{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:05:56Z","timestamp":1780103156982,"version":"3.54.0"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2019,6,11]],"date-time":"2019-06-11T00:00:00Z","timestamp":1560211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Beijing Municipal Science & Technology Commission"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81861138053"],"award-info":[{"award-number":["81861138053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31870134"],"award-info":[{"award-number":["31870134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Streptococcus pneumoniae is the most common human respiratory pathogen, and \u03b2-lactam antibiotics have been employed to treat infections caused by S. pneumoniae for decades. \u03b2-lactam resistance is steadily increasing in pneumococci and is mainly associated with the alteration in penicillin-binding proteins (PBPs) that reduce binding affinity of antibiotics to PBPs. However, the high variability of PBPs in clinical isolates and their mosaic gene structure hamper the predication of resistance level according to the PBP gene sequences. In this study, we developed a systematic strategy for applying supervised machine learning to predict S. pneumoniae antimicrobial susceptibility to \u03b2-lactam antibiotics. We combined published PBP sequences with minimum inhibitory concentration (MIC) values as labelled data and the sequences from NCBI database without MIC values as unlabelled data to develop an approach, using only a fragment from pbp2x (750 bp) and a fragment from pbp2b (750 bp) to predicate the cefuroxime and amoxicillin resistance. We further validated the performance of the supervised learning model by constructing mutants containing the randomly selected pbps and testing more clinical strains isolated from Chinese hospital. In addition, we established the association between resistance phenotypes and serotypes and sequence type of S. pneumoniae using our approach, which facilitate the understanding of the worldwide epidemiology of S. pneumonia.<\/jats:p>","DOI":"10.1093\/bib\/bbz056","type":"journal-article","created":{"date-parts":[[2019,4,19]],"date-time":"2019-04-19T11:09:39Z","timestamp":1555672179000},"page":"1347-1355","source":"Crossref","is-referenced-by-count":12,"title":["Systematic analysis of supervised machine learning as an effective approach to predicate \u03b2-lactam resistance phenotype in Streptococcus pneumoniae"],"prefix":"10.1093","volume":"21","author":[{"given":"Chaodong","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"},{"name":"Singapore Centre for Environmental Life Sciences Engineering, Nanyang Technological University 60 Nanyang Drive, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjiao","family":"Ju","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"},{"name":"College of Life Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Tang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"},{"name":"College of Life Science, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Clinical Pharmacology, Peking University First Hospital, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqin","family":"Song","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailing","family":"Fang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Medicine, Southern University of Science and Technology, Shenzhen, Guangdong Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Feng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Microbial Resources, Institute of Microbiology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,6,11]]},"reference":[{"issue":"5","key":"2020080709264840000_ref1","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1056\/NEJMp0804651","article-title":"Antibiotic-resistant bugs in the 21st century\u2014a clinical super-challenge","volume":"360","author":"Arias","year":"2009","journal-title":"N Engl J Med"},{"key":"2020080709264840000_ref2","author":"Review on Antimicrobial Resistance (AMR Review)"},{"key":"2020080709264840000_ref3","author":"Review on Antimicrobial Resistance (AMR Review)"},{"issue":"410","key":"2020080709264840000_ref4","doi-asserted-by":"crossref","first-page":"eaal3693","DOI":"10.1126\/scitranslmed.aal3693","article-title":"Rapid pathogen-specific phenotypic antibiotic susceptibility testing using digital LAMP quantification in clinical samples","volume":"9","author":"Schoepp","year":"2017","journal-title":"Sci Transl Med"},{"issue":"29","key":"2020080709264840000_ref5","doi-asserted-by":"crossref","first-page":"E5787","DOI":"10.1073\/pnas.1703736114","article-title":"Rapid phenotypic antimicrobial susceptibility testing using nanoliter arrays","volume":"114","author":"Avesar","year":"2017","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"2020080709264840000_ref6","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1080\/14737159.2017.1283220","article-title":"Microbial genomics and antimicrobial susceptibility testing","volume":"17","author":"Dunne","year":"2017","journal-title":"Expert Rev Mol Diagn"},{"issue":"7","key":"2020080709264840000_ref7","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1101\/gr.089342.108","article-title":"Genome sequencing of linezolid-resistant Streptococcus pneumoniae mutants reveals novel mechanisms of resistance","volume":"19","author":"Feng","year":"2009","journal-title":"Genome Res"},{"issue":"8","key":"2020080709264840000_ref8","doi-asserted-by":"crossref","first-page":"1718","DOI":"10.1093\/jac\/dkt113","article-title":"Genomic analysis and reconstruction of cefotaxime resistance in Streptococcus pneumoniae","volume":"68","author":"Fani","year":"2013","journal-title":"J Antimicrob Chemother"},{"issue":"6","key":"2020080709264840000_ref9","doi-asserted-by":"crossref","first-page":"3529","DOI":"10.1128\/AAC.00429-15","article-title":"Commensal streptococci serve as a reservoir for beta-lactam resistance genes in Streptococcus pneumoniae","volume":"59","author":"Jensen","year":"2015","journal-title":"Antimicrob Agents Chemother"},{"issue":"6","key":"2020080709264840000_ref10","doi-asserted-by":"crossref","first-page":"2244","DOI":"10.1128\/AAC.48.6.2244-2250.2004","article-title":"Complete sequences of six penicillin-binding protein genes from 40 Streptococcus pneumoniae clinical isolates collected in Japan","volume":"48","author":"Sanbongi","year":"2004","journal-title":"Antimicrob Agents Chemother"},{"issue":"3","key":"2020080709264840000_ref11","doi-asserted-by":"crossref","first-page":"395","DOI":"10.2217\/fmb.12.2","article-title":"Molecular mechanisms of beta-lactam resistance in Streptococcus pneumoniae","volume":"7","author":"Hakenbeck","year":"2012","journal-title":"Future Microbiol"},{"issue":"1","key":"2020080709264840000_ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10408363.2018.1517144","article-title":"Bacterial imbalance and gut pathologies: association and contribution of E. coli in inflammatory bowel disease","volume":"56","author":"Khan","year":"2019","journal-title":"Crit Rev Clin Lab Sci"},{"issue":"3","key":"2020080709264840000_ref13","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1016\/j.critrevonc.2015.05.002","article-title":"Potential role of Escherichia coli DNA mismatch repair proteins in colon cancer","volume":"96","author":"Khan","year":"2015","journal-title":"Crit Rev Oncol Hematol"},{"issue":"7","key":"2020080709264840000_ref14","doi-asserted-by":"crossref","first-page":"e0181195","DOI":"10.1371\/journal.pone.0181195","article-title":"Independent component analysis (ICA) based-clustering of temporal RNA-seq data","volume":"12","author":"Nascimento","year":"2017","journal-title":"PLoS One"},{"key":"2020080709264840000_ref15","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1186\/1471-2156-9-71","article-title":"Application of two machine learning algorithms to genetic association studies in the presence of covariates","volume":"9","author":"Nonyane","year":"2008","journal-title":"BMC Genet"},{"issue":"1","key":"2020080709264840000_ref16","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/s41467-017-02465-5","article-title":"A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia","volume":"9","author":"Lee","year":"2018","journal-title":"Nat Commun"},{"issue":"5","key":"2020080709264840000_ref17","doi-asserted-by":"crossref","first-page":"994","DOI":"10.3390\/molecules23050994","article-title":"To decipher the mycoplasma hominis proteins targeting into the endoplasmic reticulum and their implications in prostate cancer etiology using next-generation sequencing data","volume":"23","author":"Zakariah","year":"2018","journal-title":"Molecules"},{"issue":"19","key":"2020080709264840000_ref18","doi-asserted-by":"crossref","first-page":"30830","DOI":"10.18632\/oncotarget.8306","article-title":"Prediction of mycoplasma hominis proteins targeting in mitochondria and cytoplasm of host cells and their implication in prostate cancer etiology","volume":"8","author":"Khan","year":"2017","journal-title":"Oncotarget"},{"issue":"1","key":"2020080709264840000_ref19","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1186\/s12864-016-2889-6","article-title":"Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons","volume":"17","author":"Drouin","year":"2016","journal-title":"BMC Genomics"},{"issue":"3","key":"2020080709264840000_ref20","doi-asserted-by":"crossref","first-page":"e00756-16","DOI":"10.1128\/mBio.00756-16","article-title":"Penicillin-binding protein Transpeptidase signatures for tracking and predicting beta-lactam resistance levels in Streptococcus pneumoniae","volume":"7","author":"Li","year":"2016","journal-title":"MBio"},{"issue":"1","key":"2020080709264840000_ref21","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1186\/s12864-017-4017-7","article-title":"Validation of beta-lactam minimum inhibitory concentration predictions for pneumococcal isolates with newly encountered penicillin binding protein (PBP) sequences","volume":"18","author":"Li","year":"2017","journal-title":"BMC Genomics"},{"issue":"2","key":"2020080709264840000_ref22","doi-asserted-by":"crossref","DOI":"10.1080\/10691898.2007.11889465","article-title":"Variability for categorical variables","volume":"15","author":"Kader","year":"2007","journal-title":"J Stat Educ"},{"key":"2020080709264840000_ref23","author":"Jones"},{"key":"2020080709264840000_ref24","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1111\/j.1467-6419.1996.tb00013.x","article-title":"Pseudo-R2 measures for some common limited dependent variable models","volume":"10","author":"Veall","year":"1996","journal-title":"J Econ Surv"},{"key":"2020080709264840000_ref25","volume-title":"Mathematical Methods of Statistics (PMS-9)","author":"Cram\u00e9r","year":"2016"},{"key":"2020080709264840000_ref26","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2020080709264840000_ref27","article-title":"Tensorflow: A system for large-scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi","year":"2016"},{"key":"2020080709264840000_ref28","article-title":"Understanding deep neural networks with rectified linear units,","author":"Arora","year":"2016"},{"issue":"3","key":"2020080709264840000_ref29","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1006\/jtbi.2001.2512","article-title":"Amino acid encoding schemes from protein structure alignments: multi-dimensional vectors to describe residue types","volume":"216","author":"Lin","year":"2002","journal-title":"J Theor Biol"},{"issue":"17","key":"2020080709264840000_ref30","doi-asserted-by":"crossref","first-page":"2461","DOI":"10.1111\/j.1365-2958.1992.tb01422.x","article-title":"Genetics of resistance to third-generation cephalosporins in clinical isolates of Streptococcus pneumoniae","volume":"6","author":"Munoz","year":"1992","journal-title":"Mol Microbiol"},{"key":"2020080709264840000_ref31","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/B978-0-12-385120-8.00015-2","article-title":"Enzymatic assembly of overlapping DNA fragments","volume":"498","author":"Gibson","year":"2011","journal-title":"Methods Enzymol"},{"issue":"19","key":"2020080709264840000_ref32","doi-asserted-by":"crossref","first-page":"5709","DOI":"10.1128\/JB.183.19.5709-5717.2001","article-title":"Genome of the bacterium Streptococcus pneumoniae strain R6","volume":"183","author":"Hoskins","year":"2001","journal-title":"J Bacteriol"},{"key":"2020080709264840000_ref33","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1186\/1471-2164-12-512","article-title":"Whole genome analysis of linezolid resistance in Streptococcus pneumoniae reveals resistance and compensatory mutations","volume":"12","author":"Billal","year":"2011","journal-title":"BMC Genomics"},{"key":"2020080709264840000_ref34","doi-asserted-by":"crossref","first-page":"2275","DOI":"10.1099\/mic.0.2008\/019265-0","article-title":"Shuttle expression plasmids for genetic studies in Streptococcus mutans","volume":"154","author":"Biswas","year":"2008","journal-title":"Microbiology"},{"key":"2020080709264840000_ref35","first-page":"856","volume-title":"Proceedings of the 20th international conference on machine learning (ICML-03)","author":"Yu","year":"2003"},{"issue":"22","key":"2020080709264840000_ref36","doi-asserted-by":"crossref","first-page":"3691","DOI":"10.1093\/bioinformatics\/btv421","article-title":"Roary: rapid large-scale prokaryote pan genome analysis","volume":"31","author":"Page","year":"2015","journal-title":"Bioinformatics"},{"issue":"3","key":"2020080709264840000_ref37","doi-asserted-by":"crossref","first-page":"e9490","DOI":"10.1371\/journal.pone.0009490","article-title":"FastTree 2\u2014approximately maximum-likelihood trees for large alignments","volume":"5","author":"Price","year":"2010","journal-title":"PLoS One"},{"issue":"12","key":"2020080709264840000_ref38","doi-asserted-by":"crossref","first-page":"e0189163","DOI":"10.1371\/journal.pone.0189163","article-title":"Comparison of sequential multiplex PCR, sequetyping and whole genome sequencing for serotyping of Streptococcus pneumoniae","volume":"12","author":"Mauffrey","year":"2017","journal-title":"PLoS One"},{"issue":"5","key":"2020080709264840000_ref39","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1128\/JB.186.5.1518-1530.2004","article-title":"eBURST: inferring patterns of evolutionary descent among clusters of related bacterial genotypes from multilocus sequence typing data","volume":"186","author":"Feil","year":"2004","journal-title":"J Bacteriol"},{"key":"2020080709264840000_ref40","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/1471-2105-13-87","article-title":"PHYLOViZ: phylogenetic inference and data visualization for sequence based typing methods","volume":"13","author":"Francisco","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2020080709264840000_ref41","first-page":"207","volume-title":"Canadian Conference on Artificial Intelligence","author":"Gaudette","year":"2009"},{"key":"2020080709264840000_ref42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ygeno.2015.11.003","article-title":"The sequence of sequencers: the history of sequencing DNA","volume":"107","author":"Heather","year":"2016","journal-title":"Genomics"},{"key":"2020080709264840000_ref43","first-page":"3","article-title":"When training and test sets are different: characterizing learning transfer[J]","volume-title":"Dataset Shift in Machine Learning","author":"Storkey","year":"2009"},{"issue":"8","key":"2020080709264840000_ref44","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s12272-017-0933-y","article-title":"Pneumonia and Streptococcus pneumoniae vaccine","volume":"40","author":"Kim","year":"2017","journal-title":"Arch Pharm Res"},{"issue":"3","key":"2020080709264840000_ref45","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1128\/JCM.01778-16","article-title":"Emergence of multidrug-resistant pneumococcal serotype 35B among children in the United States","volume":"55","author":"Olarte","year":"2017","journal-title":"J Clin Microbiol"},{"issue":"2","key":"2020080709264840000_ref46","doi-asserted-by":"crossref","first-page":"e1002000","DOI":"10.1371\/journal.ppat.1002000","article-title":"Compensatory evolution of pbp mutations restores the fitness cost imposed by beta-lactam resistance in Streptococcus pneumoniae","volume":"7","author":"Albarracin Orio","year":"2011","journal-title":"PLoS Pathog"},{"issue":"2","key":"2020080709264840000_ref47","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1111\/j.0006-341X.2001.00632.x","article-title":"Relating amino acid sequence to phenotype: analysis of peptide-binding data","volume":"57","author":"Segal","year":"2001","journal-title":"Biometrics"},{"issue":"2","key":"2020080709264840000_ref48","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgen.1006508","article-title":"Interacting networks of resistance, virulence and core machinery genes identified by genome-wide epistasis analysis","volume":"13","author":"Skwark","year":"2017","journal-title":"PLoS Genet"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/21\/4\/1347\/33584209\/bbz056.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/21\/4\/1347\/33584209\/bbz056.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,7]],"date-time":"2020-08-07T13:39:32Z","timestamp":1596807572000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/21\/4\/1347\/5512424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,11]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2019,6,11]]},"published-print":{"date-parts":[[2020,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbz056","relation":{},"ISSN":["1477-4054"],"issn-type":[{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,7]]},"published":{"date-parts":[[2019,6,11]]}}}