{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T01:19:24Z","timestamp":1767921564901,"version":"3.49.0"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"20","license":[{"start":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T00:00:00Z","timestamp":1620691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"UKRI Research England\u2019s THYME project"},{"name":"Children\u2019s Liver Disease Foundation Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,25]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>High-throughput biological data, thanks to technological advances, have become cheaper to collect, leading to the availability of vast amounts of omic data of different types. In parallel, the in silico reconstruction and modeling of metabolic systems is now acknowledged as a key tool to complement experimental data on a large scale. The integration of these model- and data-driven information is therefore emerging as a new challenge in systems biology, with no clear guidance on how to better take advantage of the inherent multisource and multiomic nature of these data types while preserving mechanistic interpretation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Here, we investigate different regularization techniques for high-dimensional data derived from the integration of gene expression profiles with metabolic flux data, extracted from strain-specific metabolic models, to improve cellular growth rate predictions. To this end, we propose ad-hoc extensions of previous regularization frameworks including group, view-specific and principal component regularization and experimentally compare them using data from 1143 Saccharomyces cerevisiae strains. We observe a divergence between methods in terms of regression accuracy and integration effectiveness based on the type of regularization employed. In multiomic regression tasks, when learning from experimental and model-generated omic data, our results demonstrate the competitiveness and ease of interpretation of multimodal regularized linear models compared to data-hungry methods based on neural networks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>All data, models and code produced in this work are available on GitHub at https:\/\/github.com\/Angione-Lab\/HybridGroupIPFLasso_pc2Lasso.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab324","type":"journal-article","created":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T03:23:42Z","timestamp":1619580222000},"page":"3546-3552","source":"Crossref","is-referenced-by-count":26,"title":["Multimodal regularized linear models with flux balance analysis for mechanistic integration of omics data"],"prefix":"10.1093","volume":"37","author":[{"given":"Giuseppe","family":"Magazz\u00f9","sequence":"first","affiliation":[{"name":"School of Computing, Engineering and Digital Technologies, Teesside University , Middlesbrough, UK"}]},{"given":"Guido","family":"Zampieri","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Digital Technologies, Teesside University , Middlesbrough, UK"},{"name":"Department of Biology, University of Padova , Padova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3140-7909","authenticated-orcid":false,"given":"Claudio","family":"Angione","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Digital Technologies, Teesside University , Middlesbrough, UK"},{"name":"Healthcare Innovation Centre, Teesside University , Middlesbrough, UK"},{"name":"Centre for Digital Innovation, Teesside University , Middlesbrough, UK"}]}],"member":"286","published-online":{"date-parts":[[2021,5,11]]},"reference":[{"key":"2023051609042392600_btab324-B1","doi-asserted-by":"crossref","first-page":"e1000257","DOI":"10.1371\/journal.pcbi.1000257","article-title":"Predicting cellular growth from gene expression signatures","volume":"5","author":"Airoldi","year":"2009","journal-title":"PLoS Comput. Biol"},{"key":"2023051609042392600_btab324-B2","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1093\/bioinformatics\/btx562","article-title":"Integrating splice-isoform expression into genome-scale models characterizes breast cancer metabolism","volume":"34","author":"Angione","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051609042392600_btab324-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2017\/7691937","article-title":"Ipf-lasso: integrative-penalized regression with penalty factors for prediction based on multi-omics data","volume":"2017","author":"Boulesteix","year":"2017","journal-title":"Comput. Math. Methods Med"},{"key":"2023051609042392600_btab324-B4","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-030-13035-0_5","article-title":"Yeast genome-scale metabolic models for simulating genotype\u2013phenotype relations","volume":"58","author":"Castillo","year":"2019","journal-title":"Prog. Mol. Subcell. Biol"},{"key":"2023051609042392600_btab324-B5","doi-asserted-by":"crossref","first-page":"536","DOI":"10.3390\/metabo5040536","article-title":"Using gene essentiality and synthetic lethality information to correct yeast and CHO cell genome-scale models","volume":"5","author":"Chowdhury","year":"2015","journal-title":"Metabolites"},{"key":"2023051609042392600_btab324-B6","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":"Culley","year":"2020","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051609042392600_btab324-B7","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1002\/biot.201300138","article-title":"Predicting complex phenotype\u2013genotype interactions to enable yeast engineering: Saccharomyces cerevisiae as a model organism and a cell factory","volume":"8","author":"Dikicioglu","year":"2013","journal-title":"Biotechnol. J"},{"key":"2023051609042392600_btab324-B8","doi-asserted-by":"crossref","first-page":"5843","DOI":"10.1128\/jb.179.18.5843-5848.1997","article-title":"Regulation of yeast phospholipid biosynthetic genes in phosphatidylserine decarboxylase mutants","volume":"179","author":"Griac","year":"1997","journal-title":"J. Bacteriol"},{"key":"2023051609042392600_btab324-B9","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1038\/s41596-018-0098-2","article-title":"Creation and analysis of biochemical constraint-based models using the cobra toolbox v. 3.0","volume":"14","author":"Heirendt","year":"2019","journal-title":"Nat. Protoc"},{"key":"2023051609042392600_btab324-B10","doi-asserted-by":"crossref","first-page":"3395","DOI":"10.1016\/j.patcog.2013.06.014","article-title":"Roc curves for regression","volume":"46","author":"Hern\u00e1ndez-Orallo","year":"2013","journal-title":"Pattern Recognit"},{"key":"2023051609042392600_btab324-B11","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1016\/j.cell.2014.02.054","article-title":"Large-scale genetic perturbations reveal regulatory networks and an abundance of gene-specific repressors","volume":"157","author":"Kemmeren","year":"2014","journal-title":"Cell"},{"key":"2023051609042392600_btab324-B12","doi-asserted-by":"crossref","first-page":"13090","DOI":"10.1038\/ncomms13090","article-title":"Multi-omics integration accurately predicts cellular state in unexplored conditions for Escherichia coli","volume":"7","author":"Kim","year":"2016","journal-title":"Nat. Commun"},{"key":"2023051609042392600_btab324-B13","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1111\/j.1432-1033.1989.tb15109.x","article-title":"Characterization of the methyltransferases in the yeast phosphatidylethanolamine methylation pathway by selective gene disruption","volume":"185","author":"Kodaki","year":"1989","journal-title":"Eur. J. Biochem"},{"key":"2023051609042392600_btab324-B14","doi-asserted-by":"crossref","first-page":"5795","DOI":"10.1016\/S0021-9258(17)38452-1","article-title":"Phosphatidylserine biosynthesis in cultured Chinese hamster ovary cells. III. Genetic evidence for utilization of phosphatidylcholine and phosphatidylethanolamine as precursors","volume":"261","author":"Kuge","year":"1986","journal-title":"J. Biol. Chem"},{"key":"2023051609042392600_btab324-B15","first-page":"325","article-title":"A review on machine learning principles for multi-view biological data integration","volume":"19","author":"Li","year":"2016","journal-title":"Brief. Bioinform"},{"key":"2023051609042392600_btab324-B16","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.ymben.2018.04.011","article-title":"Recent advances in metabolic engineering of Saccharomyces cerevisiae: new tools and their applications","volume":"50","author":"Lian","year":"2018","journal-title":"Metab. Eng"},{"key":"2023051609042392600_btab324-B17","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1109\/TCBB.2014.2377729","article-title":"Integrative data analysis of multi-platform cancer data with a multimodal deep learning approach","volume":"12","author":"Liang","year":"2014","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"2023051609042392600_btab324-B18","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nrg3920","article-title":"Machine learning applications in genetics and genomics","volume":"16","author":"Libbrecht","year":"2015","journal-title":"Nat. Rev. Genet"},{"key":"2023051609042392600_btab324-B19","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1093\/bioinformatics\/btz781","article-title":"Exploiting transfer learning for the reconstruction of the human gene regulatory network","volume":"36","author":"Mignone","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051609042392600_btab324-B20","doi-asserted-by":"crossref","first-page":"732","DOI":"10.15252\/msb.20145172","article-title":"Cell cycle population effects in perturbation studies","volume":"10","author":"O\u2019Duibhir","year":"2014","journal-title":"Mol. Syst. Biol"},{"key":"2023051609042392600_btab324-B21","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.cels.2016.03.001","article-title":"Metabolic network prediction of drug side effects","volume":"2","author":"Shaked","year":"2016","journal-title":"Cell Syst"},{"key":"2023051609042392600_btab324-B22","doi-asserted-by":"crossref","first-page":"i501","DOI":"10.1093\/bioinformatics\/btz318","article-title":"Moli: multi-omics late integration with deep neural networks for drug response prediction","volume":"35","author":"Sharifi-Noghabi","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051609042392600_btab324-B23","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/j.cell.2013.06.041","article-title":"Methionine inhibits autophagy and promotes growth by inducing the SAM-responsive methylation of PP2A","volume":"154","author":"Sutter","year":"2013","journal-title":"Cell"},{"key":"2023051609042392600_btab324-B24","article-title":"Principal component-guided sparse regression","author":"Tay","year":"2018","journal-title":"arXiv:1810.04651"},{"key":"2023051609042392600_btab324-B25","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J. R. Stat. Soc. B"},{"key":"2023051609042392600_btab324-B26","doi-asserted-by":"crossref","first-page":"101818","DOI":"10.1016\/j.isci.2020.101818","article-title":"A hybrid flux balance analysis and machine learning pipeline elucidates metabolic adaptation in cyanobacteria","volume":"23","author":"Vijayakumar","year":"2020","journal-title":"iScience"},{"key":"2023051609042392600_btab324-B27","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1073\/pnas.1808080116","article-title":"Predicting growth rate from gene expression","volume":"116","author":"Wytock","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051609042392600_btab324-B28","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1186\/s12859-018-2383-z","article-title":"The poly-omics of ageing through individual-based metabolic modelling","volume":"19","author":"Yaneske","year":"2018","journal-title":"BMC Bioinform"},{"key":"2023051609042392600_btab324-B29","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1016\/j.cell.2019.04.016","article-title":"A white-box machine learning approach for revealing antibiotic mechanisms of action","volume":"177","author":"Yang","year":"2019","journal-title":"Cell"},{"key":"2023051609042392600_btab324-B30","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1002\/yea.1823","article-title":"A novel mechanism regulates H2S and SO2 production in Saccharomyces cerevisiae","volume":"28","author":"Yoshida","year":"2011","journal-title":"Yeast"},{"key":"2023051609042392600_btab324-B31","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1111\/j.1467-9868.2005.00532.x","article-title":"Model selection and estimation in regression with grouped variables","volume":"68","author":"Yuan","year":"2006","journal-title":"J. R. Stat. Soc. B"},{"key":"2023051609042392600_btab324-B32","doi-asserted-by":"crossref","first-page":"e1007084","DOI":"10.1371\/journal.pcbi.1007084","article-title":"Machine and deep learning meet genome-scale metabolic modeling","volume":"15","author":"Zampieri","year":"2019","journal-title":"PLoS Comput. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab324\/38377683\/btab324.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/20\/3546\/50338621\/btab324.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/20\/3546\/50338621\/btab324.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T16:44:06Z","timestamp":1724949846000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/20\/3546\/6273576"}},"subtitle":[],"editor":[{"given":"Nobuhide","family":"Doi","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,5,11]]},"references-count":32,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2021,10,25]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab324","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10,15]]},"published":{"date-parts":[[2021,5,11]]}}}