{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:59:50Z","timestamp":1790312390559,"version":"4.1.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Antimicrobial resistance is a major global health threat, and \u03b2-lactamase-mediated inactivation of \u03b2-lactam antibiotics remains a leading cause of treatment failure. Rapid identification of emerging \u03b2-lactamase variants and improved understanding of their functional diversity are therefore essential for resistance surveillance and therapeutic development.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Here, we developed an interpretable machine learning framework to classify major Class A \u03b2-lactamase subclasses (TEM, SHV, and CTX-M) and distinguish them from non-\u03b2-lactamase hydrolases using multidimensional protein descriptors. Descriptors based on sequence composition, physicochemical properties, residue accessibility, and structural topology were evaluated to identify a minimal panel of 30 descriptors while preserving biological interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The selected descriptors provided strong discriminatory power and were linked to steric environment, hydrophobicity, flexibility, solvent exposure, and residue interaction patterns, consistent with roles in substrate recognition and catalysis. Projection into reduced descriptor space identified transitional variants near subclass boundaries, including CTX-M\/SHV convergence zones and non-\u03b2-lactamase hydrolases with partial \u03b2-lactamase-like signatures. Representative case studies indicated that some apparent misclassifications may reflect annotation inconsistencies, scaffold convergence, or early adaptive trajectories, highlighting candidates for experimental follow-up. External validation using 271 independent proteins annotated as non-\u03b2-lactamase hydrolases demonstrated 96.95% specificity, with only limited false-positive assignments. Most incorrect classifications showed weak statistical support, indicating that confidence filtering could further improve screening performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Overall, this study demonstrates that compact descriptor-based models can provide accurate and interpretable classification of \u03b2-lactamase-related proteins while identifying emerging boundary variants relevant to antimicrobial resistance surveillance. The framework offers a scalable approach for protein annotation, monitoring resistance evolution, and supporting future inhibitor development.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2026.1876559","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:26:13Z","timestamp":1790310373000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning classifies \u03b2-lactamase subclasses and prioritizes boundary variants for antimicrobial resistance surveillance"],"prefix":"10.3389","volume":"17","author":[{"given":"Rahul","family":"Kaushik","sequence":"first","affiliation":[{"name":"Laboratory of In-silico Design, Artificial Intelligence Center for Health and Biomedical Research, National Institutes of Biomedical Innovation, Health and Nutrition (NIBN)","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyong","family":"Re","sequence":"additional","affiliation":[{"name":"Laboratory of In-silico Design, Artificial Intelligence Center for Health and Biomedical Research, National Institutes of Biomedical Innovation, Health and Nutrition (NIBN)","place":["Osaka, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"B2","doi-asserted-by":"publisher","first-page":"D690","DOI":"10.1093\/nar\/gkac920","article-title":"CARD 2023: expanded curation, support for machine learning, and resistome prediction at the comprehensive antibiotic resistance database","volume":"51","author":"Alcock","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s40168-018-0401-z","article-title":"DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data","volume":"6","author":"Arango-Argoty","year":"2018","journal-title":"Microbiome"},{"key":"B4","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the universal protein knowledgebase in 2025","volume":"53","author":"Bateman","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1444781","DOI":"10.3389\/fphar.2024.1444781","article-title":"Mechanism of antibacterial resistance, strategies and next-generation antimicrobials to contain antimicrobial resistance: a review","volume":"15","author":"Belay","year":"2024","journal-title":"Front. Pharmacol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nmeth.3176","article-title":"Fast and sensitive protein alignment using DIAMOND","volume":"12","author":"Buchfink","year":"2015","journal-title":"Nat. Methods"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e01076-18","DOI":"10.1128\/AAC.01076-18","article-title":"Past and present perspectives on \u03b2-Lactamases","volume":"62","author":"Bush","year":"2018","journal-title":"Antimicrob. Agents Chemother."},{"key":"B8","doi-asserted-by":"publisher","first-page":"e00047-19","DOI":"10.1128\/CMR.00047-19","article-title":"Epidemiology of \u03b2-Lactamase-Producing pathogens","volume":"33","author":"Bush","year":"2020","journal-title":"Clin. Microbiol. Rev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1016\/j.bbrc.2016.10.119","article-title":"Protein folding is a convergent problem","volume":"480","author":"Das Gupta","year":"2016","journal-title":"Biochem. Biophysical Res. Commun."},{"key":"B10","doi-asserted-by":"publisher","first-page":"e1002184","DOI":"10.1371\/journal.pmed.1002184","article-title":"Will 10 million people die a year due to antimicrobial resistance by 2050?","volume":"13","author":"de Kraker","year":"2016","journal-title":"PLoS Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"18438","DOI":"10.1039\/D5SC04513D","article-title":"Prediction of enzyme function using an interpretable optimized ensemble learning framework","volume":"16","author":"Dhibar","year":"2025","journal-title":"Chem. Sci."},{"key":"B12","doi-asserted-by":"publisher","first-page":"S44","DOI":"10.1093\/jtm\/taw102","article-title":"The ecology of extended-spectrum \u03b2-lactamases (ESBLs) in the developed world","volume":"24","author":"Doi","year":"2017","journal-title":"J. Travel Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1038\/s42003-024-06880-5","article-title":"Computational screening of the effects of mutations on protein-protein off-rates and dissociation mechanisms by \u03c4RAMD","volume":"7","author":"D\u2019Arrigo","year":"2024","journal-title":"Commun. Biol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Others, ProtTrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B15","doi-asserted-by":"publisher","first-page":"31179","DOI":"10.1038\/s41598-025-13178-x","article-title":"An efficient machine-learning framework for predicting protein post-translational modification sites","volume":"15","author":"Elreify","year":"2025","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1016\/j.csbj.2023.05.022","article-title":"An overview of descriptors to capture protein properties \u2013 tools and perspectives in the context of QSAR modeling","volume":"21","author":"Emonts","year":"2023","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B17","doi-asserted-by":"publisher","first-page":"mgen000832","DOI":"10.1099\/mgen.0.000832","article-title":"Curation of the AMRFinderPlus databases: applications, functionality and impact","volume":"8","author":"Feldgarden","year":"2022","journal-title":"Microb. Genomics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1016\/j.jmb.2007.06.017","article-title":"Convergent evolution of enzyme active sites is not a rare phenomenon","volume":"372","author":"Gherardini","year":"2007","journal-title":"J. Mol. Biol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/j.1469-0691.2007.01854.x","article-title":"Evolution of extended-spectrum \u03b2-lactamases by mutation","volume":"14","author":"Gniadkowski","year":"2008","journal-title":"Clin. Microbiol. Infect."},{"key":"B20","doi-asserted-by":"publisher","first-page":"6656","DOI":"10.1038\/s41598-019-42866-8","article-title":"The structural dynamics of engineered \u03b2-Lactamases vary broadly on three timescales yet sustain native function","volume":"9","author":"Gobeil","year":"2019","journal-title":"Sci. Rep."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1093\/jac\/dki130","article-title":"Revised ambler classification of \u03b2-lactamases","volume":"55","author":"Hall","year":"2005","journal-title":"J. Antimicrob. Chemother."},{"key":"B22","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"key":"B23","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s43586-024-00363-x","article-title":"Uniform manifold approximation and projection","volume":"4","author":"Healy","year":"2024","journal-title":"Nat. Rev. Methods Prim."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e70208","DOI":"10.1002\/pro.70208","article-title":"DSSP 4: FAIR annotation of protein secondary structure","volume":"34","author":"Hekkelman","year":"2025","journal-title":"Protein Sci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"107200","DOI":"10.1016\/j.ijid.2024.107200","article-title":"Critical insights from recent outbreaks of mycoplasma pneumoniae: decoding the challenges and effective interventions strategies","volume":"147","author":"Kant","year":"2024","journal-title":"Int. J. Infect. Dis."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1880887","DOI":"10.3389\/frbis.2026.1880887","article-title":"Intrinsically disordered regions as drivers of protein aggregation: mechanisms, phase separation, and emerging predictive frameworks","volume":"4","author":"Kaushik","year":"2026","journal-title":"Front. Biophysics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1002\/prot.25900","article-title":"A protein sequence fitness function for identifying natural and nonnatural proteins","volume":"88","author":"Kaushik","year":"2020","journal-title":"Proteins"},{"key":"B28","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1093\/bioinformatics\/btab666","article-title":"ProFitFun: a protein tertiary structure fitness function for quantifying the accuracies of model structures","volume":"38","author":"Kaushik","year":"","journal-title":"Bioinformatics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"6467","DOI":"10.1016\/j.csbj.2022.11.032","article-title":"An integrated protein structure fitness scoring approach for identifying native-like model structures","volume":"20","author":"Kaushik","year":"","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B30","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1021\/acs.biochem.7b01073","article-title":"Where informatics lags chemistry leads","volume":"57","author":"Kaushik","year":"2018","journal-title":"Biochemistry"},{"key":"B31","doi-asserted-by":"publisher","first-page":"113303","DOI":"10.1016\/j.envres.2022.113303","article-title":"A novel structure-based approach for identification of vertebrate susceptibility to SARS-CoV-2: implications for future surveillance programmes","volume":"212","author":"Kaushik","year":"2022","journal-title":"Environ. Res."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1258159","DOI":"10.3389\/fbrio.2023.1258159","article-title":"Artificial intelligence in accelerating vaccine development - current and future perspectives","volume":"2","author":"Kaushik","year":"2023","journal-title":"Front. Bacteriol."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1101\/2024.06.11.598423","article-title":"Decoding protein aggregation through computational approach: identification and scoring of aggregation-prone regions in protein sequences","author":"Kaushik","year":"2024","journal-title":"bioRXiv"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1111\/eva.12835","article-title":"The functional convergence of antibiotic resistance in \u03b2-lactamases is not conferred by a simple convergent substitution of amino acid","volume":"12","author":"Keshri","year":"2019","journal-title":"Evol. Appl."},{"key":"B35","doi-asserted-by":"publisher","first-page":"2435365","DOI":"10.1080\/14756366.2024.2435365","article-title":"Structural comparison of substrate-binding pockets of serine \u03b2-lactamases in classes A, C, and D","volume":"40","author":"Lee","year":"2025","journal-title":"J. Enzyme Inhibition Med. Chem."},{"key":"B36","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.medine.2022.05.004","article-title":"Resistance mechanisms in Gram-negative bacteria","volume":"46","author":"Lepe","year":"2022","journal-title":"Med. Intensiva Engl. Ed."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"B38","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"B39","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.1038\/s41598-025-86519-5","article-title":"Benchmarking protein language models for protein crystallization","volume":"15","author":"Mall","year":"2025","journal-title":"Sci. Rep."},{"key":"B40","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1038\/s42003-021-02586-0","article-title":"Accelerating antibiotic discovery through artificial intelligence","volume":"4","author":"Melo","year":"2021","journal-title":"Commun. Biol."},{"key":"B41","doi-asserted-by":"publisher","first-page":"e4792","DOI":"10.1002\/pro.4792","article-title":"UCSF ChimeraX: tools for structure building and analysis","volume":"32","author":"Meng","year":"2023","journal-title":"Protein Sci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"12555","DOI":"10.3390\/ijms252312555","article-title":"AAindexNC: estimating the physicochemical properties of non-canonical amino acids, including those derived from the PDB and PDBeChem databank","volume":"25","author":"Milchevskiy","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"B43","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/S0140-6736(21)02724-0","article-title":"Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis","volume":"399","author":"Murray","year":"2022","journal-title":"Lancet"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1016\/S0140-6736(24)01867-1","article-title":"Global burden of bacterial antimicrobial resistance 1990\u20132021: a systematic analysis with forecasts to 2050","volume":"404","author":"Naghavi","year":"2024","journal-title":"Lancet"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1016\/j.cmi.2025.03.013","article-title":"Emerging resistance mechanisms to newer \u03b2-lactams in Pseudomonas aeruginosa","volume":"31","author":"Oliver","year":"2025","journal-title":"Clin. Microbiol. Infect."},{"key":"B46","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1002\/prot.26776","article-title":"\u03b1\/\u03b2 hydrolases: toward unraveling entangled classification","volume":"93","author":"Ozhelvaci","year":"2025","journal-title":"Proteins"},{"key":"B47","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/s41586-025-09519-5","article-title":"Connecting chemical and protein sequence space to predict biocatalytic reactions","volume":"646","author":"Paton","year":"2025","journal-title":"Nature"},{"key":"B48","doi-asserted-by":"publisher","first-page":"14085","DOI":"10.1021\/acs.chemrev.1c00757","article-title":"Protein design: from the aspect of water solubility and stability","volume":"122","author":"Qing","year":"2022","journal-title":"Chem. Rev."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1420170","DOI":"10.3389\/fphar.2024.1420170","article-title":"Novel \u03b2-lactam antibiotics versus other antibiotics for treatment of complicated urinary tract infections: a systematic review and meta-analysis","volume":"15","author":"Quan","year":"2024","journal-title":"Front. Pharmacol."},{"key":"B50","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1038\/s42003-024-05868-5","article-title":"Positive epistasis drives clavulanic acid resistance in double mutant libraries of BlaC \u03b2-lactamase","volume":"7","author":"Radojkovi\u0107","year":"2024","journal-title":"Commun. Biol."},{"key":"B51","doi-asserted-by":"publisher","first-page":"e0029022","DOI":"10.1128\/aac.00290-22","article-title":"Evolutionary trajectories toward high-level \u03b2-Lactam\/\u03b2-Lactamase inhibitor resistance in the presence of multiple \u03b2-Lactamases","volume":"66","author":"Rajer","year":"2022","journal-title":"Antimicrob. Agents Chemother."},{"key":"B52","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","article-title":"Computational approaches streamlining drug discovery","volume":"616","author":"Sadybekov","year":"2023","journal-title":"Nature"},{"key":"B53","doi-asserted-by":"publisher","first-page":"e0108224","DOI":"10.1128\/aac.01082-24","article-title":"Genomics for antimicrobial resistance-progress and future directions","volume":"69","author":"Sherry","year":"2025","journal-title":"Antimicrob. Agents Chemother."},{"key":"B54","doi-asserted-by":"publisher","first-page":"8180","DOI":"10.1038\/s41467-024-52533-w","article-title":"Accurately predicting enzyme functions through geometric graph learning on ESMFold-predicted structures","volume":"15","author":"Song","year":"2024","journal-title":"Nat. Commun."},{"key":"B55","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1039\/c8md00342d","article-title":"\u03b2-lactam\/\u03b2-lactamase inhibitor combinations: an update","volume":"9","author":"Tehrani","year":"2018","journal-title":"Med. Chem. Comm."},{"key":"B56","doi-asserted-by":"publisher","first-page":"7166","DOI":"10.1021\/jacs.2c12123","article-title":"Tautomer-specific deacylation and \u03a9-Loop flexibility explain the carbapenem-hydrolyzing broad-spectrum activity of the KPC-2 \u03b2-Lactamase","volume":"145","author":"Tooke","year":"2023","journal-title":"J. Am. Chem. Soc."},{"key":"B57","doi-asserted-by":"publisher","first-page":"D489","DOI":"10.1093\/nar\/gkaf1187","article-title":"RCSB protein data bank: delivering integrative structures alongside experimental structures and computed structure models","volume":"54","author":"Vallat","year":"2026","journal-title":"Nucleic Acids Res."},{"key":"B58","doi-asserted-by":"publisher","first-page":"btad690","DOI":"10.1093\/bioinformatics\/btad690","article-title":"PLM-ARG: antibiotic resistance gene identification using a pretrained protein language model","volume":"39","author":"Wu","year":"2023","journal-title":"Bioinformatics"},{"key":"B59","doi-asserted-by":"publisher","first-page":"101036","DOI":"10.1016\/j.drup.2023.101036","article-title":"Global spread characteristics of CTX-M-type extended-spectrum \u03b2-lactamases: a genomic epidemiology analysis","volume":"73","author":"Yu","year":"2024","journal-title":"Drug Resist. Updat."},{"key":"B60","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"B61","doi-asserted-by":"publisher","first-page":"1565860","DOI":"10.3389\/fphar.2025.1565860","article-title":"Predicting protein\u2013protein interactions in microbes associated with cardiovascular diseases using deep denoising autoencoders and evolutionary information","volume":"16","author":"Zhou","year":"2025","journal-title":"Front. Pharmacol."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1876559\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:26:14Z","timestamp":1790310374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2026.1876559\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":61,"alternative-id":["10.3389\/fphar.2026.1876559"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2026.1876559","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"article-number":"1876559"}}