{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T15:27:17Z","timestamp":1791732437745,"version":"4.3.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013862","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000}}],"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["5R35GM143009"],"award-info":[{"award-number":["5R35GM143009"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Pancreatic ductal adenocarcinoma is one of the deadliest forms of cancer, presenting significant clinical challenges due to poor prognosis and limited treatment options. Understanding the metabolic reprogramming that drives this disease is crucial for identifying new therapeutic targets and improving patient outcomes. We developed a novel computational framework integrating genome-scale metabolic modeling with machine learning to identify metabolic signatures and therapeutic vulnerabilities in pancreatic cancer. To address the inherent class imbalance in cancer datasets, we generated synthetic healthy samples using a Wasserstein Generative Adversarial Network with Gradient Penalty, implementing a rigorous three-step biological filtration process to ensure their validity. This approach enabled the creation of a balanced dataset for robust comparison of healthy versus cancerous metabolic states. Our machine learning classifier achieved 94.83% accuracy in distinguishing between these states, demonstrating the effectiveness of our integrated approach. Systems-level analysis revealed three key dysregulated pathways: heparan sulfate degradation, O-glycan metabolism, and heme degradation. We identified impaired lysosomal degradation of heparan sulfate proteoglycans as a potential contributor to disease pathogenesis, providing a mechanistic explanation for the previously observed association between lysosomal storage disorders and pancreatic cancer. Additionally, nervonic acid transport emerged as the most discriminative reaction between healthy and cancerous states, with gene-level analysis highlighting fatty acid binding proteins, fatty acid transporters, and acyl-CoA synthetases as key molecular drivers of metabolic reprogramming. Our multi-level approach connected genetic drivers to functional metabolic consequences, revealing coordinated upregulation of fatty acid transport and activation processes. These findings enhance our understanding of pancreatic cancer metabolism and present potential therapeutic targets, demonstrating the value of integrated computational approaches in cancer research.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013862","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T19:01:25Z","timestamp":1767380485000},"page":"e1013862","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["GAN-enhanced machine learning and metabolic modeling identify reprogramming in pancreatic cancer"],"prefix":"10.1371","volume":"22","author":[{"given":"Tahereh","family":"Razmpour","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masoud","family":"Tabibian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0900-8768","authenticated-orcid":true,"given":"Arman","family":"Roohi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2974-0243","authenticated-orcid":true,"given":"Rajib","family":"Saha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"issue":"10242","key":"pcbi.1013862.ref001","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1016\/S0140-6736(20)30974-0","article-title":"Pancreatic cancer","volume":"395","author":"JD Mizrahi","year":"2020","journal-title":"Lancet"},{"issue":"1","key":"pcbi.1013862.ref002","doi-asserted-by":"crossref","first-page":"10","DOI":"10.14740\/wjon1166","article-title":"Epidemiology of Pancreatic Cancer: Global Trends, Etiology and Risk Factors","volume":"10","author":"P Rawla","year":"2019","journal-title":"World J Oncol"},{"issue":"13","key":"pcbi.1013862.ref003","doi-asserted-by":"crossref","first-page":"3423","DOI":"10.3390\/cancers15133423","article-title":"State-of-the-Art and Upcoming Innovations in Pancreatic Cancer Care: A Step Forward to Precision Medicine","volume":"15","author":"T Schepis","year":"2023","journal-title":"Cancers (Basel)"},{"issue":"2","key":"pcbi.1013862.ref004","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1038\/s43018-023-00697-7","article-title":"The Molecular Twin artificial-intelligence platform integrates multi-omic data to predict outcomes for pancreatic adenocarcinoma patients","volume":"5","author":"A Osipov","year":"2024","journal-title":"Nat Cancer"},{"issue":"6","key":"pcbi.1013862.ref005","doi-asserted-by":"crossref","first-page":"104483","DOI":"10.1016\/j.isci.2022.104483","article-title":"Exploring the metabolic landscape of pancreatic ductal adenocarcinoma cells using genome-scale metabolic modeling","volume":"25","author":"MM Islam","year":"2022","journal-title":"iScience"},{"issue":"12","key":"pcbi.1013862.ref006","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.3390\/cancers16122240","article-title":"Pancreatic Ductal Adenocarcinoma (PDAC): A Review of Recent Advancements Enabled by Artificial Intelligence","volume":"16","author":"A Mukund","year":"2024","journal-title":"Cancers (Basel)"},{"issue":"1","key":"pcbi.1013862.ref007","doi-asserted-by":"crossref","first-page":"15626","DOI":"10.1038\/s41598-021-95128-x","article-title":"A stacking ensemble deep learning approach to cancer type classification based on TCGA data","volume":"11","author":"M Mohammed","year":"2021","journal-title":"Sci Rep"},{"issue":"624","key":"pcbi.1013862.ref008","doi-asserted-by":"crossref","DOI":"10.1126\/scisignal.aaz1482","article-title":"An atlas of human metabolism","volume":"13","author":"JL Robinson","year":"2020","journal-title":"Sci Signal"},{"issue":"6352","key":"pcbi.1013862.ref009","doi-asserted-by":"crossref","DOI":"10.1126\/science.aan2507","article-title":"A pathology atlas of the human cancer transcriptome","volume":"357","author":"M Uhlen","year":"2017","journal-title":"Science"},{"issue":"24","key":"pcbi.1013862.ref010","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1093\/bioinformatics\/btq602","article-title":"iMAT: an integrative metabolic analysis tool","volume":"26","author":"H Zur","year":"2010","journal-title":"Bioinformatics"},{"issue":"3","key":"pcbi.1013862.ref011","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1002\/msb.145122","article-title":"Identification of anticancer drugs for hepatocellular carcinoma through personalized genome-scale metabolic modeling","volume":"10","author":"R Agren","year":"2014","journal-title":"Mol Syst Biol"},{"issue":"8","key":"pcbi.1013862.ref012","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000489","article-title":"Interpreting expression data with metabolic flux models: predicting Mycobacterium tuberculosis mycolic acid production","volume":"5","author":"C Colijn","year":"2009","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"pcbi.1013862.ref013","article-title":"E-Flux2 and SPOT: Validated Methods for Inferring Intracellular Metabolic Flux Distributions from Transcriptomic Data","volume":"11","author":"MK Kim","year":"2016","journal-title":"PLoS One"},{"issue":"12","key":"pcbi.1013862.ref014","doi-asserted-by":"crossref","first-page":"108400","DOI":"10.1016\/j.isci.2023.108400","article-title":"A multi-organ maize metabolic model connects temperature stress with energy production and reducing power generation","volume":"26","author":"NB Chowdhury","year":"2023","journal-title":"iScience"},{"issue":"6","key":"pcbi.1013862.ref015","first-page":"1218","article-title":"Seeing the wood for the trees: a forest of methods for optimization and omic-network integration in metabolic modelling","volume":"19","author":"S Vijayakumar","year":"2018","journal-title":"Brief Bioinform"},{"issue":"3","key":"pcbi.1013862.ref016","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1038\/nbt.1614","article-title":"What is flux balance analysis?","volume":"28","author":"JD Orth","year":"2010","journal-title":"Nat Biotechnol"},{"key":"pcbi.1013862.ref017","doi-asserted-by":"crossref","DOI":"10.1002\/9781119188902","volume-title":"Optimization methods in metabolic networks","author":"CD Maranas","year":"2016"},{"issue":"11","key":"pcbi.1013862.ref018","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.3390\/molecules29112594","article-title":"Identification of Anticancer Enzymes and Biomarkers for Hepatocellular Carcinoma through Constraint-Based Modeling","volume":"29","author":"F-S Wang","year":"2024","journal-title":"Molecules"},{"issue":"11","key":"pcbi.1013862.ref019","doi-asserted-by":"crossref","first-page":"4535","DOI":"10.3390\/molecules28114535","article-title":"Multi-Omics Analysis Revealed Increased De Novo Synthesis of Serine and Lower Activity of the Methionine Cycle in Breast Cancer Cell Lines","volume":"28","author":"M Pankevi\u010di\u016bt\u0117-Bukauskien\u0117","year":"2023","journal-title":"Molecules"},{"issue":"5","key":"pcbi.1013862.ref020","article-title":"Identifying essential genes in genome-scale metabolic models of consensus molecular subtypes of colorectal cancer","volume":"18","author":"C-T Cheng","year":"2023","journal-title":"PLoS One"},{"key":"pcbi.1013862.ref021","doi-asserted-by":"crossref","first-page":"103994","DOI":"10.1016\/j.compbiomed.2020.103994","article-title":"Genome-scale metabolic modelling predicts biomarkers and therapeutic targets for neuropsychiatric disorders","volume":"125","author":"STR Moolamalla","year":"2020","journal-title":"Comput Biol Med"},{"issue":"1","key":"pcbi.1013862.ref022","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1186\/s13059-024-03208-8","article-title":"Prediction of metabolites associated with somatic mutations in cancers by using genome-scale metabolic models and mutation data","volume":"25","author":"G Lee","year":"2024","journal-title":"Genome Biol"},{"key":"pcbi.1013862.ref023","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.ebiom.2019.03.009","article-title":"Discovery of therapeutic agents for prostate cancer using genome-scale metabolic modeling and drug repositioning","volume":"42","author":"B Turanli","year":"2019","journal-title":"EBioMedicine"},{"issue":"5","key":"pcbi.1013862.ref024","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1016\/j.cell.2015.05.019","article-title":"Using Genome-scale Models to Predict Biological Capabilities","volume":"161","author":"EJ O\u2019Brien","year":"2015","journal-title":"Cell"},{"issue":"4","key":"pcbi.1013862.ref025","doi-asserted-by":"crossref","first-page":"667","DOI":"10.3390\/sym12040667","article-title":"Pancreatic Cancer Early Detection Using Twin Support Vector Machine Based on Kernel","volume":"12","author":"W Sadewo","year":"2020","journal-title":"Symmetry"},{"issue":"5","key":"pcbi.1013862.ref026","article-title":"Identification of pancreatic cancer driver genes: Random forest modeling of principal components of scRNA-seq","volume":"5","author":"MJ Liang","year":"2023","journal-title":"Int J High School Res"},{"issue":"7","key":"pcbi.1013862.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007084","article-title":"Machine and deep learning meet genome-scale metabolic modeling","volume":"15","author":"G Zampieri","year":"2019","journal-title":"PLoS Comput Biol"},{"issue":"31","key":"pcbi.1013862.ref028","doi-asserted-by":"crossref","first-page":"18869","DOI":"10.1073\/pnas.2002959117","article-title":"A mechanism-aware and multiomic machine-learning pipeline characterizes yeast cell growth","volume":"117","author":"C Culley","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1013862.ref029","doi-asserted-by":"crossref","first-page":"3041","DOI":"10.1016\/j.csbj.2022.06.027","article-title":"Machine learning-guided evaluation of extraction and simulation methods for cancer patient-specific metabolic models","volume":"20","author":"SM Lee","year":"2022","journal-title":"Comput Struct Biotechnol J"},{"key":"pcbi.1013862.ref030","first-page":"3951","author":"M Tabibian","year":"2025"},{"issue":"1","key":"pcbi.1013862.ref031","doi-asserted-by":"crossref","first-page":"2700","DOI":"10.1038\/s41467-021-22989-1","article-title":"Integration of machine learning and genome-scale metabolic modeling identifies multi-omics biomarkers for radiation resistance","volume":"12","author":"JE Lewis","year":"2021","journal-title":"Nat Commun"},{"issue":"9","key":"pcbi.1013862.ref032","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He Haibo","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pcbi.1013862.ref033","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"pcbi.1013862.ref034","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1186\/1471-2105-14-106","article-title":"SMOTE for high-dimensional class-imbalanced data","volume":"14","author":"R Blagus","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1013862.ref035","doi-asserted-by":"crossref","first-page":"16498","DOI":"10.1109\/ACCESS.2024.3360215","article-title":"A GAN-Based Data Augmentation Method for Imbalanced Multi-Class Skin Lesion Classification","volume":"12","author":"Q Su","year":"2024","journal-title":"IEEE Access"},{"issue":"14","key":"pcbi.1013862.ref036","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1080\/10255842.2022.2134729","article-title":"Imbalanced medical disease dataset classification using enhanced generative adversarial network","volume":"26","author":"T Suresh","year":"2023","journal-title":"Comput Methods Biomech Biomed Engin"},{"issue":"1","key":"pcbi.1013862.ref037","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1186\/s12967-023-04549-x","article-title":"Genetic assessment of pathogenic germline alterations in lysosomal genes among Asian patients with pancreatic ductal adenocarcinoma","volume":"21","author":"Y Koh","year":"2023","journal-title":"J Transl Med"},{"key":"pcbi.1013862.ref038","doi-asserted-by":"crossref","DOI":"10.1055\/s-0041-1725066","volume-title":"Biology of the heparanase\u2013heparan sulfate axis and its role in disease pathogenesis","author":"I Vlodavsky","year":"2021"},{"key":"pcbi.1013862.ref039","doi-asserted-by":"crossref","first-page":"759376","DOI":"10.3389\/fonc.2021.759376","article-title":"The Metabolism Symbiosis Between Pancreatic Cancer and Tumor Microenvironment","volume":"11","author":"Y Li","year":"2021","journal-title":"Front Oncol"},{"issue":"10","key":"pcbi.1013862.ref040","doi-asserted-by":"crossref","first-page":"3919","DOI":"10.1073\/pnas.1219555110","article-title":"Strengthened glycolysis under hypoxia supports tumor symbiosis and hexosamine biosynthesis in pancreatic adenocarcinoma","volume":"110","author":"F Guillaumond","year":"2013","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"10","key":"pcbi.1013862.ref041","doi-asserted-by":"crossref","DOI":"10.1042\/BSR20220094","article-title":"O-glycosylation and its role in therapeutic proteins","volume":"42","author":"N Thompson","year":"2022","journal-title":"Biosci Rep"},{"key":"pcbi.1013862.ref042","doi-asserted-by":"crossref","first-page":"1093496","DOI":"10.3389\/fonc.2022.1093496","article-title":"The (Sialyl) Tn antigen: Contributions to immunosuppression in gastrointestinal cancers","volume":"12","author":"C Rajesh","year":"2023","journal-title":"Front Oncol"},{"issue":"3","key":"pcbi.1013862.ref043","doi-asserted-by":"crossref","first-page":"275","DOI":"10.3390\/ijms17030275","article-title":"The Role of Sialyl-Tn in Cancer","volume":"17","author":"J Munkley","year":"2016","journal-title":"Int J Mol Sci"},{"key":"pcbi.1013862.ref044","doi-asserted-by":"crossref","first-page":"18","DOI":"10.21037\/dmr.2020.04.04","article-title":"Chemotherapy in advanced pancreatic cancer with hyperbilirubinemia","volume":"3","author":"S Noventa","year":"2020","journal-title":"Dig Med Res"},{"issue":"1","key":"pcbi.1013862.ref045","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s43162-024-00298-5","article-title":"Bilirubin metabolism: delving into the cellular and molecular mechanisms to predict complications","volume":"36","author":"S Kumbhar","year":"2024","journal-title":"Egypt J Intern Med"},{"issue":"1","key":"pcbi.1013862.ref046","doi-asserted-by":"crossref","first-page":"14085","DOI":"10.1038\/s41598-020-71008-8","article-title":"C24:0 and C24:1 sphingolipids in cholesterol-containing, five- and six-component lipid membranes","volume":"10","author":"EJ Gonz\u00e1lez-Ram\u00edrez","year":"2020","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1013862.ref047","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1038\/s41416-019-0650-z","article-title":"Reprogramming of fatty acid metabolism in cancer","volume":"122","author":"N Koundouros","year":"2020","journal-title":"Br J Cancer"},{"issue":"4","key":"pcbi.1013862.ref048","doi-asserted-by":"crossref","first-page":"322","DOI":"10.2478\/jtim-2022-0022","article-title":"Oncogenic KRAS triggers metabolic reprogramming in pancreatic ductal adenocarcinoma","volume":"11","author":"X Shen","year":"2022","journal-title":"J Transl Int Med"},{"issue":"8","key":"pcbi.1013862.ref049","doi-asserted-by":"crossref","first-page":"10574","DOI":"10.1096\/fj.202000052R","article-title":"SREBP1 regulates mitochondrial metabolism in oncogenic KRAS expressing NSCLC","volume":"34","author":"CF Ruiz","year":"2020","journal-title":"FASEB J"},{"issue":"4","key":"pcbi.1013862.ref050","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.soard.2021.12.002","article-title":"Fatty acid binding protein 4 regulates pancreatic cancer cell proliferation via activation of nuclear factor E2-related factor 2","volume":"18","author":"K Wirth","year":"2022","journal-title":"Surg Obes Relat Dis"},{"issue":"5","key":"pcbi.1013862.ref051","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.3390\/ijms23052481","article-title":"Augmentation of Transcriptomic Data for Improved Classification of Patients with Respiratory Diseases of Viral Origin","volume":"23","author":"M Kircher","year":"2022","journal-title":"Int J Mol Sci"},{"key":"pcbi.1013862.ref052","doi-asserted-by":"crossref","DOI":"10.1101\/sqb.2011.76.010942","volume-title":"Regulation of glycolysis and gluconeogenesis by acetylation of PKM and PEPCK","author":"Y Xiong","year":"2011"},{"issue":"5","key":"pcbi.1013862.ref053","doi-asserted-by":"crossref","DOI":"10.1186\/gb-2006-7-5-r39","article-title":"Influence of metabolic network structure and function on enzyme evolution","volume":"7","author":"D Vitkup","year":"2006","journal-title":"Genome Biol"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013862","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:47:28Z","timestamp":1767815248000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013862"}},"subtitle":[],"editor":[{"given":"Sunil","family":"Laxman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013862","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.06.01.657244","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]}}}