{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T11:59:54Z","timestamp":1792929594065,"version":"4.5.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"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. Pharmacol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This project aims to employ high-performance chemical isotope labeling (HP-CIL) liquid chromatography\u2013mass spectrometry (LC-MS) to conduct a metabolomic study on the mechanisms underlying intrinsic and idiosyncratic drug-induced liver injury (DILI). By comparing the metabolic characteristics between these two types of DILI, we seek to identify biomarkers for predicting intrinsic and idiosyncratic DILI using machine learning strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Based on the diagnostic criteria outlined in the EASL clinical practice guidelines on drug-induced liver injury, a review published in NEJM, enrolled DILI cases were classified according to the pathogenic mechanism into an intrinsic type (n = 17) and an idiosyncratic type (n = 27). Serum samples were collected from both groups. Metabolomic profiling was performed using high-performance chemical isotope labeling liquid chromatography\u2013mass spectrometry (HP-CIL LC-MS) to identify differentially expressed metabolites between the two groups. Metabolites that showed significance in both univariate and multivariate statistical analyses were selected for further receiver operating characteristic (ROC) analysis. Machine learning approaches were employed to develop diagnostic models for distinguishing intrinsic and idiosyncratic DILI. These models were compared to identify potential biomarkers capable of discriminating between the two types of DILI, and the diagnostic performance of these candidate biomarkers was evaluated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>Serum metabolomic profiling identified four differential metabolites that distinguished intrinsic from idiosyncratic DILI through multivariate and univariate statistical analyses, followed by ROC curve analysis and machine learning-based selection. These potential biomarkers included Alanyl-Glycine (level 1),N2-Acetyl-L-Cystathionine (level 2a), Isomer 1 of 5-Hydroxyindoleacetic acid (level 2a), and Isomer 1 of 5-Hydroxyindoleacetic acid (level 2a). ROC analysis using multiple machine learning models yielded area under the curve (AUC) values greater than 0.8 for all models, indicating high diagnostic performance. Under a multivariate regression model, internal cross-validation (CV) within the training set demonstrated robust model tuning and stability, with an AUC of 0.983. Holdout validation further confirmed model reliability with an AUC of 0.935. Metabolic pathway analysis of these metabolites revealed that the most significantly associated pathways affecting intrinsic and idiosyncratic DILI were primarily related to amino acid metabolism, including tryptophan metabolism, tyrosine metabolism, cysteine and methionine metabolism, and the biosynthesis of phenylalanine, tyrosine, and tryptophan.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates that machine learning-assisted serum metabolomics can effectively characterize currently well-established intrinsic and idiosyncratic drug-induced liver injury, reveal metabolic disparities between the two types, and identify differential metabolites associated with their respective pathogenesis. These findings provide a valuable reference for predicting the mechanistic type of liver injury induced by various hepatotoxic drugs in the future.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphar.2025.1727462","type":"journal-article","created":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:47:10Z","timestamp":1772207230000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning-assisted analysis of serum metabolomics for identifying biomarkers in intrinsic and idiosyncratic drug-induced liver injury"],"prefix":"10.3389","volume":"16","author":[{"given":"Xianni","family":"Wei","sequence":"first","affiliation":[{"name":"Department of Pharmacy, Haicang Hospital Affiliated to Xiamen Medical College","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbao","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Haicang Hospital Affiliated to Xiamen Medical College","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Haicang Hospital Affiliated to Xiamen Medical College","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Department of Pharmacy, Haicang Hospital Affiliated to Xiamen Medical College","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e0206389","DOI":"10.1371\/journal.pone.0206389","article-title":"Cytokine profiles in acute liver injury-results from the US drug-induced liver injury network (DILIN) and the acute liver failure study group","volume":"13","author":"Bonkovsky","year":"2018","journal-title":"PLoS One"},{"key":"B2","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1002\/hep.29802","article-title":"Candidate biomarkers for the diagnosis and prognosis of drug-induced liver injury: an international collaborative effort","volume":"69","author":"Church","year":"2019","journal-title":"Hepatology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"810","DOI":"10.14000\/j.cnki.issn.1008-1704.2015.10.002","article-title":"Guideline for the diagnosis and management of drug-induced liver injury","volume":"23","year":"2015","journal-title":"Chin. J. Hepatology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"64","DOI":"10.3138\/jammi-2022-0029","article-title":"Hepatotoxicity and tuberculosis treatment outcomes in chronic liver disease","volume":"8","author":"Edwards","year":"2023","journal-title":"J. Assoc. Med. Microbiol. Infect. Dis. Can."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1016\/j.jhep.2019.02.014","article-title":"EASL clinical practice guidelines: drug-induced liver injury","volume":"70","year":"2019","journal-title":"J. Hepatology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1002\/hep.32689","article-title":"AASLD practice guidance on drug, herbal, and dietary supplement-induced liver injury","volume":"77","author":"Fontana","year":"2023","journal-title":"Hepatology"},{"key":"B7","doi-asserted-by":"publisher","first-page":"27239","DOI":"10.1038\/srep27239","article-title":"A metabolomics cell-based approach for anticipating and investigating drug-induced liver injury","volume":"6","author":"Garc\u00eda-Ca\u00f1averas","year":"2016","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-1-4939-7592-1_14","article-title":"Chemical isotope labeling lc-ms for human blood metabolome analysis","volume":"1730","author":"Han","year":"2018","journal-title":"Methods Mol. Biol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"9979","DOI":"10.3390\/ijms22189979","article-title":"A novel UPLcMS\/MS method identifies organ-specific dipeptide profiles","volume":"22","author":"Heidenreich","year":"2021","journal-title":"Int. J. Mol. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1056\/NEJMra1816149","article-title":"Drug-induced liver injury - types and phenotypes","volume":"381","author":"Hoofnagle","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e512","DOI":"10.1002\/ctm2.512","article-title":"Prevotella contributes to individual response of FOLFOXin Colon cancer","volume":"11","author":"Hou","year":"2021","journal-title":"Clin. Transl. Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1080\/14737159.2018.1415145","article-title":"Mi R-122 and other micro RNAs as potential circulating biomarkers of drug-induced liver injury","volume":"18","author":"Howell","year":"2018","journal-title":"Expert Rev. Mol. Diagn"},{"key":"B13","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.jchromb.2014.08.011","article-title":"An effective assessment of valproate sodium-induced hepatotoxicity with UPLC-MS and 1HNMR-based metabonomics approach","volume":"969","author":"Huo","year":"2014","journal-title":"J. Chromatogr. B"},{"key":"B14","doi-asserted-by":"publisher","first-page":"S55","DOI":"10.4103\/jpbs.jpbs_568_25","article-title":"Drug-induced liver injury: mechanisms, diagnosis, and management: a review","volume":"17","author":"Keshari","year":"2025","journal-title":"J. Pharm. Bioallied Sci."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/toxsci\/kfab069","article-title":"Analytical and omics-based advances in the study of drug-induced liver injury","volume":"183","author":"Kralj","year":"2021","journal-title":"Toxicol. Sci."},{"key":"B16","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1053\/j.gastro.2019.03.020","article-title":"Tyrosine and glutamine-leucine are metabolic markers of early-stage colorectal cancers","volume":"157","author":"Li","year":"2019","journal-title":"Gastroen-terology"},{"key":"B17","first-page":"921","article-title":"Indirect drug-induced liver injury: new types and new challenges","volume":"47","author":"Li","year":"2024","journal-title":"Drug Eval. Res."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.3969\/j.issn.1001-5256.2023.08.007","article-title":"Guidelines for identification, management, and assessment of drug-induced liver injury in clinical trials","volume":"39","year":"2023","journal-title":"J. Clin. Hepatol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"442","DOI":"10.3390\/metabo10110442","article-title":"Comprehensive dipeptide analysis revealed cancer-specific profile in the liver of Pa-tients with HepatocellularCarcinoma and hepatitis","volume":"10","author":"Ozawa","year":"2020","journal-title":"Metabolites"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1007\/s00204-021-03114-z","article-title":"Metabolomic analysis to discriminate drug-induced liver injury (DILI) phenotypes","volume":"95","author":"Quint\u00e1s","year":"2021","journal-title":"Arch. Toxicol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1038\/s41436-021-01200-2","article-title":"Quantitative analysis of the natural history of prolidase deficieney:description of17 families and systematic review of published cases","volume":"23","author":"Rossignol","year":"2021","journal-title":"Genet. Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s00018-025-05744-3","article-title":"Mechanisms of drug induced liver injury","volume":"82","author":"Skat-Rordam","year":"2025","journal-title":"Cell Mol. Life Sci."},{"key":"B23","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1080\/1354750X.2016.1269131","article-title":"A longitudinal assessment of mi R-122 and GLDH as biomarkers of drug-induced liver injury in the rat","volume":"22","author":"Thulin","year":"2017","journal-title":"Biomarkers"},{"key":"B24","doi-asserted-by":"publisher","first-page":"422","DOI":"10.11778\/j.jdxb.2017.05.009","article-title":"Metabolite biomarkers of drug-induced liver injury","volume":"38","author":"Wang","year":"2017","journal-title":"J. Jinan Univ. Nat. Sci. Med. Ed."},{"key":"B25","doi-asserted-by":"publisher","first-page":"D622","DOI":"10.1093\/nar\/gkab1062","article-title":"HMDB 5.0: the human metabolome database for 2022","volume":"51","author":"Wishart","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2091","DOI":"10.1002\/rcm.6656","article-title":"Liquid chromatography\/massspectrometry methods for measuring dipeptide abundance in nonsmall-cell lung cancer","volume":"27","author":"Wu","year":"2013","journal-title":"Rapid Commun. Mass Spectrom."},{"key":"B27","doi-asserted-by":"publisher","first-page":"852","DOI":"10.3390\/metabo11120852","article-title":"Targeted metabolomics analysis of bile acids in patients with idiosyncratic drug-induced liver injury","volume":"11","author":"Xie","year":"2021","journal-title":"Metabolites"},{"key":"B28","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/s11306-011-0333-0","article-title":"Metabolic profiling of fifteen amino acids in serum of chemical-induced liver injured rats by hydrophilic interaction liquid chromatography coupled with tandem mass spectrometry","volume":"8","author":"Xu","year":"2012","journal-title":"Metabolomics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1054797","DOI":"10.1155\/2018\/1054797","article-title":"The tryptophan pathway targeting antioxi\u2010dant capacity in the placenta","volume":"2018","author":"Xu","year":"2018","journal-title":"Oxid. Med. Cell Longev."},{"key":"B30","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.tifs.2019.02.050","article-title":"Bioavailability of bioactive peptides derived from food proteins across the intestinal epithelialmembrane:a review","volume":"86","author":"Xu","year":"2019","journal-title":"Trends Food Sci. Tech."},{"key":"B31","first-page":"2515","article-title":"Pathogenesis of drug-induced liver injury: current understanding and future needs","volume":"37","author":"Yu","year":"2021","journal-title":"J. Clin. Hepatol."},{"key":"B32","first-page":"895","article-title":"The mechanisms of drug induced liver injury","volume":"37","author":"Yu","year":"2017","journal-title":"Chin. Hosp. Pharm. J."},{"key":"B33","doi-asserted-by":"publisher","first-page":"28","DOI":"10.3969\/j.issn.1674-7380.2019.04.003","article-title":"Research progress of amino acid metabolomics on drug-induced liver injury","volume":"11","author":"Zhao","year":"2019","journal-title":"Chin. J. Liver Dis. Electron. Version"},{"key":"B34","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1152\/physrev.00031.2024","article-title":"Ferroptosis: when metabolism meets cell death","volume":"105","author":"Zheng","year":"2025","journal-title":"Physiol. Rev."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2025.1727462\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:47:18Z","timestamp":1772207238000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2025.1727462\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":34,"alternative-id":["10.3389\/fphar.2025.1727462"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2025.1727462","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"article-number":"1727462"}}