{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:21:18Z","timestamp":1785392478264,"version":"3.55.0"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"IBM Computational Discovery Programme"},{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/T008784\/1"],"award-info":[{"award-number":["BB\/T008784\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S024093\/1"],"award-info":[{"award-number":["EP\/S024093\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013373","name":"NIHR Oxford Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013373","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"publisher","award":["NIHR207397"],"award-info":[{"award-number":["NIHR207397"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Microbiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Pyrazinamide is an important first-line antibiotic for treating tuberculosis, with resistance primarily driven by mutations in the\n                      <jats:italic>pncA<\/jats:italic>\n                      gene. Traditional machine learning models are able to predict pyrazinamide resistance with some success but are limited in their ability to incorporate 3-dimensional protein structural information. Graph neural networks offer the potential to integrate protein structure and residue-level features to better predict the impact of mutations on drug resistance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We trained a graph convolutional network on PncA variants containing missense mutations and evaluated its ability to classify resistance to pyrazinamide. Each PncA variant was represented as an amino acid-level graph, with edges calculated from 3-dimensional spatial proximity, and node features derived from chemical properties and mutation meta-predictors. We used AlphaFold2 to generate predicted structures of the PncA variants, which we used to create the protein graphs. The predicted structures of resistant PncA variants showed greater deviation from the wild-type structure compared to susceptible variants. Our model achieved an F1 score of 81.6%, sensitivity of 81.6% and specificity of 80.4% on the test set and either matched or exceeded the performance of a published set of traditional machine learning models. We show that both structural graph connectivity and node features contribute significantly to model performance. Furthermore, we employ additional train\/test dataset splits to demonstrate the GCN\u2019s ability to generalise and predict resistance in samples with mutations in unseen positions and structural regions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our study demonstrates that graph-based deep learning can leverage protein structure and biochemical features to accurately predict antimicrobial resistance, despite being trained on a small dataset with little variation. We present this as a proof-of-concept for these methods to be applied to resistance phenotype prediction in more genetically diverse pathogens to predict the more complex observed patterns of antimicrobial resistance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12866-026-04876-1","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T13:32:45Z","timestamp":1772544765000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting pyrazinamide resistance in Mycobacterium tuberculosis using a graph convolutional network"],"prefix":"10.1186","volume":"26","author":[{"given":"Dylan","family":"Dissanayake","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktoria","family":"Brunner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan","family":"Adlard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph A.","family":"Morrone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip W.","family":"Fowler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"issue":"7","key":"4876_CR1","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1179\/2047773215Y.0000000030","volume":"109","author":"F Prestinaci","year":"2015","unstructured":"Prestinaci F, Pezzotti P, Pantosti A. Antimicrobial resistance: a global multifaceted phenomenon. Pathogens Global Health. 2015;109(7):309\u201318. https:\/\/doi.org\/10.1179\/2047773215Y.0000000030.","journal-title":"Pathogens Global Health"},{"issue":"10","key":"4876_CR2","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.3390\/pathogens10101310","volume":"10","author":"G Mancuso","year":"2021","unstructured":"Mancuso G, Midiri A, Gerace E, Biondo C. Bacterial Antibiotic Resistance: The Most Critical Pathogens. Pathogens. 2021;10(10):1310. https:\/\/doi.org\/10.3390\/pathogens10101310.","journal-title":"Pathogens"},{"issue":"10325","key":"4876_CR3","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/S0140-6736(21)02724-0","volume":"399","author":"CJL Murray","year":"2022","unstructured":"Murray CJL, Ikuta KS, Sharara F, Swetschinski L, Aguilar GR, Gray A, et al. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. Lancet. 2022;399(10325):629\u201355. https:\/\/doi.org\/10.1016\/S0140-6736(21)02724-0.","journal-title":"Lancet"},{"key":"4876_CR4","unstructured":"World Health Organization. Global tuberculosis report 2023. Available from: https:\/\/www.who.int\/publications\/i\/item\/9789240083851."},{"issue":"3","key":"4876_CR5","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1016\/S1473-3099(17)30753-3","volume":"18","author":"E Tacconelli","year":"2018","unstructured":"Tacconelli E, Carrara E, Savoldi A, Harbarth S, Mendelson M, Monnet DL, et al. Discovery, research, and development of new antibiotics: the WHO priority list of antibiotic-resistant bacteria and tuberculosis. Lancet Infect Dis. 2018;18(3):318\u201327. https:\/\/doi.org\/10.1016\/S1473-3099(17)30753-3.","journal-title":"Lancet Infect Dis"},{"issue":"7","key":"4876_CR6","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1093\/jac\/dkr173","volume":"66","author":"PEA Almeida Da Silva","year":"2011","unstructured":"Almeida Da Silva PEA, Palomino JC. Molecular basis and mechanisms of drug resistance in Mycobacterium tuberculosis: classical and new drugs. J Antimicrob Chemother. 2011;66(7):1417\u201330. https:\/\/doi.org\/10.1093\/jac\/dkr173.","journal-title":"J Antimicrob Chemother"},{"issue":"1","key":"4876_CR7","doi-asserted-by":"publisher","first-page":"e20","DOI":"10.1016\/S2666-5247(22)00359-7","volume":"4","author":"S Bagcchi","year":"2023","unstructured":"Bagcchi S, WHO\u2019s Global Tuberculosis Report 2022. Lancet Microbe. 2023;4(1):e20. https:\/\/doi.org\/10.1016\/S2666-5247(22)00359-7.","journal-title":"Lancet Microbe"},{"key":"4876_CR8","unstructured":"World Health Organization. Global tuberculosis report 2024. ISBN: 978- 92-4-010153-1. Available from: https:\/\/www.who.int\/publications\/i\/item\/9789240101531."},{"issue":"6","key":"4876_CR9","doi-asserted-by":"publisher","first-page":"5202","DOI":"10.3390\/ijms24065202","volume":"24","author":"SSR Alsayed","year":"2023","unstructured":"Alsayed SSR, Gunosewoyo H, Tuberculosis. Pathogenesis, Current Treatment Regimens and New Drug Targets. Int J Mol Sci. 2023;24(6):5202. https:\/\/doi.org\/10.3390\/ijms24065202.","journal-title":"Int J Mol Sci"},{"issue":"58","key":"4876_CR10","doi-asserted-by":"publisher","first-page":"35565","DOI":"10.1039\/D0RA06072K","volume":"10","author":"A Ali","year":"2020","unstructured":"Ali A, Khan MT, Khan A, Ali S, Chinnasamy S, Akhtar K, et al. Pyrazinamide resistance of novel mutations in pncA and their dynamic behavior. RSC Adv. 2020;10(58):35565\u201373. https:\/\/doi.org\/10.1039\/D0RA06072K.","journal-title":"RSC Adv"},{"issue":"3","key":"4876_CR11","doi-asserted-by":"publisher","first-page":"491","DOI":"10.3201\/eid2303.161034","volume":"23","author":"S Allana","year":"2017","unstructured":"Allana S, Shashkina E, Mathema B, Bablishvili N, Tukvadze N, Shah NS, et al. pncA Gene Mutations Associated with Pyrazinamide Resistance in Drug-Resistant Tuberculosis, South Africa and Georgia. Emerg Infect Dis. 2017;23(3):491. https:\/\/doi.org\/10.3201\/eid2303.161034.","journal-title":"Emerg Infect Dis"},{"issue":"1","key":"4876_CR12","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1038\/s41598-020-58635-x","volume":"10","author":"M Karmakar","year":"2020","unstructured":"Karmakar M, Rodrigues CHM, Horan K, Denholm JT, Ascher DB. Structure guided prediction of Pyrazinamide resistance mutations in pncA. Sci Rep. 2020;10(1):1875. https:\/\/doi.org\/10.1038\/s41598-020-58635-x.","journal-title":"Sci Rep"},{"issue":"1","key":"4876_CR13","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1038\/s41467-017-00721-2","volume":"8","author":"AN Yadon","year":"2017","unstructured":"Yadon AN, Maharaj K, Adamson JH, Lai YP, Sacchettini JC, Ioerger TR, et al. A comprehensive characterization of PncA polymorphisms that confer resistance to pyrazinamide. Nat Commun. 2017;8(1):588. https:\/\/doi.org\/10.1038\/s41467-017-00721-2.","journal-title":"Nat Commun"},{"issue":"4","key":"4876_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1128\/microbiolspec.MGM2-0023-2013","volume":"2","author":"Y Zhang","year":"2013","unstructured":"Zhang Y, Shi W, Zhang W, Mitchison D. Mechanisms of Pyrazinamide Action and Resistance. Microbiol Spectr. 2013;2(4):1\u201312. https:\/\/doi.org\/10.1128\/microbiolspec.MGM2-0023-2013.","journal-title":"Microbiol Spectr"},{"issue":"6","key":"4876_CR15","doi-asserted-by":"publisher","first-page":"e02681","DOI":"10.1128\/AAC","volume":"63","author":"W Shi","year":"2019","unstructured":"Shi W, Cui P, Niu H, Zhang S, T\u00f8njum T, Zhu B, et al. Introducing RpsA Point Mutations \u2206438A and D123A into the Chromosome of Mycobacterium tuberculosis Confirms Their Role in Causing Resistance to Pyrazinamide. Antimicrob Agents Chemother. 2019;63(6):e02681\u201318. https:\/\/doi.org\/10.1128\/AAC.","journal-title":"Antimicrob Agents Chemother"},{"issue":"11","key":"4876_CR16","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1021\/acsinfecdis.7b00079","volume":"3","author":"P Gopal","year":"2017","unstructured":"Gopal P, Nartey W, Ragunathan P, Sarathy J, Kaya F, Yee M, et al. Pyrazinoic Acid Inhibits Mycobacterial Coenzyme A Biosynthesis by Binding to Aspartate Decarboxylase PanD. ACS Infect Dis. 2017;3(11):807\u201319. https:\/\/doi.org\/10.1021\/acsinfecdis.7b00079.","journal-title":"ACS Infect Dis"},{"issue":"2","key":"4876_CR17","doi-asserted-by":"publisher","first-page":"e02342","DOI":"10.1128\/AAC.02342-16","volume":"61","author":"M Yee","year":"2017","unstructured":"Yee M, Gopal P, Dick T. Missense Mutations in the Unfoldase ClpC1 of the Caseinolytic Protease Complex Are Associated with Pyrazinamide Resistance in Mycobacterium tuberculosis. Antimicrob Agents Chemother. 2017;61(2):e02342\u201316. https:\/\/doi.org\/10.1128\/AAC.02342-16.","journal-title":"Antimicrob Agents Chemother"},{"key":"4876_CR18","doi-asserted-by":"publisher","unstructured":"Zhang Y, Zhang J, Cui P, Zhang Y, Zhang W. Identification of Novel Efflux Proteins Rv0191, Rv3756c, Rv3008, and Rv1667c Involved in Pyrazinamide Resistance in Mycobacterium tuberculosis. Antimicrob Agents Chemother. 2017;61(8). https:\/\/doi.org\/10.1128\/aac.00940-17.","DOI":"10.1128\/aac.00940-17"},{"key":"4876_CR19","doi-asserted-by":"publisher","first-page":"102013","DOI":"10.1016\/j.tube.2020.102013","volume":"125","author":"PW Ei","year":"2020","unstructured":"Ei PW, Mon AS, Htwe MM, Win SM, Aye KT, San LL, et al. Pyrazinamide resistance and pncA mutations in drug resistant Mycobacterium tuberculosis clinical isolates from Myanmar. Tuberculosis. 2020;125:102013. https:\/\/doi.org\/10.1016\/j.tube.2020.102013.","journal-title":"Tuberculosis"},{"issue":"9","key":"4876_CR20","doi-asserted-by":"publisher","first-page":"4132","DOI":"10.3390\/cimb44090283","volume":"44","author":"D Shrestha","year":"2022","unstructured":"Shrestha D, Maharjan B, Thapa J, Akapelwa ML, Bwalya P, Chizimu JY, et al. Detection of Mutations in pncA in Mycobacterium tuberculosis Clinical Isolates from Nepal in Association with Pyrazinamide Resistance. Curr Issues Mol Biol. 2022;44(9):4132. https:\/\/doi.org\/10.3390\/cimb44090283.","journal-title":"Curr Issues Mol Biol"},{"issue":"1","key":"4876_CR21","doi-asserted-by":"publisher","first-page":"4628","DOI":"10.1038\/s41598-018-22883-9","volume":"8","author":"R Baddam","year":"2018","unstructured":"Baddam R, Kumar N, Wieler LH, Lankapalli AK, Ahmed N, Peacock SJ, et al. Analysis of mutations in pncA reveals non-overlapping patterns among various lineages of Mycobacterium tuberculosis. Sci Rep. 2018;8(1):4628. https:\/\/doi.org\/10.1038\/s41598-018-22883-9.","journal-title":"Sci Rep"},{"key":"4876_CR22","doi-asserted-by":"publisher","unstructured":"Cheng SJ, Thibert L, Sanchez T, Heifets L, Zhang Y. pncA Mutations as a Major Mechanism of Pyrazinamide Resistance in Mycobacterium tuberculosis: Spread of a Monoresistant Strain in Quebec, Canada. Antimicrob Agents Chemotherapy. 2000;44(3):528\u2013532. https:\/\/doi.org\/10.1128\/aac.44.3.528-532.","DOI":"10.1128\/aac.44.3.528-532"},{"issue":"7","key":"4876_CR23","doi-asserted-by":"publisher","first-page":"e0133869","DOI":"10.1371\/journal.pone.0133869","volume":"10","author":"MG Whitfield","year":"2015","unstructured":"Whitfield MG, Soeters HM, Warren RM, York T, Sampson SL, Streicher EM, et al. A Global Perspective on Pyrazinamide Resistance: Systematic Review and Meta-Analysis. PLoS ONE. 2015;10(7):e0133869. https:\/\/doi.org\/10.1371\/journal.pone.0133869.","journal-title":"PLoS ONE"},{"issue":"5","key":"4876_CR24","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.jiph.2018.04.005","volume":"11","author":"MT Zaw","year":"2018","unstructured":"Zaw MT, Emran NA, Lin Z. Mutations inside rifampicin-resistance determining region of rpoB gene associated with rifampicin-resistance in Mycobacterium tuberculosis. J Infect Public Health. 2018;11(5):605\u201310. https:\/\/doi.org\/10.1016\/j.jiph.2018.04.005.","journal-title":"J Infect Public Health"},{"issue":"5","key":"4876_CR25","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1128\/AAC.01691-09","volume":"54","author":"H Ando","year":"2010","unstructured":"Ando H, Kondo Y, Suetake T, Toyota E, Kato S, Mori T, et al. Identification of katG Mutations Associated with High-Level Isoniazid Resistance in Mycobacterium tuberculosis. Antimicrob Agents Chemother. 2010;54(5):1793\u20139. https:\/\/doi.org\/10.1128\/AAC.01691-09.","journal-title":"Antimicrob Agents Chemother"},{"issue":"1","key":"4876_CR26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/0263-7855(96)00018-5","volume":"14","author":"W Humphrey","year":"1996","unstructured":"Humphrey W, Dalke A, Schulten K. VMD: visual molecular dynamics. J Mol Graph. 1996;14(1):33\u20138.","journal-title":"J Mol Graph"},{"issue":"2","key":"4876_CR27","doi-asserted-by":"publisher","first-page":"dlae037","DOI":"10.1093\/jacamr\/dlae037","volume":"6","author":"JJ Carter","year":"2024","unstructured":"Carter JJ, Walker TM, Walker AS, Whitfield MG, Morlock GP, Lynch CI, et al. Prediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based machine-learning approaches. JAC-Antimicrobial Resist. 2024;6(2):dlae037. https:\/\/doi.org\/10.1093\/jacamr\/dlae037.","journal-title":"JAC-Antimicrobial Resist"},{"issue":"4","key":"4876_CR28","doi-asserted-by":"publisher","first-page":"e265","DOI":"10.1016\/S2666-5247(21)00301-3","volume":"3","author":"TM Walker","year":"2022","unstructured":"Walker TM, Miotto P, Koser CU, Fowler PW, Knaggs J, Iqbal Z, et al. The 2021\u00a8 WHO catalogue of Mycobacterium tuberculosis complex mutations associated with drug resistance: a genotypic analysis. Lancet Microbe. 2022;3(4):e265\u201373. https:\/\/doi.org\/10.1016\/S2666-5247(21)00301-3.","journal-title":"Lancet Microbe"},{"key":"4876_CR29","unstructured":"World Health Organization. Catalogue of mutations in Mycobacterium tuberculosis complex and their association with drug resistance, 2nd ed. ISBN: 978-92-4-008241-0. Available from: https:\/\/www.who.int\/publications-detail-redirect\/9789240082410"},{"issue":"8","key":"4876_CR30","doi-asserted-by":"publisher","first-page":"e3001721","DOI":"10.1371\/journal.pbio.3001721","volume":"20","author":"The CRyPTIC Consortium","year":"2022","unstructured":"The CRyPTIC Consortium. A data compendium associating the genomes of 12,289 Mycobacterium tuberculosis isolates with quantitative resistance phenotypes to 13 antibiotics. PLoS Biol. 2022;20(8):e3001721. https:\/\/doi.org\/10.1371\/journal.pbio.3001721.","journal-title":"PLoS Biol"},{"key":"4876_CR31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-06449-4","author":"X Kuang","year":"2022","unstructured":"Kuang X, Wang F, Hernandez KM, Zhang Z, Grossman RL. Accurate and rapid prediction of tuberculosis drug resistance from genome sequence data using traditional machine learning algorithms and CNN. Sci Rep. 2022;12(1):2427. https:\/\/doi.org\/10.1038\/s41598-022-06449-4."},{"issue":"13","key":"4876_CR32","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1093\/bioinformatics\/bty949","volume":"35","author":"S Kouchaki","year":"2019","unstructured":"Kouchaki S, Yang Y, Walker TM, Sarah Walker A, Wilson DJ, Peto TEA, et al. Application of machine learning techniques to tuberculosis drug resistance analysis. Bioinformatics. 2019;35(13):2276\u201382. https:\/\/doi.org\/10.1093\/bioinformatics\/bty949.","journal-title":"Bioinformatics"},{"key":"4876_CR33","unstructured":"World Health Organization. Catalogue of mutations in Mycobacterium tuberculosis complex and their association with drug resistance. 2021."},{"issue":"7553","key":"4876_CR34","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436\u201344. https:\/\/doi.org\/10.1038\/nature14539.","journal-title":"Nature"},{"key":"4876_CR35","doi-asserted-by":"publisher","unstructured":"Bronstein MM, Bruna J, LeCun Y, Szlam A, Vandergheynst P. Geometric Deep Learning: Going beyond Euclidean data. IEEE Signal Processing Magazine. 2017;34(4):18\u201342. Conference Name: IEEE Signal Processing Magazine. https:\/\/doi.org\/10.1109\/MSP.2017.2693418","DOI":"10.1109\/MSP.2017.2693418"},{"key":"4876_CR36","doi-asserted-by":"publisher","unstructured":"Kipf TN, Welling M. Semi-Supervised Classification with Graph Convolutional Networks. 2017;ArXiv:1609.02907. https:\/\/doi.org\/10.48550\/arXiv.1609.02907","DOI":"10.48550\/arXiv.1609.02907"},{"issue":"1","key":"4876_CR37","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","volume":"12","author":"V Gligorijevic","year":"2021","unstructured":"Gligorijevic V, Renfrew PD, Kosciolek T, Leman JK, Berenberg D, Vatanen T. Structure-based protein function prediction using graph convolutional networks. Nat Commun. 2021;12(1):3168. https:\/\/doi.org\/10.1038\/s41467-021-23303-9.","journal-title":"Nat Commun"},{"issue":"1","key":"4876_CR38","doi-asserted-by":"publisher","first-page":"16728","DOI":"10.1038\/s41598-022-21144-0","volume":"12","author":"J Com\u00b4\u0131n","year":"2022","unstructured":"Com\u00b4\u0131n J, Cebollada A, Samper S. Estimation of the mutation rate of Mycobacterium tuberculosis in cases with recurrent tuberculosis using whole genome sequencing. Sci Rep. 2022;12(1):16728. https:\/\/doi.org\/10.1038\/s41598-022-21144-0.","journal-title":"Sci Rep"},{"issue":"1","key":"4876_CR39","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s13073-025-01458-0","volume":"17","author":"Y Chen","year":"2025","unstructured":"Chen Y, Zhang X, Liang J, Jiang Q, Peierdun M, Xu P, et al. Advantages of updated WHO mutation catalog combined with existing wholegenome sequencing-based approaches for Mycobacterium tuberculosis resistance prediction. Genome Med. 2025;17(1):31. https:\/\/doi.org\/10.1186\/s13073-025-01458-0.","journal-title":"Genome Med"},{"issue":"10","key":"4876_CR40","doi-asserted-by":"publisher","first-page":"3686","DOI":"10.1128\/jcm.38.10.3686-3688.2000","volume":"38","author":"AP Davies","year":"2000","unstructured":"Davies AP, Billington OJ, McHugh TD, Mitchison DA, Gillespie SH. Comparison of Phenotypic and Genotypic Methods for Pyrazinamide Susceptibility Testing with Mycobacterium tuberculosis. J Clin Microbiol. 2000;38(10):3686\u20138. https:\/\/doi.org\/10.1128\/jcm.38.10.3686-3688.2000.","journal-title":"J Clin Microbiol"},{"key":"4876_CR41","doi-asserted-by":"publisher","unstructured":"Mok S, Roycroft E, Flanagan PR, Montgomery L, Borroni E, Rogers TR, et al. Overcoming the Challenges of Pyrazinamide Susceptibility Testing in Clinical Mycobacterium tuberculosis Isolates. Antimicrob Agents Chemother. 2021;65(8). https:\/\/doi.org\/10.1128\/aac.02617-20.","DOI":"10.1128\/aac.02617-20"},{"key":"4876_CR42","doi-asserted-by":"publisher","unstructured":"Harris J, Yadalam PK, Anegundi RV, Arumuganainar D, Harris J, Yadalam, Pk, et al. Comparing Graph Sample and Aggregation (SAGE) and Graph Attention Networks in the Prediction of Drug-Gene Associations of Extended-Spectrum Beta-Lactamases in Periodontal Infections and Resistance. Cureus. 2024;16(8). https:\/\/doi.org\/10.7759\/cureus.68082.","DOI":"10.7759\/cureus.68082"},{"key":"4876_CR43","doi-asserted-by":"publisher","unstructured":"Sielemann J, Sielemann K, Brejova B, Vina\u00b4 r T, Chauve C. \u02c7 plASgraph2: using graph neural networks to detect plasmid contigs from an assembly graph. Front Microbiol. 2023;14. https:\/\/doi.org\/10.3389\/fmicb.2023.1267695.","DOI":"10.3389\/fmicb.2023.1267695"},{"key":"4876_CR44","doi-asserted-by":"publisher","first-page":"e17729","DOI":"10.7717\/peerj.17729","volume":"12","author":"F Zhao","year":"2024","unstructured":"Zhao F, Qiu J, Xiang D, Jiao P, Cao Y, Xu Q, et al. deepAMPNet: a novel antimicrobial peptide predictor employing AlphaFold2 predicted structures and a bi-directional long short-term memory protein language model. PeerJ. 2024;12:e17729. https:\/\/doi.org\/10.7717\/peerj.17729.","journal-title":"PeerJ"},{"issue":"1","key":"4876_CR45","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/s41579-020-0416-x","volume":"19","author":"E Denamur","year":"2021","unstructured":"Denamur E, Clermont O, Bonacorsi S, Gordon D. The population genetics of pathogenic Escherichia coli. Nat Rev Microbiol. 2021;19(1):37\u201354. https:\/\/doi.org\/10.1038\/s41579-020-0416-x.","journal-title":"Nat Rev Microbiol"},{"key":"4876_CR46","unstructured":"Carter JJ, Fowler PW. predict-pyrazinamide-resistance. Available from: https:\/\/github.com\/fowler-lab\/predict-pyrazinamide-resistance."},{"issue":"6","key":"4876_CR47","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","volume":"19","author":"M Mirdita","year":"2022","unstructured":"Mirdita M, Schutze K, Moriwaki Y, Heo L, Ovchinnikov S, Steinegger M. Colab-\u00a8 Fold: making protein folding accessible to all. Nat Methods. 2022;19(6):679\u201382. https:\/\/doi.org\/10.1038\/s41592-022-01488-1.","journal-title":"Nat Methods"},{"issue":"7873","key":"4876_CR48","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583\u20139. https:\/\/doi.org\/10.1038\/s41586-021-03819-2.","journal-title":"Nature"},{"issue":"1","key":"4876_CR49","doi-asserted-by":"publisher","first-page":"e15785","DOI":"10.1371\/journal.pone.0015785","volume":"6","author":"S Petrella","year":"2011","unstructured":"Petrella S, Gelus-Ziental N, Maudry A, Laurans C, Boudjelloul R, Sougakoff W. Crystal Structure of the Pyrazinamidase of Mycobacterium tuberculosis: Insights into Natural and Acquired Resistance to Pyrazinamide. PLoS ONE. 2011;6(1):e15785. https:\/\/doi.org\/10.1371\/journal.pone.0015785.","journal-title":"PLoS ONE"},{"key":"4876_CR50","doi-asserted-by":"publisher","unstructured":"Fyfe PK, Rao VA, Zemla A, Cameron S, Hunter WN. Specificity and mechanism of acinetobacter baumanii nicotinamidase: Implications for activation of the front-line tuberculosis drug pyrazinamide. Angew Chem Int Ed. 2009;48(48). https:\/\/doi.org\/10.1002\/anie.200903407.","DOI":"10.1002\/anie.200903407"},{"key":"4876_CR51","unstructured":"Adlard D, Lynch C, Fowler PW. sbmlcore: a collection of core classes and functions for structure-based machine learning to predict antimicrobial resistance. Available from: https:\/\/github.com\/fowler-lab\/sbmlcore."},{"issue":"4","key":"4876_CR52","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1021\/acs.jcim.8b00697","volume":"59","author":"H Cao","year":"2019","unstructured":"Cao H, Wang J, He L, Qi Y, Zhang JZ. DeepDDG: Predicting the Stability Change of Protein Point Mutations Using Neural Networks. J Chem Inf Model. 2019;59(4):1508\u201314. https:\/\/doi.org\/10.1021\/acs.jcim.8b00697.","journal-title":"J Chem Inf Model"},{"key":"4876_CR53","doi-asserted-by":"publisher","first-page":"e82593","DOI":"10.7554\/eLife.82593","volume":"12","author":"LM Blaabjerg","year":"2023","unstructured":"Blaabjerg LM, Kassem MM, Good LL, Jonsson N, Cagiada M, Johansson KE, et al. Rapid protein stability prediction using deep learning representations. eLife. 2023;12:e82593. https:\/\/doi.org\/10.7554\/eLife.82593.","journal-title":"eLife"},{"issue":"7","key":"4876_CR54","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1101\/gr.3804205","volume":"15","author":"EA Stone","year":"2005","unstructured":"Stone EA, Sidow A. Physicochemical constraint violation by missense substitutions mediates impairment of protein function and disease severity. Genome Res. 2005;15(7):978\u201386. https:\/\/doi.org\/10.1101\/gr.3804205.","journal-title":"Genome Res"},{"issue":"8","key":"4876_CR55","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1186\/1471-2164-16-S8-S1","volume":"16","author":"M Hecht","year":"2015","unstructured":"Hecht M, Bromberg Y, Rost B. Better prediction of functional effects for sequence variants. BMC Genomics. 2015;16(8):S1. https:\/\/doi.org\/10.1186\/1471-2164-16-S8-S1.","journal-title":"BMC Genomics"},{"key":"4876_CR56","unstructured":"Fey M, Lenssen JE. Fast Graph Representation Learning with PyTorch Geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds; 2019."},{"key":"4876_CR57","unstructured":"Morris C, Ritzert M, Fey M, Hamilton WL, Lenssen JE, Rattan G et al. Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks. ArXiv:1810.02244. Available from: http:\/\/arxiv.org\/abs\/1810.02244."},{"key":"4876_CR58","unstructured":"Biewald L. Experiment Tracking with Weights and Biases. Software available from wandb.com. Available from: https:\/\/www.wandb.com\/."},{"key":"4876_CR59","doi-asserted-by":"publisher","unstructured":"Humphries RM, Ambler J, Mitchell SL, Castanheira M, Dingle T, Hindler JA, et al. CLSI Methods Development and Standardization Working Group Best Practices for Evaluation of Antimicrobial Susceptibility Tests. J Clin Microbiol. 2018;56(4). https:\/\/doi.org\/10.1128\/jcm.01934-17.","DOI":"10.1128\/jcm.01934-17"},{"key":"4876_CR60","doi-asserted-by":"crossref","unstructured":"S\u00f8gaard A, Ebert S, Bastings J, Filippova K. We Need To Talk About Random Splits. In: Merlo P, Tiedemann J, Tsarfaty R, editors. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Online: Association for Computational Linguistics; 2021. pp. 1823\u20131832. Available from: https:\/\/aclanthology.org\/2021.eacl-main.156\/.","DOI":"10.18653\/v1\/2021.eacl-main.156"},{"issue":"5","key":"4876_CR61","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1093\/bib\/bbv082","volume":"17","author":"I Walsh","year":"2016","unstructured":"Walsh I, Pollastri G, Tosatto SCE. Correct machine learning on protein sequences: a peer-reviewing perspective. Brief Bioinform. 2016;17(5):831\u201340. https:\/\/doi.org\/10.1093\/bib\/bbv082.","journal-title":"Brief Bioinform"},{"key":"4876_CR62","unstructured":"Wang Y, Zhang T, Guo X, Shen Z. Gradient based Feature Attribution in Explainable AI: A Technical Review. ArXiv:2403.10415. Available from: http: https:\/\/arxiv.org\/abs\/2403.10415."},{"key":"4876_CR63","unstructured":"Simonyan K, Vedaldi A, Zisserman A. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. ArXiv:1312.6034. Available from: http:\/\/arxiv.org\/abs\/1312.6034."},{"key":"4876_CR64","doi-asserted-by":"publisher","unstructured":"Khan MT, Ali S, Zeb MT, Kaushik AC, Malik SI, Wei DQ. Gibbs Free Energy Calculation of Mutation in PncA and RpsA Associated With Pyrazinamide Resistance. Front Mol Biosci. 2020;7. https:\/\/doi.org\/10.3389\/fmolb.2020.00052.","DOI":"10.3389\/fmolb.2020.00052"},{"key":"4876_CR65","doi-asserted-by":"publisher","first-page":"633365","DOI":"10.3389\/fmolb.2021.633365","volume":"8","author":"AS Nangraj","year":"2021","unstructured":"Nangraj AS, Khan A, Umbreen S, Sahar S, Arshad M, Younas S, et al. Insights Into Mutations Induced Conformational Changes and Rearrangement of Fe2+ Ion in pncA Gene of Mycobacterium tuberculosis to Decipher the Mechanism of Resistance to Pyrazinamide. Front Mol Biosci. 2021;8:633365. https:\/\/doi.org\/10.3389\/fmolb.2021.633365.","journal-title":"Front Mol Biosci"},{"issue":"8016","key":"4876_CR66","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A, et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature. 2024;630(8016):493\u2013500. https:\/\/doi.org\/10.1038\/s41586-024-07487-w.","journal-title":"Nature"},{"issue":"6736","key":"4876_CR67","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","volume":"387","author":"T Hayes","year":"2025","unstructured":"Hayes T, Rao R, Akin H, Sofroniew NJ, Oktay D, Lin Z, et al. Simulating 500 million years of evolution with a language model. Science. 2025;387(6736):850\u20138. https:\/\/doi.org\/10.1126\/science.ads0018.","journal-title":"Science"},{"key":"4876_CR68","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/j.csbj.2023.12.041","volume":"23","author":"C Jin","year":"2023","unstructured":"Jin C, Jia C, Hu W, Xu H, Shen Y, Yue M. Predicting antimicrobial resistance in E. coli with discriminative position fused deep learning classifier. Comput Struct Biotechnol J. 2023;23:559\u201365. https:\/\/doi.org\/10.1016\/j.csbj.2023.12.041.","journal-title":"Comput Struct Biotechnol J"},{"issue":"2","key":"4876_CR69","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.cmi.2016.09.008","volume":"23","author":"D Papaventsis","year":"2017","unstructured":"Papaventsis D, Casali N, Kontsevaya I, Drobniewski F, Cirillo DM, Nikolayevskyy V. Whole genome sequencing of Mycobacterium tuberculosis for detection of drug resistance: a systematic review. Clin Microbiol Infect. 2017;23(2):61\u20138. https:\/\/doi.org\/10.1016\/j.cmi.2016.09.008.","journal-title":"Clin Microbiol Infect"},{"issue":"3","key":"4876_CR70","doi-asserted-by":"publisher","first-page":"00952","DOI":"10.1183\/23120541.00952-2024","volume":"11","author":"CI Lynch","year":"2025","unstructured":"Lynch CI, Adlard D, Fowler PW. Predicting rifampicin resistance in Mycobacterium tuberculosis using machine learning informed by protein structural and chemical features. ERJ open Res. 2025;11(3):00952\u20132024. https:\/\/doi.org\/10.1183\/23120541.00952-2024.","journal-title":"ERJ open Res"},{"key":"4876_CR71","unstructured":"Dissanayake D, Fowler PW. tb-pnca-gnn: a graph convolutional neural network for predicting pyrazinamide resistance in Mycobacterium tuberculosis based on mutations in the pncA gene. Available from: https:\/\/github.com\/fowler-lab\/tb-pnca-gnn."}],"container-title":["BMC Microbiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12866-026-04876-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12866-026-04876-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12866-026-04876-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:14:41Z","timestamp":1781637281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12866-026-04876-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,3]]},"references-count":71,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["4876"],"URL":"https:\/\/doi.org\/10.1186\/s12866-026-04876-1","relation":{"references":[{"id-type":"doi","id":"10.1038\/s41598-022-06449-4","asserted-by":"subject"}]},"ISSN":["1471-2180"],"issn-type":[{"value":"1471-2180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,3]]},"assertion":[{"value":"29 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work used a published, open dataset as described in Methods and hence no ethics approval or consent to participate was required.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"PWF works as a consultant by the Ellison Institute of Technology, Oxford Ltd.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"319"}}