{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T04:19:53Z","timestamp":1772252393873,"version":"3.50.1"},"reference-count":44,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT\/MCTES","award":["UIDB\/50006\/2020"],"award-info":[{"award-number":["UIDB\/50006\/2020"]}]},{"name":"FCT\/MCTES","award":["UIDP\/50006\/2020"],"award-info":[{"award-number":["UIDP\/50006\/2020"]}]},{"name":"FCT\/MCTES","award":["870292"],"award-info":[{"award-number":["870292"]}]},{"name":"FCT\/MCTES","award":["SFRD\/BD14610472019"],"award-info":[{"award-number":["SFRD\/BD14610472019"]}]},{"DOI":"10.13039\/501100000780","name":"European Union\u2019s Horizon 2020 research and innovation program","doi-asserted-by":"publisher","award":["UIDB\/50006\/2020"],"award-info":[{"award-number":["UIDB\/50006\/2020"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union\u2019s Horizon 2020 research and innovation program","doi-asserted-by":"publisher","award":["UIDP\/50006\/2020"],"award-info":[{"award-number":["UIDP\/50006\/2020"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union\u2019s Horizon 2020 research and innovation program","doi-asserted-by":"publisher","award":["870292"],"award-info":[{"award-number":["870292"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union\u2019s Horizon 2020 research and innovation program","doi-asserted-by":"publisher","award":["SFRD\/BD14610472019"],"award-info":[{"award-number":["SFRD\/BD14610472019"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PhD","award":["UIDB\/50006\/2020"],"award-info":[{"award-number":["UIDB\/50006\/2020"]}]},{"name":"PhD","award":["UIDP\/50006\/2020"],"award-info":[{"award-number":["UIDP\/50006\/2020"]}]},{"name":"PhD","award":["870292"],"award-info":[{"award-number":["870292"]}]},{"name":"PhD","award":["SFRD\/BD14610472019"],"award-info":[{"award-number":["SFRD\/BD14610472019"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia (FCT)","award":["UIDB\/50006\/2020"],"award-info":[{"award-number":["UIDB\/50006\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia (FCT)","award":["UIDP\/50006\/2020"],"award-info":[{"award-number":["UIDP\/50006\/2020"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia (FCT)","award":["870292"],"award-info":[{"award-number":["870292"]}]},{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia (FCT)","award":["SFRD\/BD14610472019"],"award-info":[{"award-number":["SFRD\/BD14610472019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AI"],"abstract":"<jats:p>In this paper, a computational framework is proposed that merges mechanistic modeling with deep neural networks obeying the Systems Biology Markup Language (SBML) standard. Over the last 20 years, the systems biology community has developed a large number of mechanistic models that are currently stored in public databases in SBML. With the proposed framework, existing SBML models may be redesigned into hybrid systems through the incorporation of deep neural networks into the model core, using a freely available python tool. The so-formed hybrid mechanistic\/neural network models are trained with a deep learning algorithm based on the adaptive moment estimation method (ADAM), stochastic regularization and semidirect sensitivity equations. The trained hybrid models are encoded in SBML and uploaded in model databases, where they may be further analyzed as regular SBML models. This approach is illustrated with three well-known case studies: the Escherichia coli threonine synthesis model, the P58IPK signal transduction model, and the Yeast glycolytic oscillations model. The proposed framework is expected to greatly facilitate the widespread use of hybrid modeling techniques for systems biology applications.<\/jats:p>","DOI":"10.3390\/ai4010014","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T04:22:28Z","timestamp":1677730948000},"page":"303-318","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["A General Hybrid Modeling Framework for Systems Biology Applications: Combining Mechanistic Knowledge with Deep Neural Networks under the SBML Standard"],"prefix":"10.3390","volume":"4","author":[{"given":"Jos\u00e9","family":"Pinto","sequence":"first","affiliation":[{"name":"LAQV-REQUIMTE, Department of Chemistry, NOVA School of Science and Technology, NOVA University Lisbon, Campus da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6832-6774","authenticated-orcid":false,"given":"Jo\u00e3o R. C.","family":"Ramos","sequence":"additional","affiliation":[{"name":"LAQV-REQUIMTE, Department of Chemistry, NOVA School of Science and Technology, NOVA University Lisbon, Campus da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7539-488X","authenticated-orcid":false,"given":"Rafael S.","family":"Costa","sequence":"additional","affiliation":[{"name":"LAQV-REQUIMTE, Department of Chemistry, NOVA School of Science and Technology, NOVA University Lisbon, Campus da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8077-4177","authenticated-orcid":false,"given":"Rui","family":"Oliveira","sequence":"additional","affiliation":[{"name":"LAQV-REQUIMTE, Department of Chemistry, NOVA School of Science and Technology, NOVA University Lisbon, Campus da Caparica, 2829-516 Caparica, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.compchemeng.2013.08.008","article-title":"Hybrid semi-parametric modeling in process systems engineering: Past, present and future","volume":"60","author":"Oliveira","year":"2014","journal-title":"Comput. Chem. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1002\/aic.690381003","article-title":"A Hybrid Neural Network-1st Principles Approach to Process Modeling","volume":"38","author":"Psichogios","year":"1992","journal-title":"Aiche J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1002\/aic.690400806","article-title":"Modeling Chemical Processes Using Prior Knowledge and Neural Networks","volume":"40","author":"Thompson","year":"1994","journal-title":"Aiche J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1002\/ceat.270170103","article-title":"Hybrid Modeling of Yeast Production Processes\u2014Combination of a-Priori Knowledge on Different Levels of Sophistication","volume":"17","author":"Schubert","year":"1994","journal-title":"Chem. Eng. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1021\/bp0502328","article-title":"Bioprocess iterative batch-to-batch optimization based on hybrid parametric\/nonparametric models","volume":"22","author":"Teixeira","year":"2006","journal-title":"Biotechnol. Prog."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Teixeira, A.P., Alves, C., Alves, P.M., Carrondo, M.J., and Oliveira, R. (2007). Hybrid elementary flux analysis\/nonparametric modeling: Application for bioprocess control. BMC Bioinform., 8.","DOI":"10.1186\/1471-2105-8-30"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10862","DOI":"10.1016\/j.eswa.2011.02.117","article-title":"A novel identification method for hybrid (N)PLS dynamical systems with application to bioprocesses","volume":"38","author":"Oliveira","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1007\/s00449-019-02181-y","article-title":"A bootstrap-aggregated hybrid semi-parametric modeling framework for bioprocess development","volume":"42","author":"Pinto","year":"2019","journal-title":"Bioprocess Biosyst. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e17715","DOI":"10.1002\/aic.17715","article-title":"Integration of machine learning and first principles models","volume":"68","author":"Rajulapati","year":"2022","journal-title":"Aiche J."},{"key":"ref_10","unstructured":"Taylor&Francis (2018). Hybrid Modeling in Process Industries, CRC Press. [1st ed.]."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Agharafeie, R., Oliveira, R., Ramos, J., and Mendes, J. (2023). Application of Hybrid Neural Models to Bioprocesses: A Systematic Literature Review. Authorea.","DOI":"10.22541\/au.167465887.70993839\/v1"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Le, N.Q.K., Do, D.T., Hung, T.N.K., Lam, L.H.T., Huynh, T.T., and Nguyen, N.T.K. (2020). A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21239070"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e2100232","DOI":"10.1002\/pmic.202100232","article-title":"Potential of deep representative learning features to interpret the sequence information in proteomics","volume":"22","author":"Le","year":"2022","journal-title":"Proteomics"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","article-title":"A guide to machine learning for biologists","volume":"23","author":"Greener","year":"2022","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/978-1-0716-2617-7_18","article-title":"Machine Learning and Hybrid Methods for Metabolic Pathway Modeling","volume":"2553","author":"Bennett","year":"2023","journal-title":"Methods Mol. Biol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3287","DOI":"10.1016\/j.csbj.2020.10.011","article-title":"The era of big data: Genome-scale modelling meets machine learning","volume":"18","author":"Antonakoudis","year":"2020","journal-title":"Comput. Struct Biotec."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.coisb.2021.03.001","article-title":"Machine learning applications in genome-scale metabolic modeling","volume":"25","author":"Kim","year":"2021","journal-title":"Curr. Opin. Syst. Biol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Carinhas, N., Bernal, V., Teixeira, A.P., Carrondo, M.J.T., Alves, P.M., and Oliveira, R. (2011). Hybrid metabolic flux analysis: Combining stoichiometric and statistical constraints to model the formation of complex recombinant products. BMC Syst. Biol., 5.","DOI":"10.1186\/1752-0509-5-34"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1007\/s00449-016-1611-z","article-title":"Hybrid metabolic flux analysis and recombinant protein prediction in Pichia pastoris X-33 cultures expressing a singlechain antibody fragment","volume":"39","author":"Isidro","year":"2016","journal-title":"Bioprocess Biosyst. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1007\/s00449-013-1029-9","article-title":"Fast development of Pichia pastoris GS115 Mut(+) cultures employing batch-to-batch control and hybrid semi-parametric modeling","volume":"37","author":"Ferreira","year":"2014","journal-title":"Bioprocess Biosyst. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Teixeira, A.P., Dias, J.M.L., Carinhas, N., Sousa, M., Clemente, J.J., Cunha, A.E., von Stosch, M., Alves, P.M., Carrondo, M.J.T., and Oliveira, R. (2011). Cell functional enviromics: Unravelling the function of environmental factors. BMC Syst. Biol., 5.","DOI":"10.1186\/1752-0509-5-92"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"von Stosch, M., Peres, J., de Azevedo, S.F., and Oliveira, R. (2010). Modelling biochemical networks with intrinsic time delays: A hybrid semi-parametric approach. BMC Syst. Biol., 4.","DOI":"10.1186\/1752-0509-4-131"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1039\/C5MB00828J","article-title":"Principal elementary mode analysis (PEMA)","volume":"12","author":"Marques","year":"2016","journal-title":"Mol. Biosyst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1007\/s00449-016-1557-1","article-title":"Hybrid modeling as a QbD\/PAT tool in process development: An industrial E-coli case study","volume":"39","author":"Hamelink","year":"2016","journal-title":"Bioprocess Biosyst. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lee, D., Jayaraman, A., and Kwon, J.S. (2020). Development of a hybrid model for a partially known intracellular signaling pathway through correction term estimation and neural network modeling. PLoS Comput. Biol., 16.","DOI":"10.1371\/journal.pcbi.1008472"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104235","DOI":"10.1016\/j.rinp.2021.104235","article-title":"A novel study of Morlet neural networks to solve the nonlinear HIV infection system of latently infected cells","volume":"25","author":"Umar","year":"2021","journal-title":"Results Phys."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Umar, M., Sabir, Z., Raja, M.A.Z., Shoaib, M., Gupta, M., and Sanchez, Y.G. (2020). A Stochastic Intelligent Computing with Neuro-Evolution Heuristics for Nonlinear SITR System of Novel COVID-19 Dynamics. Symmetry, 12.","DOI":"10.3390\/sym12101628"},{"key":"ref_28","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":"ref_29","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":"Lewis","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_30","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":"ref_31","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1007\/s00449-022-02795-9","article-title":"Genome-scale modeling of Chinese hamster ovary cells by hybrid semi-parametric flux balance analysis","volume":"45","author":"Ramos","year":"2022","journal-title":"Bioprocess Biosyst. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"D689","DOI":"10.1093\/nar\/gkj092","article-title":"BioModels Database: A free, centralized database of curated, published, quantitative kinetic models of biochemical and cellular systems","volume":"34","author":"Bornstein","year":"2006","journal-title":"Nucleic Acids Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1093\/bioinformatics\/bth200","article-title":"Web-based kinetic modelling using JWS Online","volume":"20","author":"Olivier","year":"2004","journal-title":"Bioinformatics"},{"key":"ref_34","first-page":"baaa093","article-title":"KiMoSys 2.0: An upgraded database for submitting, storing and accessing experimental data for kinetic modeling","volume":"2020","author":"Mochao","year":"2020","journal-title":"Database J. Biol. Databases Curation"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1093\/bioinformatics\/btg015","article-title":"The systems biology markup language (SBML): A medium for representation and exchange of biochemical network models","volume":"19","author":"Hucka","year":"2003","journal-title":"Bioinformatics"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"btad044","DOI":"10.1093\/bioinformatics\/btad044","article-title":"SBML2HYB: A Python interface for SBML compatible hybrid modelling","volume":"39","author":"Pinto","year":"2023","journal-title":"Bioinformatics"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107952","DOI":"10.1016\/j.compchemeng.2022.107952","article-title":"A general deep hybrid model for bioreactor systems: Combining first principles with deep neural networks","volume":"165","author":"Pinto","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1042\/bj3560433","article-title":"Control of the threonine-synthesis pathway in Escherichia coli: A theoretical and experimental approach","volume":"356","author":"Chassagnole","year":"2001","journal-title":"Biochem. J."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.virol.2011.04.020","article-title":"Virus infection rapidly activates the P58(IPK) pathway, delaying peak kinase activation to enhance viral replication","volume":"417","author":"Goodman","year":"2011","journal-title":"Virology"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"4862","DOI":"10.1111\/j.1742-4658.2006.05485.x","article-title":"Reduction of a biochemical model with preservation of its basic dynamic properties","volume":"273","author":"Dano","year":"2006","journal-title":"Febs J."},{"key":"ref_41","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arxiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.1093\/bioinformatics\/btl485","article-title":"COPASI\u2014A COmplex PAthway SImulator","volume":"22","author":"Hoops","year":"2006","journal-title":"Bioinformatics"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1093\/bioinformatics\/bts432","article-title":"CySBML: A Cytoscape plugin for SBML","volume":"28","author":"Konig","year":"2012","journal-title":"Bioinformatics"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/S0169-7439(02)00051-5","article-title":"Model selection for partial least squares regression","volume":"64","author":"Li","year":"2002","journal-title":"Chemom. Intell. Lab."}],"container-title":["AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-2688\/4\/1\/14\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:45:23Z","timestamp":1760121923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-2688\/4\/1\/14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["ai4010014"],"URL":"https:\/\/doi.org\/10.3390\/ai4010014","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202301.0579.v1","asserted-by":"object"}]},"ISSN":["2673-2688"],"issn-type":[{"value":"2673-2688","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]}}}