{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T11:13:57Z","timestamp":1772882037114,"version":"3.50.1"},"posted":{"date-parts":[[2025,3,20]]},"group-title":"Pharmacology and Therapeutics","reference-count":44,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T00:00:00Z","timestamp":1742428800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,3,20]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>\n                  Antimicrobial resistance poses a major global threat due to the diminishing efficacy of current treatments and limited new therapies. Combination therapy with existing drugs offers a promising solution, yet current empirical methods often lead to suboptimal efficacy and inadvertent toxicity. The high cost of experimentally testing numerous combinations underscores the need for data-driven methods to streamline treatment design. We introduce CALMA, an approach that predicts the potency and toxicity of multi-drug combinations in\n                  <jats:italic>Escherichia coli<\/jats:italic>\n                  and\n                  <jats:italic>Mycobacterium tuberculosis<\/jats:italic>\n                  . CALMA identified synergistic antimicrobial combinations involving vancomycin and isoniazid that were antagonistic for toxicity, which were validated using\n                  <jats:italic>in vitro<\/jats:italic>\n                  cell viability assays in human cell lines and through mining of patient health records that showed reduced side effects in patients taking combinations identified by CALMA. By combining mechanistic modelling with deep learning, CALMA improves the interpretability of neural networks, identifies key pathways influencing drug interactions, and prioritizes combinations with enhanced potency and reduced toxicity.\n                <\/jats:p>","DOI":"10.1101\/2025.03.19.25324270","type":"posted-content","created":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T15:45:40Z","timestamp":1742485540000},"source":"Crossref","is-referenced-by-count":2,"title":["A mechanistic neural network model predicts both potency and toxicity of antimicrobial combination therapies"],"prefix":"10.64898","author":[{"given":"Harkirat Singh","family":"Arora","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katherine","family":"Lev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Robida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramraj","family":"Velmurugan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8405-5708","authenticated-orcid":false,"given":"Sriram","family":"Chandrasekaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025032401511922000_2025.03.19.25324270v1.1","unstructured":"\u201cNew report calls for urgent action to avert antimicrobial resistance crisis.\u201d [Online]. Available: https:\/\/www.who.int\/news\/item\/29-04-2019-new-report-calls-for-urgent-action-to-avert-antimicrobial-resistance-crisis. [Accessed: 16-Mar-2025]."},{"key":"2025032401511922000_2025.03.19.25324270v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2012.12.006"},{"issue":"1","key":"2025032401511922000_2025.03.19.25324270v1.3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1111\/nyas.14649","article-title":"The future of antibiotics begins with discovering new combinations","volume":"1496","year":"2021","journal-title":"Ann. N. Y. Acad. Sci"},{"key":"2025032401511922000_2025.03.19.25324270v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41579-018-0141-x"},{"key":"2025032401511922000_2025.03.19.25324270v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41579-022-00700-5"},{"issue":"657","key":"2025032401511922000_2025.03.19.25324270v1.6","doi-asserted-by":"crossref","first-page":"eabo7793","DOI":"10.1126\/scitranslmed.abo7793","article-title":"The past, present, and future of antibiotics","volume":"14","year":"2022","journal-title":"Sci. Transl. Med"},{"key":"2025032401511922000_2025.03.19.25324270v1.7","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20156777"},{"key":"2025032401511922000_2025.03.19.25324270v1.8","doi-asserted-by":"crossref","unstructured":"S. Ma et al., \u201cTranscriptomic signatures predict regulators of drug synergy and clinical regimen efficacy against tuberculosis,\u201d MBio, vol. 10, no. 6, Nov. 2019.","DOI":"10.1128\/mBio.02627-19"},{"issue":"3","key":"2025032401511922000_2025.03.19.25324270v1.9","doi-asserted-by":"crossref","first-page":"gac132","DOI":"10.1093\/pnasnexus\/pgac132","article-title":"A flux-based machine learning model to simulate the impact of pathogen metabolic heterogeneity on drug interactions","volume":"1","year":"2022","journal-title":"PNAS Nexus"},{"key":"2025032401511922000_2025.03.19.25324270v1.10","unstructured":"D. Sun , \u201c90% of drugs fail clinical trials \u2013 here\u2019s one way researchers can select better drug candidates,\u201d The Conversation, 2022. [Online]. Available: http:\/\/theconversation.com\/90-of-drugs-fail-clinical-trials-heres-one-way-researchers-can-select-better-drug-candidates-174152. [Accessed: 16-Mar-2025]."},{"key":"2025032401511922000_2025.03.19.25324270v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2016.136"},{"key":"2025032401511922000_2025.03.19.25324270v1.12","doi-asserted-by":"publisher","DOI":"10.1053\/j.ackd.2019.08.001"},{"issue":"11","key":"2025032401511922000_2025.03.19.25324270v1.13","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1016\/j.ekir.2023.08.031","article-title":"Overview of antibiotic-induced nephrotoxicity","volume":"8","year":"2023","journal-title":"Kidney Int. Rep"},{"key":"2025032401511922000_2025.03.19.25324270v1.14","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2015.03.006"},{"key":"2025032401511922000_2025.03.19.25324270v1.15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.13766"},{"key":"2025032401511922000_2025.03.19.25324270v1.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2022.01.012"},{"issue":"9","key":"2025032401511922000_2025.03.19.25324270v1.17","doi-asserted-by":"crossref","first-page":"e1010402","DOI":"10.1371\/journal.pcbi.1010402","article-title":"A multi-label learning model for predicting drug-induced pathology in multi-organ based on toxicogenomics data","volume":"18","year":"2022","journal-title":"PLoS Comput. Biol"},{"issue":"51","key":"2025032401511922000_2025.03.19.25324270v1.18","doi-asserted-by":"crossref","first-page":"47536","DOI":"10.1021\/acsomega.2c05693","article-title":"Machine learning toxicity prediction: Latest advances by toxicity end point","volume":"7","year":"2022","journal-title":"ACS Omega"},{"issue":"9","key":"2025032401511922000_2025.03.19.25324270v1.19","doi-asserted-by":"crossref","first-page":"100565","DOI":"10.1016\/j.patter.2022.100565","article-title":"Knowledge-guided deep learning models of drug toxicity improve interpretation","volume":"3","year":"2022","journal-title":"Patterns (N. Y"},{"issue":"2","key":"2025032401511922000_2025.03.19.25324270v1.20","doi-asserted-by":"crossref","first-page":"100413","DOI":"10.1016\/j.crmeth.2023.100413","article-title":"Machine learning approaches to predict drug efficacy and toxicity in oncology","volume":"3","year":"2023","journal-title":"Cell Rep. Methods"},{"key":"2025032401511922000_2025.03.19.25324270v1.21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty294"},{"issue":"1","key":"2025032401511922000_2025.03.19.25324270v1.22","doi-asserted-by":"crossref","first-page":"15590","DOI":"10.1038\/s41598-022-19999-4","article-title":"Prediction of drug-drug interaction events using graph neural networks based feature extraction","volume":"12","year":"2022","journal-title":"Sci. Rep"},{"key":"2025032401511922000_2025.03.19.25324270v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/nrmicro1023"},{"key":"2025032401511922000_2025.03.19.25324270v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmet.2019.06.009"},{"key":"2025032401511922000_2025.03.19.25324270v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/msb.2011.65"},{"issue":"1","key":"2025032401511922000_2025.03.19.25324270v1.26","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s12918-018-0557-y","article-title":"Updated and standardized genome-scale reconstruction of Mycobacterium tuberculosis H37Rv, iEK1011, simulates flux states indicative of physiological conditions","volume":"12","year":"2018","journal-title":"BMC Syst. Biol"},{"key":"2025032401511922000_2025.03.19.25324270v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2010.11.052"},{"key":"2025032401511922000_2025.03.19.25324270v1.28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006677"},{"key":"2025032401511922000_2025.03.19.25324270v1.29","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.3003377"},{"key":"2025032401511922000_2025.03.19.25324270v1.30","doi-asserted-by":"publisher","DOI":"10.1021\/acschembio.9b00565"},{"issue":"3","key":"2025032401511922000_2025.03.19.25324270v1.31","doi-asserted-by":"crossref","first-page":"e0295136","DOI":"10.1371\/journal.pone.0295136","article-title":"Vancomycin nephrotoxicity: A comprehensive clinico-pathological study","volume":"19","year":"2024","journal-title":"PLoS One"},{"key":"2025032401511922000_2025.03.19.25324270v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/S0149-2918(96)80179-2"},{"key":"2025032401511922000_2025.03.19.25324270v1.33","doi-asserted-by":"publisher","DOI":"10.4065\/74.6.613"},{"key":"2025032401511922000_2025.03.19.25324270v1.34","unstructured":"\u201cIsoniazid,\u201d in LiverTox: Clinical and Research Information on Drug-Induced Liver Injury, Bethesda (MD): National Institute of Diabetes and Digestive and Kidney Diseases, 2012."},{"key":"2025032401511922000_2025.03.19.25324270v1.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2022.01.004"},{"key":"2025032401511922000_2025.03.19.25324270v1.36","doi-asserted-by":"publisher","DOI":"10.1038\/nature25979"},{"key":"2025032401511922000_2025.03.19.25324270v1.37","doi-asserted-by":"publisher","DOI":"10.1128\/AAC.00832-12"},{"key":"2025032401511922000_2025.03.19.25324270v1.38","doi-asserted-by":"crossref","unstructured":"M. M. Reuter et al., \u201cUltra-high-throughput screening of antimicrobial combination therapies using a two-stage transparent machine learning model,\u201d bioRxivorg, p. 2024.11.25.625231, 25-Nov-2024.","DOI":"10.1101\/2024.11.25.625231"},{"key":"2025032401511922000_2025.03.19.25324270v1.39","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa1005"},{"key":"2025032401511922000_2025.03.19.25324270v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1487"},{"key":"2025032401511922000_2025.03.19.25324270v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq602"},{"key":"2025032401511922000_2025.03.19.25324270v1.42","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1661-z"},{"key":"2025032401511922000_2025.03.19.25324270v1.43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-9224-9_14"},{"key":"2025032401511922000_2025.03.19.25324270v1.44","unstructured":"release-notes\/v0.1.md at master \u00b7 tatonetti-lab\/nsides-release. Github."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.03.19.25324270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:31:29Z","timestamp":1768509089000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.03.19.25324270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,20]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1101\/2025.03.19.25324270","relation":{},"subject":[],"published":{"date-parts":[[2025,3,20]]},"subtype":"preprint"}}