"page":"e1010613","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":37,"title":["A machine learning model trained on a high-throughput antibacterial screen increases the hit rate of drug discovery"],"prefix":"10.1371","volume":"18","author":[{"given":"A. S. M. Zisanur","family":"Rahman","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2078-9737","authenticated-orcid":true,"given":"Chengyou","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Hunter","family":"Sturm","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0782-012X","authenticated-orcid":true,"given":"Andrew M.","family":"Hogan","sequence":"additional","affiliation":[]},{"given":"Rebecca","family":"Davis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9546-2245","authenticated-orcid":true,"given":"Pingzhao","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0629-8886","authenticated-orcid":true,"given":"Silvia T.","family":"Cardona","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"pcbi.1010613.ref001","volume-title":"Antibiotic Resistance Threats in the United States.","author":"CDC","year":"2019"},{"key":"pcbi.1010613.ref002","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1177\/0098858816658277","article-title":"A New Product Development Partnership Model for Antibiotic Resistance","volume":"42","author":"JK Billington","year":"2016","journal-title":"Am J Law Med"},{"key":"pcbi.1010613.ref003","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1038\/nature17042","article-title":"Antibacterial drug discovery in the resistance era","volume":"529","author":"ED Brown","year":"2016","journal-title":"Nature"},{"key":"pcbi.1010613.ref004","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1038\/nrd2201","article-title":"Drugs for bad bugs: confronting the challenges of antibacterial discovery","volume":"6","author":"DJ Payne","year":"2007","journal-title":"Nat Rev Discov."},{"key":"pcbi.1010613.ref005","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1021\/acsinfecdis.5b00097","article-title":"Permeability Barrier of Gram-Negative Cell Envelopes and Approaches To Bypass It","volume":"1","author":"HI Zgurskaya","year":"2015","journal-title":"ACS Infect Dis"},{"key":"pcbi.1010613.ref006","doi-asserted-by":"crossref","first-page":"878","DOI":"10.15252\/msb.20156651","article-title":"Deep learning for computational biology","volume":"12","author":"C Angermueller","year":"2016","journal-title":"Mol Syst Biol"},{"key":"pcbi.1010613.ref007","doi-asserted-by":"crossref","first-page":"214","DOI":"10.3389\/fgene.2019.00214","article-title":"Recent Advances of Deep Learning in Bioinformatics and Computational Biology","volume":"10","author":"B Tang","year":"2019","journal-title":"Front Genet"},{"key":"pcbi.1010613.ref008","doi-asserted-by":"crossref","first-page":"dev188474","DOI":"10.1242\/dev.188474","article-title":"What machine learning can do for developmental biology","volume":"148","author":"P. Villoutreix","year":"2021","journal-title":"Development"},{"key":"pcbi.1010613.ref009","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1016\/j.tips.2019.06.004","article-title":"Advancing Drug Discovery via Artificial Intelligence","volume":"40","author":"HCS Chan","year":"2019","journal-title":"Trends Pharmacol Sci"},{"key":"pcbi.1010613.ref010","article-title":"Graph Neural Networks: A Review of Methods and Applications","author":"J Zhou","year":"2019","journal-title":"ArXiv181208434 Cs Stat"},{"key":"pcbi.1010613.ref011","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing Learned Molecular Representations for Property Prediction","volume":"59","author":"K Yang","year":"2019","journal-title":"J Chem Inf Model."},{"key":"pcbi.1010613.ref012","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1038\/s42003-021-02586-0","article-title":"Accelerating antibiotic discovery through artificial intelligence","volume":"4","author":"MCR Melo","year":"2021","journal-title":"Commun Biol"},{"key":"pcbi.1010613.ref013","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A Deep Learning Approach to Antibiotic Discovery","volume":"180","author":"JM Stokes","year":"2020","journal-title":"Cell"},{"key":"pcbi.1010613.ref014","doi-asserted-by":"crossref","first-page":"e0128587","DOI":"10.1371\/journal.pone.0128587","article-title":"A Pipeline for Screening Small Molecules with Growth Inhibitory Activity against Burkholderia cenocepacia","volume":"10","author":"C Selin","year":"2015","journal-title":"PLOS ONE"},{"key":"pcbi.1010613.ref015","doi-asserted-by":"crossref","first-page":"4088","DOI":"10.1128\/IAI.00212-10","article-title":"A decade of Burkholderia cenocepacia virulence determinant research","volume":"78","author":"SA Loutet","year":"2010","journal-title":"Infect Immun"},{"key":"pcbi.1010613.ref016","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1086\/533452","article-title":"Federal funding for the study of antimicrobial resistance in nosocomial pathogens: no ESKAPE","volume":"197","author":"LB Rice","year":"2008","journal-title":"J Infect Dis"},{"key":"pcbi.1010613.ref017","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1177\/1087057103258285","article-title":"Improved statistical methods for hit selection in high-throughput screening","volume":"8","author":"C Brideau","year":"2003","journal-title":"J Biomol Screen"},{"key":"pcbi.1010613.ref018","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the Human Out of the Loop: A Review of Bayesian Optimization","volume":"104","author":"B Shahriari","year":"2016","journal-title":"Proc IEEE"},{"key":"pcbi.1010613.ref019","first-page":"1","volume-title":"Ensemble Methods in Machine Learning. Multiple Classifier Systems.","author":"TG Dietterich","year":"2000"},{"key":"pcbi.1010613.ref020","doi-asserted-by":"crossref","first-page":"6560","DOI":"10.1021\/jm301916b","article-title":"Hit Identification and Optimization in Virtual Screening: Practical Recommendations Based Upon a Critical Literature Analysis","volume":"56","author":"T Zhu","year":"2013","journal-title":"J Med Chem"},{"key":"pcbi.1010613.ref021","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1016\/S0092-8674(01)00286-0","article-title":"Structural Mechanism for Rifampicin Inhibition of Bacterial RNA Polymerase","volume":"104","author":"EA Campbell","year":"2001","journal-title":"Cell"},{"key":"pcbi.1010613.ref022","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1016\/0005-2787(67)90147-5","article-title":"The specific inhibition of the DNA-directed RNA synthesis by rifamycin","volume":"145","author":"G Hartmann","year":"1967","journal-title":"Biochim Biophys Acta"},{"key":"pcbi.1010613.ref023","doi-asserted-by":"crossref","first-page":"465","DOI":"10.3109\/1040841X.2013.866073","article-title":"Genomic tools to profile antibiotic mode of action","volume":"4","author":"ST Cardona","year":"2015","journal-title":"Crit Rev Microbiol"},{"key":"pcbi.1010613.ref024","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1016\/j.cell.2013.02.022","article-title":"Repurposing CRISPR as an RNA-guided platform for sequence-specific control of gene expression","volume":"152","author":"LS Qi","year":"2013","journal-title":"Cell"},{"key":"pcbi.1010613.ref025","doi-asserted-by":"crossref","first-page":"2372","DOI":"10.1021\/acssynbio.9b00232","article-title":"A broad-host-range CRISPRi toolkit for silencing gene expression in Burkholderia","volume":"8","author":"AM Hogan","year":"2019","journal-title":"ACS Synth Biol"},{"key":"pcbi.1010613.ref026","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1002\/bies.950180810","article-title":"Molecular mechanisms of drug inhibition of DNA gyrase","volume":"18","author":"RJ Lewis","year":"1996","journal-title":"BioEssays News Rev Mol Cell Dev Biol"},{"key":"pcbi.1010613.ref027","first-page":"181","article-title":"Colistin, meropenem and rifampin in a combination therapy for multi-drug-resistant Acinetobacter baumannii multifocal infection","volume":"73","author":"G Biancofiore","year":"2007","journal-title":"A case report. Minerva Anestesiol."},{"key":"pcbi.1010613.ref028","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1093\/jac\/dkt437","article-title":"Successful treatment of post-neurosurgical multidrug-resistant Pseudomonas aeruginosa meningo-encephalitis with combination therapy of colistin, rifampicin and doripenem","volume":"69","author":"P Morelli","year":"2014","journal-title":"J Antimicrob Chemother"},{"key":"pcbi.1010613.ref029","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.ijantimicag.2010.10.031","article-title":"Activity of tigecycline alone and in combination with colistin and meropenem against Klebsiella pneumoniae carbapenemase (KPC)-producing Enterobacteriaceae strains by time-kill assay","volume":"37","author":"S Pournaras","year":"2011","journal-title":"Int J Antimicrob Agents"},{"key":"pcbi.1010613.ref030","doi-asserted-by":"crossref","first-page":"2732","DOI":"10.1128\/AAC.01768-09","article-title":"In vitro double and triple bactericidal activities of doripenem, polymyxin B, and rifampin against multidrug-resistant Acinetobacter baumannii, Pseudomonas aeruginosa, Klebsiella pneumoniae, and Escherichia coli","volume":"54","author":"C Urban","year":"2010","journal-title":"Antimicrob Agents Chemother"},{"key":"pcbi.1010613.ref031","doi-asserted-by":"crossref","first-page":"W488","DOI":"10.1093\/nar\/gkaa216","article-title":"SynergyFinder 2.0: visual analytics of multi-drug combination synergies","volume":"48","author":"A Ianevski","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1010613.ref032","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"SM McKinney","year":"2020","journal-title":"Nature"},{"key":"pcbi.1010613.ref033","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/s41591-019-0724-8","article-title":"Prediction of gestational diabetes based on nationwide electronic health records","volume":"26","author":"NS Artzi","year":"2020","journal-title":"Nat Med"},{"key":"pcbi.1010613.ref034","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.inffus.2018.09.012","article-title":"Machine learning for integrating data in biology and medicine: Principles, practice, and opportunities","volume":"50","author":"M Zitnik","year":"2019","journal-title":"Inf Fusion."},{"key":"pcbi.1010613.ref035","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1097\/QCO.0000000000000406","article-title":"Machine learning: novel bioinformatics approaches for combating antimicrobial resistance","volume":"30","author":"N Macesic","year":"2017","journal-title":"Curr Opin Infect Dis"},{"key":"pcbi.1010613.ref036","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1038\/nature22308","article-title":"Predictive compound accumulation rules yield a broad-spectrum antibiotic","volume":"545","author":"MF Richter","year":"2017","journal-title":"Nature"},{"key":"pcbi.1010613.ref037","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.drudis.2014.10.012","article-title":"Machine-learning approaches in drug discovery: methods and applications","volume":"20","author":"A. Lavecchia","year":"2015","journal-title":"Drug Discov Today"},{"key":"pcbi.1010613.ref038","author":"G. Landrum","year":"2006","journal-title":"RDKit: Open-source cheminformatics"},{"key":"pcbi.1010613.ref039","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1186\/s13321-019-0391-2","article-title":"Dataset\u2019s chemical diversity limits the generalizability of machine learning predictions","volume":"11","author":"M Glavatskikh","year":"2019","journal-title":"J Cheminformatics"},{"key":"pcbi.1010613.ref040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2015\/679109","article-title":"Antibacterial Mechanisms of Polymyxin and Bacterial Resistance","volume":"2015","author":"Z Yu","year":"2015","journal-title":"BioMed Res Int"},{"key":"pcbi.1010613.ref041","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1093\/jac\/12.2.119","article-title":"Mode of action of ceftazidime: affinity for the penicillin-binding proteins of Escherichia coli K12, Pseudomonas aeruginosa and Staphylococcus aureus","volume":"12","author":"MV Hayes","year":"1983","journal-title":"J Antimicrob Chemother"},{"key":"pcbi.1010613.ref042","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1093\/jac\/37.1.7","article-title":"Drug chirality: a consideration of the significance of the stereochemistry of antimicrobial agents","volume":"37","author":"Hutt AJ","year":"1996","journal-title":"J Antimicrob Chemother"},{"key":"pcbi.1010613.ref043","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1128\/AAC.40.8.1775","article-title":"Mechanism of differential activities of ofloxacin enantiomers","volume":"40","author":"I Morrissey","year":"1996","journal-title":"Antimicrob Agents Chemother"},{"key":"pcbi.1010613.ref044","author":"K Yang","year":"2019","journal-title":"chemprop: Message Passing Neural Networks for Molecule Property Prediction"},{"key":"pcbi.1010613.ref045","article-title":"Neural Message Passing for Quantum Chemistry.","author":"J Gilmer","year":"2017","journal-title":"ArXiv170401212 Cs."},{"key":"pcbi.1010613.ref046","doi-asserted-by":"crossref","first-page":"014008","DOI":"10.1088\/1749-4699\/8\/1\/014008","article-title":"Hyperopt: a Python library for model selection and hyperparameter optimization","volume":"8","author":"J Bergstra","year":"2015","journal-title":"Comput Sci Discov"},{"key":"pcbi.1010613.ref047","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine learning","volume":"9","author":"Z Wu","year":"2018","journal-title":"Chem Sci"},{"key":"pcbi.1010613.ref048","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","article-title":"Comparison of the predicted and observed secondary structure of T4 phage lysozyme","volume":"405","author":"BW Matthews","year":"1975","journal-title":"Biochim Biophys Acta"},{"key":"pcbi.1010613.ref049","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"D Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"pcbi.1010613.ref050","first-page":"3","author":"Lynne S Garcia","year":"2016","edition":"3"},{"key":"pcbi.1010613.ref051","article-title":"Synthesis and antibiotic activity of novel acylated phloroglucinol compounds against methicillin-resistant Staphylococcus aureus","author":"N Mittal","year":"2019","journal-title":"J Antibiot (Tokyo)"},{"key":"pcbi.1010613.ref052","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1111\/j.1744-7348.1939.tb06990.x","article-title":"THE TOXICITY OF POISONS APPLIED JOINTLY1","volume":"26","author":"CI Bliss","year":"1939","journal-title":"Ann Appl Biol"},{"key":"pcbi.1010613.ref053","first-page":"285","article-title":"The problem of synergism and antagonism of combined drugs","volume":"3","author":"S. Loewe","year":"1953","journal-title":"Arzneimittelforschung."},{"key":"pcbi.1010613.ref054","first-page":"93","article-title":"What is synergy?","volume":"41","author":"MC Berenbaum","year":"1989","journal-title":"Pharmacol Rev."},{"key":"pcbi.1010613.ref055","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.csbj.2015.09.001","article-title":"Searching for Drug Synergy in Complex Dose\u2013Response Landscapes Using an Interaction Potency Model","volume":"13","author":"B Yadav","year":"2015","journal-title":"Comput Struct Biotechnol J."},{"key":"pcbi.1010613.ref056","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.3390\/antibiotics10121443","article-title":"New Auranofin Analogs with Antibacterial Properties against Burkholderia Clinical Isolates","volume":"10","author":"D Maydaniuk","year":"2021","journal-title":"Antibiotics."},{"key":"pcbi.1010613.ref057","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/j.saa.2005.01.016","article-title":"Quantitative determinations of levofloxacin and rifampicin in pharmaceutical and urine samples using nuclear magnetic resonance spectroscopy","volume":"62","author":"AA Salem","year":"2005","journal-title":"Spectrochim Acta A Mol Biomol Spectrosc"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1010613","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T17:33:59Z","timestamp":1667324039000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010613"}},"subtitle":[],"editor":[{"given":"Tobias","family":"Bollenbach","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":57,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1010613","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1010613","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,13]]}}}