{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T13:02:24Z","timestamp":1787749344182,"version":"build-2784847793"},"reference-count":50,"publisher":"American Association for the Advancement of Science (AAAS)","license":[{"start":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T00:00:00Z","timestamp":1712707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T00:00:00Z","timestamp":1712707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["csbj.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Comput Struct Biotechnol J"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:p>\n                    Diagnostic markers for myasthenia gravis (MG) are limited; thus, innovative approaches are required for supportive diagnosis and personalized care. Gut microbes are associated with MG pathogenesis; however, few studies have adopted machine learning (ML) to identify the associations among MG, gut microbiota, and metabolites. In this study, we developed an explainable ML model to predict biomarkers for MG diagnosis. We enrolled 19 MG patients and 10 non-MG individuals. Stool samples were collected and microbiome assessment was performed using 16S rRNA sequencing. Untargeted metabolic profiling was conducted to identify fecal amplicon significant variants (ASVs) and metabolites. We developed an explainable ML model in which the top ASVs and metabolites are combined to identify the best predictive performance. This model uses the SHapley Additive exPlanations method to generate both global and personalized explanations. Fecal microbe\u2013metabolite composition differed significantly between groups. The key bacterial families were\n                    <jats:italic toggle=\"yes\">Lachnospiraceae<\/jats:italic>\n                    and\n                    <jats:italic toggle=\"yes\">Ruminococcaceae<\/jats:italic>\n                    , and the top three features were\n                    <jats:italic toggle=\"yes\">Lachnospiraceae<\/jats:italic>\n                    , inosine, and methylhistidine. An ML model trained with the top 1\u00a0% ASVs and top 15\u00a0% metabolites combined outperformed all other models. Personalized explanations revealed different patterns of microbe\u2013metabolite contributions in patients with MG. The integration of the microbiota-metabolite features and the development of an explainable ML framework can accurately identify MG and provide personalized explanations, revealing the associations between gut microbiota, metabolites, and MG. An online calculator employing this algorithm was developed that provides a streamlined interface for MG diagnosis screening and conducting personalized evaluations.\n                  <\/jats:p>","DOI":"10.1016\/j.csbj.2024.04.025","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T11:39:00Z","timestamp":1712749140000},"page":"1572-1583","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":15,"title":["Explainable machine learning model for identifying key gut microbes and metabolites biomarkers associated with myasthenia gravis"],"prefix":"10.34133","volume":"23","author":[{"given":"Che-Cheng","family":"Chang","sequence":"first","affiliation":[{"name":"PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Department of Neurology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Graduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tzu-Chi","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi-Jie","family":"Lu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Department of Information Management, Fu Jen Catholic University, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hou-Chang","family":"Chiu","sequence":"additional","affiliation":[{"name":"School of Medicine, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Department of Neurology, Taipei Medical University, Shuang-Ho Hospital, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ning","family":"Lin","sequence":"additional","affiliation":[{"name":"PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City, Taiwan"},{"name":"Graduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","published-online":{"date-parts":[[2024,4,10]]},"reference":[{"key":"e_1_4_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(15)00145-3"},{"key":"e_1_4_1_3_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1602678"},{"key":"e_1_4_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(21)00297-0"},{"key":"e_1_4_1_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms12015"},{"key":"e_1_4_1_6_2","doi-asserted-by":"publisher","DOI":"10.1128\/mSystems.00188-17"},{"key":"e_1_4_1_7_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0188475"},{"key":"e_1_4_1_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/advs.201901441"},{"key":"e_1_4_1_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/nu14081647"},{"key":"e_1_4_1_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.803101"},{"key":"e_1_4_1_11_2","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.13567"},{"key":"e_1_4_1_12_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2020.564579"},{"key":"e_1_4_1_13_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2018.02627"},{"key":"e_1_4_1_14_2","doi-asserted-by":"publisher","DOI":"10.1515\/metgen-2016-0001"},{"key":"e_1_4_1_15_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv683"},{"key":"e_1_4_1_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/ismej.2011.82"},{"key":"e_1_4_1_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0405-7"},{"key":"e_1_4_1_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0458-7"},{"key":"e_1_4_1_19_2","doi-asserted-by":"crossref","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch W.J.","year":"2019","unstructured":"MurdochW.J.Definitions, methods, and applications in interpretable machine learningProc Natl Acad Sci1162019220712208031619572","journal-title":"Proc Natl Acad Sci"},{"key":"e_1_4_1_20_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12934-022-01973-4"},{"key":"e_1_4_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s43440-023-00489-x"},{"key":"e_1_4_1_22_2","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2023-330168"},{"key":"e_1_4_1_23_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2023.1227300"},{"key":"e_1_4_1_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2018.01556"},{"key":"e_1_4_1_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx449"},{"key":"e_1_4_1_26_2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14806\/ej.17.1.200","article-title":"Cutadapt removes adapter sequences from highthroughput sequencing reads","volume":"17","author":"Martin M.","year":"2011","unstructured":"Martin M. Cutadapt removes adapter sequences from highthroughput sequencing reads EMBnet J 17 2011 10 12","journal-title":"EMBnet J"},{"key":"e_1_4_1_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3869"},{"key":"e_1_4_1_28_2","doi-asserted-by":"crossref","unstructured":"Bokulich N. et al. Optimizing taxonomic classification of marker-gene amplicon sequences with QIIME 2\u2032s q2-feature-classifier plugin. Microbiome 6 1\u201317. doi: 10.1186. 2018 S40168\u2013018-0470-Z\/TABLES\/3.","DOI":"10.1186\/s40168-018-0470-z"},{"key":"e_1_4_1_29_2","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"Katoh K.","year":"2013","unstructured":"KatohK.StandleyD.M.MAFFT multiple sequence alignment software version 7: improvements in performance and usabilityMol Biol Evol30201377278023329690","journal-title":"Mol Biol Evol"},{"key":"e_1_4_1_30_2","unstructured":"Van Rossum G. Drake F.L. Python 3 reference manual: (python documentation manual part 2) 2009 CreateSpace Independent Publishing Platform"},{"key":"e_1_4_1_31_2","doi-asserted-by":"crossref","unstructured":"T. Kluyver\u00a0et al. Jupyter Notebooks - a publishing format for reproducible computational workflows in International Conference on Electronic 2016 Publishing .","DOI":"10.3233\/978-1-61499-649-1-87"},{"key":"e_1_4_1_32_2","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa F.","year":"2011","unstructured":"Pedregosa F. Scikit-learn: machine learning in python J Mach Learn Res 12 2011 2825 2830","journal-title":"J Mach Learn Res"},{"key":"e_1_4_1_33_2","first-page":"30","article-title":"A unified approach to interpreting model predictions","author":"Lundberg S.M.","year":"2017","unstructured":"Lundberg S.M. Lee S.-I. A unified approach to interpreting model predictions Adv Neural Inf Process Syst 2017 30","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_4_1_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gendis.2017.06.001"},{"key":"e_1_4_1_35_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2021.634511"},{"key":"e_1_4_1_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43705-022-00182-9"},{"key":"e_1_4_1_37_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2022.964921"},{"key":"e_1_4_1_38_2","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00579"},{"key":"e_1_4_1_39_2","unstructured":"E. Goel E. Abhilasha Random Forest: A Review. 2017."},{"key":"e_1_4_1_40_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/21-SS133","article-title":"Interpretable machine learning: fundamental principles and 10 grand challenges","volume":"16","author":"Rudin C.","year":"2022","unstructured":"Rudin C. Interpretable machine learning: fundamental principles and 10 grand challenges Stat Surv 16 2022 1 85","journal-title":"Stat Surv"},{"key":"e_1_4_1_41_2","article-title":"A unified approach to interpreting model predictions","author":"Lundberg S.M.","year":"2017","unstructured":"Lundberg S.M. Lee S.-I. A unified approach to interpreting model predictions ArXiv 2017 abs\/1705.07874.","journal-title":"ArXiv"},{"key":"e_1_4_1_42_2","doi-asserted-by":"crossref","first-page":"2000","DOI":"10.3390\/healthcare11142000","article-title":"Application of SHAP for explainable machine learning on age-based subgrouping mammography questionnaire data for positive mammography prediction and risk factor identification","volume":"11","author":"Sun J.","year":"2023","unstructured":"SunJ.Application of SHAP for explainable machine learning on age-based subgrouping mammography questionnaire data for positive mammography prediction and risk factor identificationHealthcare112023200037510441","journal-title":"Healthcare"},{"key":"e_1_4_1_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpcardiol.2022.101480"},{"key":"e_1_4_1_44_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-32700-y"},{"key":"e_1_4_1_45_2","doi-asserted-by":"publisher","DOI":"10.1161\/HYPERTENSIONAHA.120.15885"},{"key":"e_1_4_1_46_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1198469"},{"key":"e_1_4_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00281-014-0455-3"},{"key":"e_1_4_1_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cellsig.2016.02.010"},{"key":"e_1_4_1_49_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abc3421"},{"key":"e_1_4_1_50_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0125371"},{"key":"e_1_4_1_51_2","doi-asserted-by":"publisher","DOI":"10.3390\/antiox7030036"}],"container-title":["Computational and Structural Biotechnology Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2001037024001041?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2001037024001041?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.1016\/j.csbj.2024.04.025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T22:35:15Z","timestamp":1778279715000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.1016\/j.csbj.2024.04.025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,10]]},"references-count":50,"alternative-id":["10.1016\/j.csbj.2024.04.025"],"URL":"https:\/\/doi.org\/10.1016\/j.csbj.2024.04.025","relation":{},"ISSN":["2001-0370"],"issn-type":[{"value":"2001-0370","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explainable machine learning model for identifying key gut microbes and metabolites biomarkers associated with myasthenia gravis","name":"articletitle","label":"Article Title"},{"value":"Computational and Structural Biotechnology Journal","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csbj.2024.04.025","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology.","name":"copyright","label":"Copyright"}]}}