{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:06:44Z","timestamp":1778800004723,"version":"3.51.4"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>In the intricate realm of enzymology, the precise quantification of enzyme efficiency, epitomized by the turnover number (<jats:italic>k<\/jats:italic><jats:sub>cat<\/jats:sub>), is a paramount yet elusive objective. Existing methodologies, though sophisticated, often grapple with the inherent stochasticity and multifaceted nature of enzymatic reactions. Thus, there arises a necessity to explore avant-garde computational paradigms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this context, we introduce \u201cenzyme catalytic efficiency prediction (ECEP),\u201d leveraging advanced deep learning techniques to enhance the previous implementation, TurNuP, for predicting the enzyme catalase <jats:italic>k<\/jats:italic><jats:sub>cat<\/jats:sub>. Our approach significantly outperforms prior methodologies, incorporating new features derived from enzyme sequences and chemical reaction dynamics. Through ECEP, we unravel the intricate enzyme-substrate interactions, capturing the nuanced interplay of molecular determinants.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Preliminary assessments, compared against established models like TurNuP and DLKcat, underscore the superior predictive capabilities of ECEP, marking a pivotal shift <jats:italic>in silico<\/jats:italic> enzymatic turnover number estimation. This study enriches the computational toolkit available to enzymologists and lays the groundwork for future explorations in the burgeoning field of bioinformatics. This paper suggested a multi-feature ensemble deep learning-based approach to predict enzyme kinetic parameters using an ensemble convolution neural network and XGBoost by calculating weighted-average of each feature-based model\u2019s output to outperform traditional machine learning methods. The proposed \u201cECEP\u201d model significantly outperformed existing methodologies, achieving a mean squared error (MSE) reduction of 0.35 from 0.81 to 0.46 and <jats:italic>R<\/jats:italic>-squared score from 0.44 to 0.54, thereby demonstrating its superior accuracy and effectiveness in enzyme catalytic efficiency prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>This improvement underscores the model\u2019s potential to enhance the field of bioinformatics, setting a new benchmark for performance.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1446063","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T05:10:48Z","timestamp":1729487448000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Enzyme catalytic efficiency prediction: employing convolutional neural networks and XGBoost"],"prefix":"10.3389","volume":"7","author":[{"given":"Meshari","family":"Alazmi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"4402","DOI":"10.1021\/bi2002289","article-title":"The moderately efficient enzyme: evolutionary and physicochemical trends shaping enzyme parameters","volume":"50","author":"Bar-Even","year":"2011","journal-title":"Biochemistry"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s43586-023-00266-3","article-title":"Bayesian optimization as a valuable tool for sustainable chemical reaction development","volume":"3","author":"Braconi","year":"2023","journal-title":"Nat. Rev. Methods Primers"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"3401","DOI":"10.1073\/pnas.1514240113","article-title":"Global characterization of in vivo enzyme catalytic rates and their correspondence to in vitro kcat measurements","volume":"113","author":"Davidi","year":"2016","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1914","DOI":"10.1038\/s41467-022-29443-w","article-title":"Learning meaningful representations of protein sequences","volume":"13","author":"Detlefsen","year":"2022","journal-title":"Nat. Commun."},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5571-3_2","article-title":"Fundamentals of machine learning","volume-title":"Neural networks and statistical learning","author":"Du","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"13091","DOI":"10.1038\/ncomms13091","article-title":"Multi-omic data integration enables discovery of hidden biological regularities","volume":"7","author":"Ebrahim","year":"2016","journal-title":"Nat. Commun."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"gzab019","DOI":"10.1093\/protein\/gzab019","article-title":"Machine learning for enzyme engineering, selection and design","volume":"34","author":"Feehan","year":"2021","journal-title":"Protein Eng. Des. Sel."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2845","DOI":"10.3390\/ijms20112845","article-title":"Prediction of enzyme function based on three parallel deep CNN and amino acid mutation","volume":"20","author":"Gao","year":"2019","journal-title":"Int. J. Mol. Sci."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"14911","DOI":"10.1021\/acs.jafc.3c05029","article-title":"Artificial intelligence aided lipase production and engineering for enzymatic performance improvement","volume":"71","author":"Ge","year":"2023","journal-title":"J. Agric. Food Chem."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e1009853","DOI":"10.1371\/journal.pcbi.1009853","article-title":"Machine learning modeling of family wide enzyme-substrate specificity screens","volume":"18","author":"Goldman","year":"2022","journal-title":"PLoS Comput. Biol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"23182","DOI":"10.1073\/pnas.2001562117","article-title":"Kinetic profiling of metabolic specialists demonstrates stability and consistency of in vivo enzyme turnover numbers","volume":"117","author":"Heckmann","year":"2020","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"13806","DOI":"10.1038\/ncomms13806","article-title":"A genome-scale Escherichia coli kinetic metabolic model k-ecoli457 satisfying flux data for multiple mutant strains","volume":"7","author":"Khodayari","year":"2016","journal-title":"Nat. Commun."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"4139","DOI":"10.1038\/s41467-023-39840-4","article-title":"Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning","volume":"14","author":"Kroll","year":"2023","journal-title":"Nat. Commun."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41929-022-00798-z","article-title":"Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction","volume":"5","author":"Li","year":"2022","journal-title":"Nat. Catal."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.cels.2020.03.002","article-title":"MONN: a multi-objective neural network for predicting compound-protein interactions and affinities","volume":"10","author":"Li","year":"2020","journal-title":"Cell Syst."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"533a","DOI":"10.1016\/j.bpj.2019.11.2926","article-title":"Enzyme function prediction using deep learning","volume":"118","author":"Memon","year":"2020","journal-title":"Biophys. J."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"4471","DOI":"10.1007\/s11831-021-09542-5","article-title":"An extensive study on deep learning: techniques, applications","volume":"28","author":"Mittal","year":"2021","journal-title":"Arch. Computat. Methods Eng."},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1016\/B978-0-12-812970-8.00002-6","article-title":"Machine learning fundamentals","volume-title":"Mobility patterns, big data and transport analytics","author":"Pereira","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"9689","DOI":"10.1101\/676825","article-title":"Evaluating protein transfer learning with TAPE","volume":"32","author":"Rao","year":"2019","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1042\/bse0590001","article-title":"Enzymes: principles and biotechnological applications","volume":"59","author":"Robinson","year":"2015","journal-title":"Essays Biochem."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"ysaa004","DOI":"10.1093\/synbio\/ysaa004","article-title":"Machine learning-based prediction of activity and substrate specificity for OleA enzymes in the thiolase superfamily","volume":"5","author":"Robinson","year":"2020","journal-title":"Synth. Biol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1016\/j.biotechadv.2017.09.005","article-title":"Formulation, construction and analysis of kinetic models of metabolism: a review of modelling frameworks","volume":"35","author":"Saa","year":"2017","journal-title":"Biotechnol. Adv."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"154","DOI":"10.3390\/metabo14030154","article-title":"Machine learning to predict enzyme-substrate interactions in elucidation of synthesis pathways: a review","volume":"14","author":"Salas-Nu\u00f1ez","year":"2024","journal-title":"Metabolites"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"935","DOI":"10.15252\/msb.20167411","article-title":"Improving the phenotype predictions of a yeast genome-scale metabolic model by incorporating enzymatic constraints","volume":"13","author":"S\u00e1nchez","year":"2017","journal-title":"Mol. Syst. Biol."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.jbiotec.2017.04.020","article-title":"The BRENDA enzyme information system\u2013from a database to an expert system","volume":"261","author":"Schomburg","year":"2017","journal-title":"J. Biotechnol."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1038\/s41586-021-03213-y","article-title":"Bayesian reaction optimization as a tool for chemical synthesis","volume":"590","author":"Shields","year":"2021","journal-title":"Nature"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"759384","DOI":"10.3389\/fgene.2021.759384","article-title":"Identification of enzymes-specific protein domain based on DDE, and convolutional neural network","volume":"12","author":"Sikander","year":"2021","journal-title":"Front. Genet."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2832","DOI":"10.1016\/j.febslet.2013.06.043","article-title":"A model of yeast glycolysis based on a consistent kinetic characterisation of all its enzymes","volume":"587","author":"Smallbone","year":"2013","journal-title":"FEBS Lett."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.copbio.2019.02.005","article-title":"Metabolic kinetic modeling provides insight into complex biological questions, but hurdles remain","volume":"59","author":"Strutz","year":"2019","journal-title":"Curr. Opin. Biotechnol."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"12336","DOI":"10.1021\/acssuschemeng.3c02402","article-title":"A customized Bayesian algorithm to optimize enzyme-catalyzed reactions","volume":"11","author":"Tachibana","year":"2023","journal-title":"ACS Sustain. Chem. Eng."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2699","DOI":"10.1093\/nar\/gky092","article-title":"UniProt: the universal protein knowledgebase","volume":"46","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.ymben.2023.06.001","article-title":"Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural network","volume":"78","author":"Upadhyay","year":"2023","journal-title":"Metab. Eng."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"bbae409","DOI":"10.1093\/bib\/bbae409","article-title":"DeepEnzyme: a robust deep learning model for improved enzyme turnover number prediction by utilizing features of protein 3D structures","volume":"25","author":"Wang","year":"2023","journal-title":"Brief. Bioinform."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1038\/s41467-023-37151-2","article-title":"Data integration across conditions improves turnover number estimates and metabolic predictions","volume":"14","author":"Wendering","year":"2023","journal-title":"Nat. Commun."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"D656","DOI":"10.1093\/nar\/gkx1065","article-title":"SABIO-RK: an updated resource for manually curated biochemical reaction kinetics","volume":"46","author":"Wittig","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1446063\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T05:10:50Z","timestamp":1729487450000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1446063\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":37,"alternative-id":["10.3389\/frai.2024.1446063"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1446063","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,21]]},"article-number":"1446063"}}