{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T02:11:21Z","timestamp":1772763081075,"version":"3.50.1"},"reference-count":52,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T00:00:00Z","timestamp":1542585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1516695"],"award-info":[{"award-number":["1516695"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1743101"],"award-info":[{"award-number":["1743101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1254205"],"award-info":[{"award-number":["1254205"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Gene expression prediction is one of the grand challenges in computational biology. The availability of transcriptomics data combined with recent advances in artificial neural networks provide an unprecedented opportunity to create predictive models of gene expression with far reaching applications.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We present the Genetic Neural Network (GNN), an artificial neural network for predicting genome-wide gene expression given gene knockouts and master regulator perturbations. In its core, the GNN maps existing gene regulatory information in its architecture and it uses cell nodes that have been specifically designed to capture the dependencies and non-linear dynamics that exist in gene networks. These two key features make the GNN architecture capable to capture complex relationships without the need of large training datasets. As a result, GNNs were 40% more accurate on average than competing architectures (MLP, RNN, BiRNN) when compared on hundreds of curated and inferred transcription modules. Our results argue that GNNs can become the architecture of choice when building predictors of gene expression from exponentially growing corpus of genome-wide transcriptomics data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>https:\/\/github.com\/IBPA\/GNN<\/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\/bty945","type":"journal-article","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T03:04:32Z","timestamp":1542423872000},"page":"2226-2234","source":"Crossref","is-referenced-by-count":28,"title":["Genetic Neural Networks: an artificial neural network architecture for capturing gene expression relationships"],"prefix":"10.1093","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2487-017X","authenticated-orcid":false,"given":"Ameen","family":"Eetemadi","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California, Davis, CA, USA"},{"name":"Genome Center, University of California, Davis, CA, USA"}]},{"given":"Ilias","family":"Tagkopoulos","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California, Davis, CA, USA"},{"name":"Genome Center, University of California, Davis, CA, USA"}]}],"member":"286","published-online":{"date-parts":[[2018,11,19]]},"reference":[{"key":"2023051701213494900_bty945-B1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.ijfoodmicro.2016.05.008","article-title":"\u2018omics\u2019 for microbial food stability: proteomics for the development of predictive models for bacterial spore stress survival and outgrowth","volume":"240","author":"Abhyankar","year":"2017","journal-title":"Int. J. Food Microbiol"},{"key":"2023051701213494900_bty945-B2","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1007\/978-3-319-25979-6_18","volume-title":"Lipids in Plant and Algae Development","author":"Aucoin","year":"2016"},{"key":"2023051701213494900_bty945-B3","doi-asserted-by":"crossref","first-page":"137","DOI":"10.3109\/10409238.2011.556597","article-title":"Mathematical modeling of gene expression: a guide for the perplexed biologist","volume":"46","author":"Ay","year":"2011","journal-title":"Crit. Rev. Biochem. Mol. Biol"},{"key":"2023051701213494900_bty945-B4","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res"},{"key":"2023051701213494900_bty945-B5","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1093\/bioinformatics\/19.2.185","article-title":"A comparison of normalization methods for high density oligonucleotide array data based on variance and bias","volume":"19","author":"Bolstad","year":"2003","journal-title":"Bioinformatics"},{"key":"2023051701213494900_bty945-B6","doi-asserted-by":"crossref","first-page":"R36.","DOI":"10.1186\/gb-2006-7-5-r36","article-title":"The inferelator: an algorithm for learning parsimonious regulatory networks from systems-biology data sets de novo","volume":"7","author":"Bonneau","year":"2006","journal-title":"Genome Biol"},{"key":"2023051701213494900_bty945-B7","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1126\/science.1160617","article-title":"Feedback loops shape cellular signals in space and time","volume":"322","author":"Brandman","year":"2008","journal-title":"Science"},{"key":"2023051701213494900_bty945-B8","doi-asserted-by":"crossref","first-page":"e38","DOI":"10.1093\/nar\/gkp022","article-title":"Model-based redesign of global transcription regulation","volume":"37","author":"Carrera","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023051701213494900_bty945-B9","doi-asserted-by":"crossref","first-page":"735.","DOI":"10.15252\/msb.20145108","article-title":"An integrative, multi-scale, genome-wide model reveals the phenotypic landscape of Escherichia coli","volume":"10","author":"Carrera","year":"2014","journal-title":"Mol. Syst. Biol"},{"key":"2023051701213494900_bty945-B10","first-page":"1","article-title":"What is a master regulator?","volume":"3","author":"Chan","year":"2013","journal-title":"J. Stem Cell Res. Ther"},{"key":"2023051701213494900_bty945-B11","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1093\/bioinformatics\/btw074","article-title":"Gene expression inference with deep learning","volume":"32","author":"Chen","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051701213494900_bty945-B12","doi-asserted-by":"crossref","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","author":"Ching","year":"2018","journal-title":"J. Royal Soc. Interface"},{"key":"2023051701213494900_bty945-B13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/BF01890115","article-title":"Efficient algorithms for agglomerative hierarchical clustering methods","volume":"1","author":"Day","year":"1984","journal-title":"J. Class"},{"key":"2023051701213494900_bty945-B14","first-page":"248","author":"Deng","year":"2009"},{"key":"2023051701213494900_bty945-B15","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/1754-1611-6-2","article-title":"A synthetic biology approach to self-regulatory recombinant protein production in Escherichia coli","volume":"6","author":"Dragosits","year":"2012","journal-title":"J. Biol. Eng"},{"key":"2023051701213494900_bty945-B16","doi-asserted-by":"crossref","first-page":"10286","DOI":"10.1073\/pnas.1702581114","article-title":"Global transcriptional regulatory network for Escherichia coli robustly connects gene expression to transcription factor activities","volume":"114","author":"Fang","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051701213494900_bty945-B17","doi-asserted-by":"crossref","first-page":"178.","DOI":"10.1038\/nature12337","article-title":"The mycobacterium tuberculosis regulatory network and hypoxia","volume":"499","author":"Galagan","year":"2013","journal-title":"Nature"},{"key":"2023051701213494900_bty945-B18","doi-asserted-by":"crossref","first-page":"D133","DOI":"10.1093\/nar\/gkv1156","article-title":"Regulondb version 9.0: high-level integration of gene regulation, coexpression, motif clustering and beyond","volume":"44","author":"Gama-Castro","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051701213494900_bty945-B19","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/clpt.2012.237","article-title":"Personalized cancer medicine: molecular diagnostics, predictive biomarkers, and drug resistance","volume":"93","author":"Gonzalez de Castro","year":"2013","journal-title":"Clin. Pharmacol. Therap"},{"key":"2023051701213494900_bty945-B20","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw"},{"key":"2023051701213494900_bty945-B21","doi-asserted-by":"crossref","first-page":"e12776.","DOI":"10.1371\/journal.pone.0012776","article-title":"Inferring regulatory networks from expression data using tree-based methods","volume":"5","author":"Irrthum","year":"2010","journal-title":"PLoS One"},{"key":"2023051701213494900_bty945-B22","doi-asserted-by":"crossref","first-page":"D353","DOI":"10.1093\/nar\/gkw1092","article-title":"Kegg: new perspectives on genomes, pathways, diseases and drugs","volume":"45","author":"Kanehisa","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2023051701213494900_bty945-B23","author":"Kansky","year":"2017"},{"key":"2023051701213494900_bty945-B24","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1126\/science.1171347","article-title":"Transcriptional regulatory circuits: predicting numbers from alphabets","volume":"325","author":"Kim","year":"2009","journal-title":"Science"},{"key":"2023051701213494900_bty945-B25","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":"2023051701213494900_bty945-B26","doi-asserted-by":"crossref","first-page":"e1005661","DOI":"10.1371\/journal.pcbi.1005661","article-title":"Deeppep: deep proteome inference from peptide profiles","volume":"13","author":"Kim","year":"2017","journal-title":"PLoS Comput. Biol"},{"key":"2023051701213494900_bty945-B27","author":"Krizhevsky","year":"2012"},{"key":"2023051701213494900_bty945-B28","first-page":"279","article-title":"Cautionary note about r 2","volume":"39","author":"Kv\u00e5lseth","year":"1985","journal-title":"Am. Stat"},{"key":"2023051701213494900_bty945-B29","doi-asserted-by":"crossref","first-page":"436.","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2023051701213494900_bty945-B30","doi-asserted-by":"crossref","first-page":"12855","DOI":"10.1038\/s41598-017-13183-9","article-title":"Cell-cell communication enhances bacterial chemotaxis toward external attractants","volume":"7","author":"Long","year":"2017","journal-title":"Sci. Rep"},{"key":"2023051701213494900_bty945-B31","doi-asserted-by":"crossref","first-page":"290.","DOI":"10.1038\/nmeth.4627","article-title":"Using deep learning to model the hierarchical structure and function of a cell","volume":"15","author":"Ma","year":"2018","journal-title":"Nat. Methods"},{"key":"2023051701213494900_bty945-B32","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1186\/s12934-014-0177-1","article-title":"Genome engineering for improved recombinant protein expression in Escherichia coli","volume":"13","author":"Mahalik","year":"2014","journal-title":"Microb. Cell Factories"},{"key":"2023051701213494900_bty945-B33","doi-asserted-by":"crossref","first-page":"6286","DOI":"10.1073\/pnas.0913357107","article-title":"Revealing strengths and weaknesses of methods for gene network inference","volume":"107","author":"Marbach","year":"2010","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051701213494900_bty945-B34","doi-asserted-by":"crossref","first-page":"796.","DOI":"10.1038\/nmeth.2016","article-title":"Wisdom of crowds for robust gene network inference","volume":"9","author":"Marbach","year":"2012","journal-title":"Nat. Methods"},{"key":"2023051701213494900_bty945-B35","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.1002\/biot.200900234","article-title":"Accomplishments in genome-scale in silico modeling for industrial and medical biotechnology","volume":"4","author":"Milne","year":"2009","journal-title":"Biotechnol. J"},{"key":"2023051701213494900_bty945-B36","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges","author":"Miotto","year":"2018","journal-title":"Brief. Bioinf"},{"key":"2023051701213494900_bty945-B37","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/S0893-6080(05)80056-5","article-title":"A scaled conjugate gradient algorithm for fast supervised learning","volume":"6","author":"M\u00f8ller","year":"1993","journal-title":"Neural Netw"},{"key":"2023051701213494900_bty945-B38","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1126\/science.1134196","article-title":"The 160-kilobase genome of the bacterial endosymbiont carsonella","volume":"314","author":"Nakabachi","year":"2006","journal-title":"Science"},{"key":"2023051701213494900_bty945-B39","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":"O\u2019Brien","year":"2015","journal-title":"Cell"},{"key":"2023051701213494900_bty945-B40","doi-asserted-by":"crossref","first-page":"2229.","DOI":"10.1103\/PhysRevLett.59.2229","article-title":"Generalization of back-propagation to recurrent neural networks","volume":"59","author":"Pineda","year":"1987","journal-title":"Phys. Rev. Lett"},{"key":"2023051701213494900_bty945-B41","doi-asserted-by":"crossref","first-page":"214.","DOI":"10.1038\/nrmicro.2017.172","article-title":"Engineering bacteria for diagnostic and therapeutic applications","volume":"16","author":"Riglar","year":"2018","journal-title":"Nat. Rev. Microbiol"},{"key":"2023051701213494900_bty945-B42","doi-asserted-by":"crossref","first-page":"1962","DOI":"10.1126\/science.1106914","article-title":"Gene regulation at the single-cell level","volume":"307","author":"Rosenfeld","year":"2005","journal-title":"Science"},{"key":"2023051701213494900_bty945-B43","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1093\/bioinformatics\/btr373","article-title":"Genenetweaver: in silico benchmark generation and performance profiling of network inference methods","volume":"27","author":"Schaffter","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051701213494900_bty945-B44","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process"},{"key":"2023051701213494900_bty945-B45","doi-asserted-by":"crossref","first-page":"i639","DOI":"10.1093\/bioinformatics\/btw427","article-title":"Deepchrome: deep-learning for predicting gene expression from histone modifications","volume":"32","author":"Singh","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051701213494900_bty945-B46","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1126\/science.349.6247.544","article-title":"Transcriptomics today: microarrays, RNA-seq, and more","volume":"349","author":"Tachibana","year":"2015","journal-title":"Science"},{"key":"2023051701213494900_bty945-B47","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. Ser. B (Methodological)"},{"key":"2023051701213494900_bty945-B48","first-page":"26","article-title":"Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA Neural Netw. Mach. Learn"},{"key":"2023051701213494900_bty945-B49","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1096\/fj.00-0361com","article-title":"Neural network model of gene expression","volume":"15","author":"Vohradsk","year":"2001","journal-title":"FASEB J"},{"key":"2023051701213494900_bty945-B50","author":"Watters","year":"2017"},{"key":"2023051701213494900_bty945-B51","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Comput"},{"key":"2023051701213494900_bty945-B52","doi-asserted-by":"crossref","first-page":"473.","DOI":"10.1038\/nrd.2016.32","article-title":"Emerging applications of metabolomics in drug discovery and precision medicine","volume":"15","author":"Wishart","year":"2016","journal-title":"Nat. Rev. Drug Discov"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/13\/2226\/50340356\/bioinformatics_35_13_2226.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/13\/2226\/50340356\/bioinformatics_35_13_2226.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T13:30:33Z","timestamp":1720791033000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/13\/2226\/5191703"}},"subtitle":[],"editor":[{"given":"Bonnie","family":"Berger","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,11,19]]},"references-count":52,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2019,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty945","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,7,1]]},"published":{"date-parts":[[2018,11,19]]}}}