{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:57:13Z","timestamp":1790575033971,"version":"4.1.0"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"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. Bioinform."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Carbapenem-resistant\n                      <jats:italic>Acinetobacter baumannii<\/jats:italic>\n                      is a hospital-associated pathogen linked to high mortality and limited treatment options. Although many resistance determinants have been identified, how they organize into coordinated systems remains unclear.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using a final binary modeling dataset of 2,448 genomes, we benchmarked machine-learning and graph-based models and developed a framework that pairs accurate prediction with systems-level genomic interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Across five random seeds and 10-fold stratified cross-validation, a Random Forest classifier achieved the strongest internal performance using a bag-of-genes representation, with an accuracy of 0.9328 \u00b1 0.0175 and ROC-AUC of 0.9650 \u00b1 0.0138. Random Forest also generalized best in an independent BV-BRC Asia validation cohort of 2,500 genomes, achieving an accuracy of 0.7728 and ROC-AUC of 0.8392. In parallel, a Graph Convolutional Network trained on gene-adjacency graphs enabled interpretation through\n                      <jats:italic>post hoc<\/jats:italic>\n                      explainability, prioritizing genes consistent with a candidate three-layer resistance architecture: (i) canonical rapid-response resistance genes, (ii) a cell-surface \u201cSugar Shield\u201d centered on GDP\/UDP-epimerase, and (iii) a metabolic \u201cCommand Center\u201d involving regulators such as DnaA and quinone oxidoreductase 1. Explanation-stability analysis identified a reproducible consensus subset while supporting cautious interpretation of individual rankings. Complementary computational analyses, including protein\u2013protein interaction enrichment, Gene Ontology enrichment, structural modeling, and molecular docking, supported the biological coherence and structural plausibility of the proposed architecture.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Together, these findings suggest that carbapenem resistance may reflect a coordinated, multi-layer defense system and nominate GDP\/UDP-epimerase and quinone oxidoreductase 1 as candidates for future experimental investigation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbinf.2026.1885813","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:34Z","timestamp":1790574274000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A comparative analysis of graph neural networks and classical machine learning for carbapenem-resistance prediction and genomic interpretation in Acinetobacter baumannii"],"prefix":"10.3389","volume":"6","author":[{"given":"Irfan Sharif","family":"Shaik","sequence":"first","affiliation":[{"name":"Hercules High School","place":["Hercules, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Morteza","family":"Sarmadi","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology Alumni Association","place":["Cambridge, MA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5574","DOI":"10.3390\/ijms26125574","article-title":"Metabolic rewiring of bacterial pathogens in response to antibiotic pressure: a molecular perspective","volume":"26","author":"Acierno","year":"2025","journal-title":"Int. J. Mol. Sci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s41597-023-01974-x","article-title":"Evaluating explainability for graph neural networks","volume":"10","author":"Agarwal","year":"2023","journal-title":"Sci. Data"},{"key":"B3","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1159\/000522232","article-title":"The capsule of Acinetobacter baumannii protects against the innate immune response","volume":"14","author":"Akoolo","year":"2022","journal-title":"J. Innate Immun."},{"key":"B4","doi-asserted-by":"publisher","first-page":"e00774-19","DOI":"10.1128\/mSystems.00774-19","article-title":"Prediction of acquired antimicrobial resistance for multiple bacterial species using neural networks","volume":"5","author":"Aytan-Aktug","year":"2020","journal-title":"mSystems"},{"key":"B5","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/s40121-022-00597-w","article-title":"Carbapenem-resistant Acinetobacter baumannii: colonization, infection and current treatment options","volume":"11","author":"Bartal","year":"2022","journal-title":"Infect. Dis. Ther."},{"key":"B6","doi-asserted-by":"publisher","first-page":"dlaf134","DOI":"10.1093\/jacamr\/dlaf134","article-title":"The global epidemiology of carbapenem-resistant Acinetobacter baumannii","volume":"7","author":"Boutzoukas","year":"2025","journal-title":"JAC Antimicrob. Resist"},{"key":"B7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B8","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.02428","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019","journal-title":"arXiv"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1320312","DOI":"10.3389\/fmicb.2023.1320312","article-title":"Machine learning and feature extraction for rapid antimicrobial resistance prediction of Acinetobacter baumannii from whole-genome sequencing data","volume":"14","author":"Gao","year":"2024","journal-title":"Front. Microbiol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e1004691","DOI":"10.1371\/journal.ppat.1004691","article-title":"Antibiotic modulation of capsular exopolysaccharide and virulence in Acinetobacter baumannii","volume":"11","author":"Geisinger","year":"2015","journal-title":"PLoS Pathog."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e1007030","DOI":"10.1371\/journal.ppat.1007030","article-title":"A global regulatory system links virulence and antibiotic resistance to envelope homeostasis in Acinetobacter baumannii","volume":"14","author":"Geisinger","year":"2018","journal-title":"PLoS Pathog."},{"key":"B14","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"node2vec: scalable feature learning for networks","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Grover","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e000306","DOI":"10.1099\/mgen.0.000306","article-title":"Emergence, molecular mechanisms and global spread of carbapenem-resistant Acinetobacter baumannii","volume":"5","author":"Hamidian","year":"2019","journal-title":"Microb. Genom"},{"key":"B16","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"B17","doi-asserted-by":"publisher","first-page":"e01805-22","DOI":"10.1128\/jcm.01805-22","article-title":"Novel clinical mNGS-based machine learning model for rapid antimicrobial susceptibility testing of Acinetobacter baumannii","volume":"61","author":"Hu","year":"2023","journal-title":"J. Clin. Microbiol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"bbae206","DOI":"10.1093\/bib\/bbae206","article-title":"Assessing computational predictions of antimicrobial resistance phenotypes from microbial genomes","volume":"25","author":"Hu","year":"2024","journal-title":"Brief. Bioinform"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e01446-24","DOI":"10.1128\/aac.01446-24","article-title":"Neural network-based predictions of antimicrobial resistance phenotypes in multidrug-resistant Acinetobacter baumannii from whole genome sequencing and gene expression","volume":"68","author":"Jia","year":"2024","journal-title":"Antimicrob. Agents Chemother."},{"key":"B20","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"B21","doi-asserted-by":"publisher","first-page":"4848","DOI":"10.1128\/AAC.00762-13","article-title":"Structures of the class D carbapenemases OXA-23 and OXA-146: mechanistic basis of activity against carbapenems, extended-spectrum cephalosporins, and aztreonam","volume":"57","author":"Kaitany","year":"2013","journal-title":"Antimicrob. Agents Chemother."},{"key":"B22","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40537-023-00876-4","article-title":"A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions","volume":"11","author":"Khemani","year":"2024","journal-title":"J. Big Data"},{"key":"B23","article-title":"Adam: a method for stochastic optimization","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Kingma","year":"2015"},{"key":"B24","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Kipf","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1038\/s41401-019-0228-6","article-title":"CB-Dock: a web server for cavity detection-guided protein-ligand blind docking","volume":"41","author":"Liu","year":"2020","journal-title":"Acta Pharmacol. Sin."},{"key":"B26","article-title":"Decoupled weight decay regularization","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3298","DOI":"10.1128\/AAC.48.9.3298-3304.2004","article-title":"Expression of the RND-type efflux pump AdeABC in Acinetobacter baumannii is regulated by the AdeRS two-component system","volume":"48","author":"Marchand","year":"2004","journal-title":"Antimicrob. Agents Chemother."},{"key":"B28","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1111\/j.1574-6976.2011.00282.x","article-title":"Metabolic regulation of antibiotic resistance","volume":"35","author":"Mart\u00ednez","year":"2011","journal-title":"FEMS Microbiol. Rev."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e1006258","DOI":"10.1371\/journal.pcbi.1006258","article-title":"Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data","volume":"14","author":"Moradigaravand","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1093\/femsre\/fux013","article-title":"Klebsiella pneumoniae: a major worldwide source and shuttle for antibiotic resistance","volume":"41","author":"Navon-Venezia","year":"2017","journal-title":"FEMS Microbiol. Rev."},{"key":"B31","doi-asserted-by":"publisher","first-page":"3555","DOI":"10.1038\/s41467-026-69934-8","article-title":"AMR-GNN: a multi-representation graph neural network framework to enable genomic antimicrobial resistance prediction","volume":"17","author":"Nguyen","year":"2026","journal-title":"Nat. Commun."},{"key":"B32","doi-asserted-by":"publisher","first-page":"D678","DOI":"10.1093\/nar\/gkac1003","article-title":"Introducing the bacterial and viral bioinformatics resource center (BV-BRC): a resource combining PATRIC, IRD and ViPR","volume":"51","author":"Olson","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B33","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.biotechadv.2018.11.013","article-title":"Antibiotic resistance in Pseudomonas aeruginosa: mechanisms and alternative therapeutic strategies","volume":"37","author":"Pang","year":"2019","journal-title":"Biotechnol. Adv."},{"key":"B34","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn Res."},{"key":"B35","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1145\/2623330.2623732","article-title":"DeepWalk: online learning of social representations","volume-title":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Perozzi","year":"2014"},{"key":"B36","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1093\/bioinformatics\/btu153","article-title":"Prokka: rapid prokaryotic genome annotation","volume":"30","author":"Seemann","year":"2014","journal-title":"Bioinformatics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"3301","DOI":"10.3389\/fmicb.2018.03301","article-title":"Diversity and function of capsular polysaccharide in Acinetobacter baumannii","volume":"9","author":"Singh","year":"2019","journal-title":"Front. Microbiol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"a012922","DOI":"10.1101\/cshperspect.a012922","article-title":"Regulating DNA replication in bacteria","volume":"5","author":"Skarstad","year":"2013","journal-title":"Cold Spring Harb. Perspect. Biol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1268","DOI":"10.1128\/JB.01025-15","article-title":"Different functions of phylogenetically distinct bacterial complex I isozymes","volume":"198","author":"Spero","year":"2016","journal-title":"J. Bacteriol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The STRING database in 2023: protein\u2013protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"Szklarczyk","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B41","doi-asserted-by":"publisher","first-page":"D330","DOI":"10.1093\/nar\/gky1055","article-title":"The gene ontology resource: 20 years and still GOing strong","volume":"47","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"B42","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"B43","article-title":"Graph attention networks","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1016\/j.cmi.2022.05.024","article-title":"External validation of WGS-based antimicrobial susceptibility prediction tools, KOVER-AMR and ResFinder 4.1, for Escherichia coli clinical isolates","volume":"28","author":"Verschuuren","year":"2022","journal-title":"Clin. Microbiol. Infect."},{"key":"B45","volume-title":"WHO Bacterial Priority Pathogens List, 2024: Bacterial Pathogens of Public Health Importance to Guide Research, Development and Strategies to Prevent and Control Antimicrobial Resistance","year":"2024"},{"key":"B46","first-page":"9240","article-title":"GNNExplainer: generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"B47","doi-asserted-by":"publisher","first-page":"e3003539","DOI":"10.1371\/journal.pbio.3003539","article-title":"Biased sampling driven by bacterial population structure confounds machine learning prediction of antimicrobial resistance","volume":"23","author":"Yu","year":"2025","journal-title":"PLoS Biol."},{"key":"B48","doi-asserted-by":"publisher","first-page":"690049","DOI":"10.3389\/fgene.2021.690049","article-title":"Graph neural networks and their current applications in bioinformatics","volume":"12","author":"Zhang","year":"2021","journal-title":"Front. Genet."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1885813\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:40Z","timestamp":1790574280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1885813\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":48,"alternative-id":["10.3389\/fbinf.2026.1885813"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1885813","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"article-number":"1885813"}}