{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T11:12:20Z","timestamp":1780917140711,"version":"3.54.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-23-IACL-0006"],"award-info":[{"award-number":["ANR-23-IACL-0006"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-23-CE12-0028-01"],"award-info":[{"award-number":["ANR-23-CE12-0028-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-23-CE14-0050-02"],"award-info":[{"award-number":["ANR-23-CE14-0050-02"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Minist\u00e8re de l'Enseignement sup\u00e9rieur, de la Recherche et de l'Espace)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We developed machine-learning models to predict isocitrate dehydrogenase (IDH) mutation status in acute myeloid leukemia (AML) from gene expression profiles and to reconstruct missing IDH annotations across public datasets. Transcriptomic data from 19 cohorts (5844 samples) were harmonized using batch correction, and 1546 samples with known IDH status were used to train a feed-forward neural network and a logistic regression (LR) classifier within a nested cross-validation framework, followed by independent validation in the TCGA-LAML dataset. The LR model showed superior performance, achieving receiver operating characteristic area under the curve\u00a0$=$ 0.994 $\\pm$ 0.007, accuracy $=$ 0.983 $\\pm$ 0.006, balanced accuracy $=$ 0.979 $\\pm$ 0.005, sensitivity for the IDH-mutant (IDH-MUT) class $=$ 0.972 $\\pm$ 0.010, and specificity $=$ 0.986 $\\pm$ 0.008, and correctly classified all IDH-MUT cases in the independent cohort. Applying the final model to samples lacking annotations enabled reconstruction of IDH status for 4148 AML cases, expanding the number of molecularly characterized transcriptomes available for downstream analyses. Predicted groups recapitulated known IDH-associated transcriptional signatures, supporting biological validity. This work demonstrates that IDH mutation status can be accurately inferred from transcriptomic data alone and provides a scalable framework to recover missing genomic annotations, thereby enhancing the utility of public AML resources for large-scale biological and translational research.<\/jats:p>","DOI":"10.1093\/nargab\/lqag058","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T11:44:05Z","timestamp":1780659845000},"source":"Crossref","is-referenced-by-count":0,"title":["Predicting isocitrate dehydrogenase mutation status in acute myeloid leukemia from gene expression profiles by machine learning"],"prefix":"10.1093","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1579-4982","authenticated-orcid":false,"given":"Ina","family":"Jung","sequence":"first","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8091-7673","authenticated-orcid":false,"given":"Anne-Laure","family":"Vitte","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6064-5183","authenticated-orcid":false,"given":"Florent","family":"Chuffart","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1790-1713","authenticated-orcid":false,"given":"Simon","family":"Chevalier","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]},{"name":"Universit\u00e9 Grenoble Alpes, CHU Grenoble Alpes, Department of Biological Hematology, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9674-5773","authenticated-orcid":false,"given":"Pascal","family":"Mossuz","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]},{"name":"Universit\u00e9 Grenoble Alpes, CHU Grenoble Alpes, Department of Biological Hematology, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0455-0857","authenticated-orcid":false,"given":"Saadi","family":"Khochbin","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5673-9045","authenticated-orcid":false,"given":"Ekaterina","family":"Bourova-Flin","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Grenoble Alpes, INSERM U1209, CNRS UMR 5309, Institute for Advanced Biosciences, 38000 , Grenoble ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"2026060806334171500_B1","doi-asserted-by":"publisher","first-page":"10208","DOI":"10.3389\/bjbs.2021.10208","article-title":"Isocitrate dehydrogenase IDH1 and IDH2 mutations in human cancer: prognostic implications for gliomas","volume":"79","author":"Murugan","year":"2022","journal-title":"Br J Biomed Sci"},{"key":"2026060806334171500_B2","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1038\/nature08617","article-title":"Cancer-associated IDH1 mutations produce 2-hydroxyglutarate","volume":"462","author":"Dang","year":"2009","journal-title":"Nature"},{"key":"2026060806334171500_B3","doi-asserted-by":"publisher","first-page":"3804","DOI":"10.1074\/jbc.M112.435495","article-title":"The potential for isocitrate dehydrogenase mutations to produce 2-hydroxyglutarate depends on allele specificity and subcellular compartmentalization","volume":"288","author":"Ward","year":"2013","journal-title":"J Biol Chem"},{"key":"2026060806334171500_B4","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.ccr.2010.11.015","article-title":"Leukemic IDH1 and IDH2 mutations result in a hypermethylation phenotype, disrupt TET2 function, and impair hematopoietic differentiation","volume":"18","author":"Figueroa","year":"2010","journal-title":"Cancer Cell"},{"key":"2026060806334171500_B5","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1016\/S0140-6736(18)31041-9","article-title":"Acute myeloid leukaemia","volume":"392","author":"Short","year":"2018","journal-title":"Lancet"},{"key":"2026060806334171500_B6","first-page":"17","article-title":"Cancer statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA Cancer J Clin"},{"key":"2026060806334171500_B7","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1309\/AJCPD7NR2RMNQDVF","article-title":"Acute myeloid leukemia with IDH1 or IDH2 mutation: frequency and clinicopathologic features","volume":"135","author":"Patel","year":"2011","journal-title":"Am J Clin Pathol"},{"key":"2026060806334171500_B8","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1182\/bloodadvances.2021004934","article-title":"Differential impact of IDH1\/2 mutational subclasses on outcome in adult AML: results from a large multicenter study","volume":"6","author":"Middeke","year":"2022","journal-title":"Blood Adv"},{"key":"2026060806334171500_B9","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1038\/leu.2015.91","article-title":"Clinical and biological implications of ancestral and non-ancestral IDH1 and IDH2 mutations in myeloid neoplasms","volume":"29","author":"Molenaar","year":"2015","journal-title":"Leukemia"},{"key":"2026060806334171500_B10","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1038\/s41408-021-00497-1","article-title":"Acute myeloid leukemia with IDH1 and IDH2 mutations: 2021 treatment algorithm","volume":"11","author":"Issa","year":"2021","journal-title":"Blood Cancer J"},{"key":"2026060806334171500_B11","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1182\/blood-2017-04-779405","article-title":"Enasidenib in mutant IDH2 relapsed or refractory acute myeloid leukemia","volume":"130","author":"Stein","year":"2017","journal-title":"Blood"},{"key":"2026060806334171500_B12","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1182\/blood.2022016867","article-title":"Diagnosis and management of AML in adults: 2022 recommendations from an international expert panel on behalf of the ELN","volume":"140","author":"D\u00f6hner","year":"2022","journal-title":"Blood"},{"key":"2026060806334171500_B13","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s12915-019-0670-4","article-title":"Exploiting metabolic vulnerabilities for personalized therapy in acute myeloid leukemia","volume":"17","author":"Stuani","year":"2019","journal-title":"BMC Biol"},{"key":"2026060806334171500_B14","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.trecan.2025.01.011","article-title":"Metabolism and therapeutic response in acute myeloid leukemia with IDH1\/2 mutations","volume":"11","author":"Gabellier","year":"2025","journal-title":"Trends Cancer"},{"key":"2026060806334171500_B15","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1038\/s41375-019-0387-y","article-title":"Data mining for mutation-specific targets in acute myeloid leukemia","volume":"33","author":"Benard","year":"2019","journal-title":"Leukemia"},{"key":"2026060806334171500_B16","first-page":"2876","article-title":"Genome-scale integrated analysis to identify prospective molecular mechanisms and therapeutic targets in isocitrate dehydrogenase 2 R140Q-mutated acute myeloid leukemia","volume":"41","author":"Huang","year":"2019","journal-title":"Oncol Rep"},{"key":"2026060806334171500_B17","doi-asserted-by":"publisher","first-page":"8946","DOI":"10.1038\/s41598-019-45346-1","article-title":"Methylation and transcription patterns are distinct in IDH mutant gliomas compared to other IDH mutant cancers","volume":"9","author":"Unruh","year":"2019","journal-title":"Sci Rep"},{"key":"2026060806334171500_B18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41598-021-04214-7","article-title":"Meta-analysis of whole-genome gene expression datasets assessing the effects of IDH1 and IDH2 mutations in isogenic disease models","volume":"12","author":"Schulten","year":"2022","journal-title":"Sci Rep"},{"key":"2026060806334171500_B19","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1093\/biostatistics\/4.2.249","article-title":"Exploration, normalization, and summaries of high density oligonucleotide array probe level data","volume":"4","author":"Irizarry","year":"2003","journal-title":"Biostatistics"},{"key":"2026060806334171500_B20","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/bioinformatics\/bts635","article-title":"STAR: ultrafast universal RNA-seq aligner","volume":"29","author":"Dobin","year":"2013","journal-title":"Bioinformatics"},{"key":"2026060806334171500_B21","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1093\/bioinformatics\/btu638","article-title":"HTSeq\u2013a Python framework to work with high-throughput sequencing data","volume":"31","author":"Anders","year":"2015","journal-title":"Bioinformatics"},{"key":"2026060806334171500_B22","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1186\/s12859-023-05578-5","article-title":"pyComBat, a Python tool for batch effects correction in high-throughput molecular data using empirical Bayes methods","volume":"24","author":"Behdenna","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"2026060806334171500_B23","doi-asserted-by":"publisher","first-page":"btac757","DOI":"10.1093\/bioinformatics\/btac757","article-title":"GSEApy: a comprehensive package for performing gene set enrichment analysis in Python","volume":"39","author":"Fang","year":"2023","journal-title":"Bioinformatics"},{"key":"2026060806334171500_B24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1186\/s12864-019-5546-z","article-title":"Architectures and accuracy of artificial neural network for disease classification from omics data","volume":"20","author":"Yu","year":"2019","journal-title":"BMC Genomics"},{"key":"2026060806334171500_B25","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1038\/ng1180","article-title":"PGC-1alpha-responsive genes involved in oxidative phosphorylation are coordinately downregulated in human diabetes","volume":"34","author":"Mootha","year":"2003","journal-title":"Nat Genet"},{"key":"2026060806334171500_B26","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026060806334171500_B27","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The Molecular Signatures Database (MSigDB) hallmark gene set collection","volume":"1","author":"Liberzon","year":"2015","journal-title":"Cell Syst"},{"key":"2026060806334171500_B28","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1038\/s41591-018-0115-6","article-title":"Clonal heterogeneity of acute myeloid leukemia treated with the IDH2 inhibitor enasidenib","volume":"24","author":"Quek","year":"2018","journal-title":"Nat Med"},{"key":"2026060806334171500_B29","doi-asserted-by":"publisher","first-page":"2675","DOI":"10.3390\/cancers16152675","article-title":"The leukemic isocitrate dehydrogenase (IDH) 1\/2 mutations impair myeloid and erythroid cell differentiation of primary human hematopoietic stem and progenitor cells (HSPCs)","volume":"16","author":"Pierangeli","year":"2024","journal-title":"Cancers (Basel)"},{"key":"2026060806334171500_B30","doi-asserted-by":"publisher","first-page":"2169","DOI":"10.1194\/jlr.M300285-JLR200","article-title":"IDH1 gene transcription is sterol regulated and activated by SREBP-1a and SREBP-2 in human hepatoma HepG2 cells: evidence that IDH1 may regulate lipogenesis in hepatic cells","volume":"44","author":"Shechter","year":"2003","journal-title":"J Lipid Res"},{"key":"2026060806334171500_B31","doi-asserted-by":"publisher","first-page":"3325","DOI":"10.3390\/ijms19113325","article-title":"Stable isotope labeling highlights enhanced fatty acid and lipid metabolism in human acute myeloid leukemia","volume":"19","author":"Stuani","year":"2018","journal-title":"Int J Mol Sci"},{"key":"2026060806334171500_B32","doi-asserted-by":"publisher","first-page":"967","DOI":"10.3390\/cells8090967","article-title":"Targeting metabolic reprogramming in acute myeloid leukemia","volume":"8","author":"Castro","year":"2019","journal-title":"Cells"},{"key":"2026060806334171500_B33","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1158\/2159-8290.CD-21-0218","article-title":"Dysregulated lipid synthesis by oncogenic IDH1 mutation is a targetable synthetic lethal vulnerability","volume":"13","author":"Thomas","year":"2023","journal-title":"Cancer Discov"},{"key":"2026060806334171500_B34","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1186\/s12967-021-03085-w","article-title":"Role of galectin 3 binding protein in cancer progression: a potential novel therapeutic target","volume":"19","author":"Capone","year":"2021","journal-title":"J Transl Med"},{"key":"2026060806334171500_B35","doi-asserted-by":"publisher","first-page":"e169830","DOI":"10.1172\/jci.insight.169830","article-title":"CD93 maintains endothelial barrier function and limits metastatic dissemination","volume":"9","author":"Vemuri","year":"2024","journal-title":"JCI Insight"},{"key":"2026060806334171500_B36","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1093\/biostatistics\/kxv027","article-title":"Methods that remove batch effects while retaining group differences may lead to exaggerated confidence in downstream analyses","volume":"17","author":"Nygaard","year":"2016","journal-title":"Biostatistics"},{"key":"2026060806334171500_B37","doi-asserted-by":"publisher","first-page":"e0202947","DOI":"10.1371\/journal.pone.0202947","article-title":"Comparison of statistical methods and the use of quality control samples for batch effect correction in human transcriptome data","volume":"13","author":"Esp\u00edn-P\u00e9rez","year":"2018","journal-title":"PLoS One"},{"key":"2026060806334171500_B38","doi-asserted-by":"publisher","first-page":"651317","DOI":"10.3389\/fcell.2021.651317","article-title":"The roles of 2-hydroxyglutarate","volume":"651317","author":"Du","year":"2021","journal-title":"Front Cell Dev Biol"}],"container-title":["NAR Genomics and Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nargab\/article-pdf\/8\/2\/lqag058\/68487637\/lqag058.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nargab\/article-pdf\/8\/2\/lqag058\/68487637\/lqag058.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:33:57Z","timestamp":1780914837000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nargab\/article\/doi\/10.1093\/nargab\/lqag058\/8703710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,27]]}},"URL":"https:\/\/doi.org\/10.1093\/nargab\/lqag058","relation":{},"ISSN":["2631-9268"],"issn-type":[{"value":"2631-9268","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,3,27]]},"article-number":"lqag058"}}