{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T11:32:39Z","timestamp":1788003159633,"version":"build-2784847793"},"posted":{"date-parts":[[2025,7,7]]},"group-title":"Bioinformatics","reference-count":64,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH NIAID","award":["1U01AI176414"],"award-info":[{"award-number":["1U01AI176414"]}]},{"name":"NIH NLM","award":["T15LM009451"],"award-info":[{"award-number":["T15LM009451"]}]},{"name":"University of Colorado Anschutz","award":["Start-up"],"award-info":[{"award-number":["Start-up"]}]},{"DOI":"10.13039\/100007709","name":"Michigan State University","doi-asserted-by":"crossref","award":["NSF-funded BEACON"],"award-info":[{"award-number":["NSF-funded BEACON"]}],"id":[{"id":"10.13039\/100007709","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,10,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Since the clinical introduction of antibiotics in the 1940s, antimicrobial resistance (AMR) has become an increasingly dire threat to global public health. Pathogens acquire AMR much faster than we discover new drugs (antibiotics), warranting innovative methods to better understand its molecular underpinnings. Traditional approaches for detecting AMR in novel bacterial strains are time-consuming and labor-intensive. However, advances in sequencing technology offer a plethora of bacterial genome data, and computational approaches like machine learning (ML) provide an optimistic scope for in silico AMR prediction. Here, we introduce a comprehensive multiscale ML approach to predict AMR phenotypes and identify AMR molecular features associated with a single drug or drug family, stratified by time and geographical locations. As a case study, we focus on a subset of the World Health Organization\u2019s Bacterial Priority Pathogens, the frequently drug-resistant and nosocomial ESKAPE pathogens: Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter species. We started with sequenced genomes with lab-derived AMR phenotypes, constructed pangenomes, clustered gene and protein sequences, and extracted protein domains to generate pangenomic features across molecular scales. To uncover the molecular mechanisms behind drug-\/drug class-specific resistance, we trained logistic regression ML models on our datasets. These yielded ranked lists of AMR-associated genes, proteins, and domains. In addition to recapitulating known AMR features, our models identified novel candidates for experimental validation. The models were performant across molecular scales, data types, and drugs while achieving a median normalized Matthews correlation coefficient of 0.89. Prediction performance showed resilience even when evaluated on geographical and temporal holdouts. We also evaluated model generalizability and cross-resistance across the drug-\/drug class-specific models cross-tested on other available drug-\/drug class genomes. Finally, we uncovered multiple drug class resistance features using multiclass and multilabel models. Our holistic approach promises reliable prediction of existing and developing resistance in newly sequenced pathogen genomes, while pinpointing the mechanistic molecular contributors of AMR. All our models and results are available at our interactive web app,\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/jravilab.org\/amr\">https:\/\/jravilab.org\/amr<\/jats:ext-link>\n                  .\n                <\/jats:p>","DOI":"10.1101\/2025.07.03.663053","type":"posted-content","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:40:16Z","timestamp":1751910016000},"source":"Crossref","is-referenced-by-count":3,"title":["From sequence to signature: Machine learning uncovers multiscale feature landscapes that predict AMR across ESKAPE pathogens"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3980-4749","authenticated-orcid":false,"given":"Abhirupa","family":"Ghosh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7067-8886","authenticated-orcid":false,"given":"Evan P","family":"Brenner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5724-0265","authenticated-orcid":false,"given":"Charmie K","family":"Vang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7544-7354","authenticated-orcid":false,"given":"Ethan P","family":"Wolfe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1718-3488","authenticated-orcid":false,"given":"Emily A","family":"Boyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7854-6304","authenticated-orcid":false,"given":"Raymond L","family":"Lesiyon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9891-3283","authenticated-orcid":false,"given":"Keenan R","family":"Manpearl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vignesh","family":"Sridhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0532-3338","authenticated-orcid":false,"given":"Joseph T","family":"Burke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0523-1508","authenticated-orcid":false,"given":"Jacob D","family":"Krol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jill MR","family":"Bilodeaux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7443-925X","authenticated-orcid":false,"given":"Janani","family":"Ravi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025102318001543000_2025.07.03.663053v2.1","doi-asserted-by":"crossref","unstructured":"Michael, C. A. , Dominey-Howes, D. & Labbate, M. The Antimicrobial Resistance Crisis: Causes, Consequences, and Management. Front. Public Health 2, (2014).","DOI":"10.3389\/fpubh.2014.00145"},{"key":"2025102318001543000_2025.07.03.663053v2.2","first-page":"dlad001","article-title":"Systematic review of time lag between antibiotic use and rise of resistant pathogens among hospitalized adults in Europe","volume":"5","year":"2023","journal-title":"JAC-Antimicrob. Resist"},{"key":"2025102318001543000_2025.07.03.663053v2.3","doi-asserted-by":"crossref","unstructured":"Ho, C. S. et al. Antimicrobial resistance: a concise update. Lancet Microbe 6, (2025).","DOI":"10.1016\/j.lanmic.2024.07.010"},{"key":"2025102318001543000_2025.07.03.663053v2.4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)02724-0\/ATTACHMENT\/4504FC2B-08AE-46D6-BD75-80811DF8B5E6\/MMC1.PDF"},{"key":"2025102318001543000_2025.07.03.663053v2.5","unstructured":"Review on Antimicrobial Resistance. Antimicrobial Resistance: Tackling a crisis for the health and wealth of nations. (2014)."},{"key":"2025102318001543000_2025.07.03.663053v2.6","doi-asserted-by":"crossref","first-page":"3148","DOI":"10.1038\/s41598-024-53130-z","article-title":"Next generation antibiotic combinations to combat pan-drug resistant Klebsiella pneumoniae","volume":"14","year":"2024","journal-title":"Sci. Rep"},{"key":"2025102318001543000_2025.07.03.663053v2.7","unstructured":"Stockholm: European Centre for Disease Prevention and Control and World Health Organization. Antimicrobial resistance surveillance in Europe 2023 - 2021 data. (2023)."},{"key":"2025102318001543000_2025.07.03.663053v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhazmat.2022.129477"},{"key":"2025102318001543000_2025.07.03.663053v2.9","unstructured":"The antibiotic resistance crisis and the development of new antibiotics - Br\u00fcssow - 2024 - Microbial Biotechnology - Wiley Online Library. https:\/\/enviromicro-journals.onlinelibrary.wiley.com\/doi\/full\/10.1111\/1751-7915.14510."},{"key":"2025102318001543000_2025.07.03.663053v2.10","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abo7793"},{"key":"2025102318001543000_2025.07.03.663053v2.11","doi-asserted-by":"crossref","unstructured":"Sati, H. et al. The WHO Bacterial Priority Pathogens List 2024: a prioritisation study to guide research, development, and public health strategies against antimicrobial resistance. Lancet Infect. Dis. 0, (2025).","DOI":"10.1016\/S1473-3099(25)00118-5"},{"key":"2025102318001543000_2025.07.03.663053v2.12","doi-asserted-by":"publisher","DOI":"10.3390\/pathogens10101310"},{"key":"2025102318001543000_2025.07.03.663053v2.13","doi-asserted-by":"crossref","first-page":"308","DOI":"10.3389\/fcimb.2020.00308","article-title":"Modern Tools for Rapid Diagnostics of Antimicrobial Resistance","volume":"10","year":"2020","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"2025102318001543000_2025.07.03.663053v2.14","first-page":"277","article-title":"The antibiotic resistance crisis: part 1: causes and threats","volume":"40","year":"2015","journal-title":"P T Peer-Rev. J. Formul. Manag"},{"key":"2025102318001543000_2025.07.03.663053v2.15","doi-asserted-by":"publisher","DOI":"10.1038\/nrmicro3380"},{"key":"2025102318001543000_2025.07.03.663053v2.16","doi-asserted-by":"crossref","first-page":"586460","DOI":"10.3389\/fcimb.2020.586460","article-title":"Editorial: The Molecular Mechanisms of Antibiotic Resistance in Aquatic Pathogens","volume":"10","year":"2020","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"2025102318001543000_2025.07.03.663053v2.17","doi-asserted-by":"crossref","first-page":"4.2.15","DOI":"10.1128\/microbiolspec.VMBF-0016-2015","article-title":"Mechanisms of Antibiotic Resistance","volume":"4","year":"2016","journal-title":"Microbiol. Spectr"},{"key":"2025102318001543000_2025.07.03.663053v2.18","doi-asserted-by":"publisher","DOI":"10.1128\/jcm.01260-20"},{"key":"2025102318001543000_2025.07.03.663053v2.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2025.04.017"},{"key":"2025102318001543000_2025.07.03.663053v2.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.biotechadv.2021.107739"},{"key":"2025102318001543000_2025.07.03.663053v2.21","doi-asserted-by":"publisher","DOI":"10.1186\/s40168-018-0401-z"},{"key":"2025102318001543000_2025.07.03.663053v2.22","doi-asserted-by":"crossref","first-page":"103733","DOI":"10.1016\/j.xpro.2025.103733","article-title":"AMRLearn: Protocol for a machine learning pipeline for characterization of antimicrobial resistance determinants in microbial genomic data","volume":"6","year":"2025","journal-title":"STAR Protoc"},{"key":"2025102318001543000_2025.07.03.663053v2.23","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC920"},{"key":"2025102318001543000_2025.07.03.663053v2.24","doi-asserted-by":"publisher","DOI":"10.1093\/JAC\/DKAA345"},{"key":"2025102318001543000_2025.07.03.663053v2.25","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC1003"},{"key":"2025102318001543000_2025.07.03.663053v2.26","unstructured":"WHO Bacterial Priority Pathogens List 2024: Bacterial Pathogens of Public Health Importance, to Guide Research, Development, and Strategies to Prevent and Control Antimicrobial Resistance. (World Health Organization, Geneva, 2024)."},{"key":"2025102318001543000_2025.07.03.663053v2.27","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320212"},{"key":"2025102318001543000_2025.07.03.663053v2.28","unstructured":"WHO AWaRe (Access, Watch, Reserve) Classification of Antibiotics for Evaluation and Monitoring of Use. (2023)."},{"key":"2025102318001543000_2025.07.03.663053v2.29","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dky208"},{"key":"2025102318001543000_2025.07.03.663053v2.30","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02090-4"},{"key":"2025102318001543000_2025.07.03.663053v2.31","first-page":"3150","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","year":"2012","journal-title":"Bioinforma. Oxf. Engl"},{"key":"2025102318001543000_2025.07.03.663053v2.32","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1082"},{"key":"2025102318001543000_2025.07.03.663053v2.33","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae997"},{"key":"2025102318001543000_2025.07.03.663053v2.34","unstructured":"Kuhn, M. & Wickham, H. Tidymodels: a collection of packages for modeling and machine learning using tidyverse principles. (2020)."},{"key":"2025102318001543000_2025.07.03.663053v2.35","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"2025102318001543000_2025.07.03.663053v2.36","doi-asserted-by":"publisher","DOI":"10.32614\/rj-2020-013"},{"key":"2025102318001543000_2025.07.03.663053v2.37","unstructured":"Reference HMM Catalog - Pathogen Detection - NCBI. https:\/\/www.ncbi.nlm.nih.gov\/pathogens\/hmm\/."},{"key":"2025102318001543000_2025.07.03.663053v2.38","unstructured":"Sean R. E. HMMER: biosequence analysis using profile hidden Markov models. (2023)."},{"key":"2025102318001543000_2025.07.03.663053v2.39","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s13062-017-0198-x","article-title":"COGcollator: a web server for analysis of distant relationships between homologous protein families","volume":"12","year":"2017","journal-title":"Biol. Direct"},{"key":"2025102318001543000_2025.07.03.663053v2.40","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.3007087"},{"key":"2025102318001543000_2025.07.03.663053v2.41","unstructured":"Treatment of enterococcal infections - UpToDate. https:\/\/www.uptodate.com\/contents\/treatment-of-enterococcal-infections."},{"key":"2025102318001543000_2025.07.03.663053v2.42","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"2025102318001543000_2025.07.03.663053v2.43","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.bsheal.2023.01.001","article-title":"The prevalence and distribution of aminoglycoside resistance genes","volume":"05","year":"2023","journal-title":"Biosaf. Health"},{"key":"2025102318001543000_2025.07.03.663053v2.44","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAA1018"},{"key":"2025102318001543000_2025.07.03.663053v2.45","doi-asserted-by":"crossref","first-page":"2.6.13","DOI":"10.1128\/microbiolspec.PLAS-0020-2014","article-title":"Plasmid-Mediated Antimicrobial Resistance in Staphylococci and Other Firmicutes","volume":"2","year":"2014","journal-title":"Microbiol. Spectr"},{"key":"2025102318001543000_2025.07.03.663053v2.46","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1038\/s41396-023-01460-7","article-title":"Trimethoprim resistance in surface and wastewater is mediated by contrasting variants of the dfrB gene","volume":"17","year":"2023","journal-title":"ISME J"},{"key":"2025102318001543000_2025.07.03.663053v2.47","doi-asserted-by":"publisher","DOI":"10.1128\/AAC.00356-10"},{"key":"2025102318001543000_2025.07.03.663053v2.48","doi-asserted-by":"publisher","DOI":"10.1128\/MMBR.57.1.138-163.1993"},{"key":"2025102318001543000_2025.07.03.663053v2.49","doi-asserted-by":"publisher","DOI":"10.1038\/nrmicro2200"},{"key":"2025102318001543000_2025.07.03.663053v2.50","doi-asserted-by":"publisher","DOI":"10.1021\/acs.biochem.5b01269"},{"key":"2025102318001543000_2025.07.03.663053v2.51","first-page":"151","article-title":"Aminoglycoside modifying enzymes","volume":"13","year":"2010","journal-title":"Drug Resist. Updat. Rev. Comment. Antimicrob. Anticancer Chemother"},{"key":"2025102318001543000_2025.07.03.663053v2.52","doi-asserted-by":"crossref","unstructured":"Ghosh, A. , Vang, C. K. , Brenner, E. P. & Ravi, J. Unlocking antimicrobial resistance with multiomics and machine learning. Trends Microbiol. 0, (2025).","DOI":"10.1016\/j.tim.2025.04.017"},{"key":"2025102318001543000_2025.07.03.663053v2.53","doi-asserted-by":"crossref","unstructured":"Karnwal, A. et al. Addressing the global challenge of bacterial drug resistance: insights, strategies, and future directions. Front. Microbiol. 16, (2025).","DOI":"10.3389\/fmicb.2025.1517772"},{"key":"2025102318001543000_2025.07.03.663053v2.54","first-page":"e01082","article-title":"Genomics for antimicrobial resistance\u2014progress and future directions","volume":"69","year":"2025","journal-title":"Antimicrob. Agents Chemother"},{"key":"2025102318001543000_2025.07.03.663053v2.55","doi-asserted-by":"crossref","first-page":"105751","DOI":"10.1016\/j.ijmedinf.2024.105751","article-title":"A novel approach to antimicrobial resistance: Machine learning predictions for carbapenem-resistant Klebsiella in intensive care units","volume":"195","year":"2025","journal-title":"Int. J. Med. Inf"},{"key":"2025102318001543000_2025.07.03.663053v2.56","doi-asserted-by":"crossref","unstructured":"Gao, Y. et al. Machine learning and feature extraction for rapid antimicrobial resistance prediction of Acinetobacter baumannii from whole-genome sequencing data. Front. Microbiol. 14, (2024).","DOI":"10.3389\/fmicb.2023.1320312"},{"key":"2025102318001543000_2025.07.03.663053v2.57","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02089-5"},{"key":"2025102318001543000_2025.07.03.663053v2.58","doi-asserted-by":"crossref","first-page":"7.3.11","DOI":"10.1128\/microbiolspec.GPP3-0060-2019","article-title":"Staphylococcus aureus in Animals","volume":"7","year":"2019","journal-title":"Microbiol. Spectr"},{"key":"2025102318001543000_2025.07.03.663053v2.59","doi-asserted-by":"crossref","unstructured":"EFSA Panel on Animal Health and Welfare (AHAW) et al. Assessment of listing and categorisation of animal diseases within the framework of the Animal Health Law (Regulation (EU) No 2016\/429): antimicrobial-resistant Pseudomonas aeruginosa in dogs and cats. EFSA J. 20, (2022).","DOI":"10.2903\/j.efsa.2022.7310"},{"key":"2025102318001543000_2025.07.03.663053v2.60","doi-asserted-by":"publisher","DOI":"10.14202\/vetworld.2021.2155-2159"},{"key":"2025102318001543000_2025.07.03.663053v2.61","unstructured":"Antibiotics: useless medicines | Heinrich B\u00f6ll Stiftung | Brussels office - European Union. https:\/\/eu.boell.org\/en\/2021\/09\/07\/antibiotics-useless-medicines."},{"key":"2025102318001543000_2025.07.03.663053v2.62","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2014.04.007"},{"key":"2025102318001543000_2025.07.03.663053v2.63","doi-asserted-by":"crossref","first-page":"dlae127","DOI":"10.1093\/jacamr\/dlae127","article-title":"Navigating fluoroquinolone resistance in Gram-negative bacteria: a comprehensive evaluation","volume":"6","year":"2024","journal-title":"JAC-Antimicrob. Resist"},{"key":"2025102318001543000_2025.07.03.663053v2.64","doi-asserted-by":"publisher","DOI":"10.1038\/nm1347"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.03.663053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:04:58Z","timestamp":1768467898000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.07.03.663053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1101\/2025.07.03.663053","relation":{},"subject":[],"published":{"date-parts":[[2025,7,7]]},"subtype":"preprint"}}