{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T16:16:17Z","timestamp":1795104977427,"version":"4.10.3"},"reference-count":42,"publisher":"American Chemical Society (ACS)","issue":"45","license":[{"start":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T00:00:00Z","timestamp":1793577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006464","name":"Birla Institute of Technology and Science, Pilani","doi-asserted-by":"publisher","award":["C1\/23\/132"],"award-info":[{"award-number":["C1\/23\/132"]}],"id":[{"id":"10.13039\/501100006464","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,11,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Optimizing surfactin production from a wild-type Bacillus sp., is challenging due to complex microbial growth kinetics, nonlinear interactions among process variables, and the lack of mechanistic models to describe surfactin production. Therefore, the present study develops data-driven machine learning models to optimize surfactin production from Bacillus subtilis MTCC 2423 under limited fermentation data. First, 25 batch fermentation experiments were performed to obtain surfactin titers under varied conditions of temperature, agitation speed, and inoculum volume, generated using a central composite design (CCD) integrated with maximin Latin hypercube sampling (LHS). Subsequently, machine learning models, viz, multivariable least-squares regression (MVLSR), Gaussian process regression (GPR), support vector regression (SVR), and random forest (RF), were trained and evaluated using the nested leave-one-out cross-validation (LOOCV) to achieve robust prediction of the surfactin titer. Hyperparameter tuning of the models was performed using a genetic algorithm (GA) and grid search. Both the GPR and SVR outperformed the other models and demonstrated comparable predictive performance on the unseen data, producing the LOOCV R2 of 0.89 and 0.86, and LOOCV RMSE of 0.6 and 0.67, respectively. Subsequently, the mean response surface plots were constructed using the GPR model to illustrate the effects of nonlinear interactions among the input features on the surfactin titer. Finally, a GPR-based constrained optimization yielded an optimal surfactin titer of 5.72 g L\u20131, compared to the base-case value of 1.49 g L\u20131, while identifying the optimal process variables. The data-driven optimization results closely agreed with the experimentally validated surfactin titer of 5.75 \u00b1 0.09 g L\u20131, demonstrating high model reliability and predictive accuracy. Our experimental design approach, integrated with machine-learning-driven optimization using limited experimental data, can be adopted across various bioprocess sectors to achieve substantial improvements in surfactin titer.<\/jats:p>","DOI":"10.1021\/acsomega.6c07721","type":"journal-article","created":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T17:02:22Z","timestamp":1793638942000},"page":"70383-70397","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning-Assisted Optimization of Surfactin\nTiter Produced by\n                    <i>Bacillus subtilis<\/i>\n                    MTCC 2423 from Minimum Fermentation Data with Experimental Validation"],"prefix":"10.1021","volume":"11","author":[{"given":"Ashwini","family":"Padole","sequence":"first","affiliation":[{"name":"Birla Institute of Technology and Science Pilani, K.K. Birla Goa Campus , , , ,","place":["Zuarinagar, Goa, India, 403726"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5604-3091","authenticated-orcid":true,"given":"Riju","family":"De","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science Pilani, K.K. Birla Goa Campus , , , ,","place":["Zuarinagar, Goa, India, 403726"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6704-2462","authenticated-orcid":true,"given":"Vivek","family":"Rangarajan","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science Pilani, K.K. Birla Goa Campus , , , ,","place":["Zuarinagar, Goa, India, 403726"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6315-4523","authenticated-orcid":true,"given":"Utpal","family":"Roy","sequence":"additional","affiliation":[{"name":"Birla Institute of Technology and Science Pilani, K.K. Birla Goa Campus , , , ,","place":["Zuarinagar, Goa, India, 403726"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,11,2]]},"reference":[{"key":"2026111910013519300_cit1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmicr.2024.100266","article-title":"Microbial Biosurfactants: Green Alternatives\nand Sustainable Solution for Augmenting Pesticide Remediation and\nManagement of Organic Waste","volume":"7","author":"Markam","year":"2024","journal-title":"Curr. Res. Microb.\nSci."},{"issue":"3","key":"2026111910013519300_cit2","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12030662","article-title":"Biosurfactants:\nPotential and Eco-Friendly Material\nfor Sustainable Agriculture and Environmental Safety\u2500A Review","volume":"12","author":"Gayathiri","year":"2022","journal-title":"Agronomy"},{"issue":"8","key":"2026111910013519300_cit3","doi-asserted-by":"publisher","DOI":"10.3390\/pharmaceutics15082156","article-title":"Harnessing the Potential of Biosurfactants\nfor Biomedical\nand Pharmaceutical Applications","volume":"15","author":"Ceresa","year":"2023","journal-title":"Pharmaceutics"},{"issue":"6","key":"2026111910013519300_cit4","doi-asserted-by":"publisher","first-page":"2084","DOI":"10.3109\/10717544.2016.1153745","article-title":"A Natural Lipopeptide of Surfactin\nfor Oral Delivery of Insulin","volume":"23","author":"Zhang","year":"2016","journal-title":"Drug Delivery"},{"issue":"2","key":"2026111910013519300_cit5","doi-asserted-by":"publisher","first-page":"195","DOI":"10.3934\/microbiol.2023012","article-title":"Chemical Structure,\nProperties and Potential Applications of Surfactin, as Well as Advanced\nStrategies for Improving Its Microbial Production","volume":"9","author":"Zhen","year":"2023","journal-title":"AIMS Microbiol."},{"issue":"2","key":"2026111910013519300_cit6","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/S0141-0229(02)00287-9","article-title":"Optimization\nof Agitation, Aeration, and Temperature Conditions for Maximum \u03b2-Mannanase\nProduction","volume":"32","author":"Feng","year":"2003","journal-title":"Enzyme Microb. Technol."},{"issue":"1","key":"2026111910013519300_cit7","doi-asserted-by":"publisher","DOI":"10.3390\/molecules23010125","article-title":"Effects of\nAgitation, Aeration and\nTemperature on Production of a Novel Glycoprotein GP-1 by Streptomyces\nKanasenisi ZX01 and Scale-Up Based on Volumetric Oxygen Transfer Coefficient","volume":"23","author":"Zhou","year":"2018","journal-title":"Molecules"},{"issue":"2","key":"2026111910013519300_cit8","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.bej.2004.06.006","article-title":"Response Surface Modeling and Optimization to Elucidate\nand Analyze the Effects of Inoculum Age and Size on Surfactin Production","volume":"21","author":"Sen","year":"2004","journal-title":"Biochem. Eng. J."},{"issue":"1","key":"2026111910013519300_cit9","doi-asserted-by":"publisher","DOI":"10.1186\/s13568-025-01978-3","article-title":"Model-Based\nProcess Design for Surfactin Production with Bacillus Subtilis","volume":"15","author":"Hiller","year":"2025","journal-title":"AMB Express"},{"key":"2026111910013519300_cit10","doi-asserted-by":"publisher","DOI":"10.1016\/j.fbio.2024.105546","article-title":"Kinetics Study\non Microbial Growth and Surfactin Production of Bacillus Subtilis\nATCC 21332 under the Synergistic Effect of Magnetic Field and Mg2+","volume":"63","author":"Chen","year":"2025","journal-title":"Food Biosci."},{"issue":"7","key":"2026111910013519300_cit11","doi-asserted-by":"publisher","DOI":"10.3390\/fermentation11070408","article-title":"Fermentation\nProcesses: Modeling, Optimization and Control: 2nd Edition","volume":"11","author":"Lo\u0301pez","year":"2025","journal-title":"Fermentation"},{"issue":"3","key":"2026111910013519300_cit12","doi-asserted-by":"publisher","DOI":"10.3390\/colloids2030036","article-title":"Statistical\nDesign, a Powerful Tool for Optimizing Biosurfactant Production: A\nReview","volume":"2","author":"Bertrand","year":"2018","journal-title":"Colloids Interfaces"},{"key":"2026111910013519300_cit13","doi-asserted-by":"publisher","DOI":"10.1016\/j.dwt.2025.101387","article-title":"Hybrid Optimization\nof Thermally-Enhanced\nZn-Fe LDH Catalysts for Fenton-like Reactions: Integrating Design\nof Experiments with Machine Learning Models for Optimisation","volume":"323","author":"Naufal","year":"2025","journal-title":"Desalin. Water Treat."},{"key":"2026111910013519300_cit14","doi-asserted-by":"publisher","DOI":"10.1016\/j.biteb.2025.102518","article-title":"Machine Learning-Driven\nCongener-Specific\nRhamnolipids Production","volume":"33","author":"Nasser","year":"2026","journal-title":"Bioresour. Technol.\nRep."},{"issue":"9","key":"2026111910013519300_cit15","doi-asserted-by":"publisher","first-page":"8465","DOI":"10.1007\/s13762-021-03639-x","article-title":"Studies on Production,\nOptimization and Machine Learning-Based\nPrediction of Biosurfactant from Debaryomyces Hansenii CBS767","volume":"19","author":"Kaur","year":"2022","journal-title":"Int. J. Environ. Sci. Technol."},{"issue":"10","key":"2026111910013519300_cit16","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1007\/s00449-019-02165-y","article-title":"Comparative Efficacy of Machine-Learning\nModels in Prediction of\nReducing Uncertainties in Biosurfactant Production","volume":"42","author":"Jovic","year":"2019","journal-title":"Bioprocess Biosyst. Eng."},{"issue":"2","key":"2026111910013519300_cit17","doi-asserted-by":"publisher","first-page":"127","DOI":"10.2298\/CICEQ150125026M","article-title":"Soft Sensor Based on\nGaussian Process Regression and Its Application\nin Erythromycin Fermentation Process","volume":"22","author":"Mei","year":"2016","journal-title":"Chem.\nInd. Chem. Eng. Q."},{"issue":"1","key":"2026111910013519300_cit18","doi-asserted-by":"publisher","DOI":"10.1186\/s12866-023-02838-5","article-title":"Optimization of Fermentation Conditions for Surfactin Production\nby B. Subtilis YPS-32","volume":"23","author":"Zhou","year":"2023","journal-title":"BMC Microbiol."},{"key":"2026111910013519300_cit19","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1016\/j.csbj.2024.02.012","article-title":"Optimisation of Surfactin Yield in Bacillus Using Data-Efficient Active Learning and High-Throughput\nMass Spectrometry","volume":"23","author":"Albornoz","year":"2024","journal-title":"Comput. Struct. Biotechnol.\nJ."},{"issue":"2","key":"2026111910013519300_cit20","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1002\/cbf.3776","article-title":"Prediction\nof Surfactin Fermentation with Bacillus Subtilis DSM10 by Response Surface Methodology Optimized Artificial Neural\nNetwork","volume":"41","author":"Czinko\u0301czky","year":"2023","journal-title":"Cell Biochem. Funct."},{"issue":"1","key":"2026111910013519300_cit21","doi-asserted-by":"publisher","DOI":"10.1186\/s12934-019-1089-x","article-title":"Rational Strain\nImprovement for Surfactin Production:\nEnhancing the Yield and Generating Novel Structures","volume":"18","author":"Hu","year":"2019","journal-title":"Microb. Cell Fact."},{"key":"2026111910013519300_cit22","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.matpr.2022.09.042","article-title":"Optimization\nof Processing Parameters\nfor the Improved Production of Surfactin from B. Subtilis Using a\nStatistical Approach and Demonstration of Its Imminent Potential in\nCosmetic Applications","volume":"76","author":"Ganesan","year":"2023","journal-title":"Mater. Today Proc."},{"key":"2026111910013519300_cit23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bcab.2021.102001","article-title":"A Kinetics\nStudy on Surfactin Production from Bacillus\nSubtilis MTCC 2415 for Application in Green Cosmetics","volume":"33","author":"Ganesan","year":"2021","journal-title":"Biocatal. Agric. Biotechnol."},{"issue":"9","key":"2026111910013519300_cit24","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.17576\/jsm-2017-4601-24","article-title":"Kinetics\nof Surfactin\nProduction by Bacillus Subtilis in a 5 L Stirred-Tank Bioreactor","volume":"46","author":"Mubarak","year":"2017","journal-title":"Sains Malays."},{"issue":"1\u20132","key":"2026111910013519300_cit25","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1080\/02648725.2016.1166335","article-title":"Process Development\nand Intensification for Enhanced\nProduction of Bacillus Lipopeptides","volume":"31","author":"Rangarajan","year":"2015","journal-title":"Biotechnol. Genet. Eng. Rev."},{"key":"2026111910013519300_cit26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112454","article-title":"GA Based Construction\nof Maximin Latin Hypercube Designs for Uncertainty Design of Experiment\nwith Dynamic Strategy Management","volume":"167","author":"Liu","year":"2024","journal-title":"Appl. Soft\nComput."},{"key":"2026111910013519300_cit27","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.cageo.2011.06.011","article-title":"Support Vector Regression to Predict Porosity and Permeability:\nEffect of Sample Size","volume":"39","author":"Al-Anazi","year":"2012","journal-title":"Comput. Geosci."},{"issue":"1","key":"2026111910013519300_cit28","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/S0893-6080(03)00169-2","article-title":"Practical Selection\nof SVM Parameters and Noise Estimation for SVM\nRegression","volume":"17","author":"Cherkassky","year":"2004","journal-title":"Neural Netw."},{"key":"2026111910013519300_cit29","doi-asserted-by":"publisher","DOI":"10.3389\/fnut.2026.1889843","article-title":"Machine Learning-Assisted Optimization\nof Ultrasound\u2013Ohmic\nProcessing of Hawthorn Vinegar: Antidiabetic Activity, Phenolic Profiling,\nand Molecular Docking Insights","volume":"13","author":"Alt\u0131ner","year":"2026","journal-title":"Front. Nutr."},{"issue":"12","key":"2026111910013519300_cit30","doi-asserted-by":"publisher","DOI":"10.1115\/1.4040985","article-title":"Confidence-Driven Design\nOptimization Using Gaussian Process Metamodeling\nWith Insufficient Data","volume":"140","author":"Li","year":"2018","journal-title":"J. Mech. Des."},{"key":"2026111910013519300_cit31","doi-asserted-by":"publisher","DOI":"10.1016\/j.marpetgeo.2020.104429","article-title":"TOC Content Prediction Based on a\nCombined Gaussian Process Regression\nModel","volume":"118","author":"Rui","year":"2020","journal-title":"Mar. Pet. Geol."},{"key":"2026111910013519300_cit32","volume-title":"Least Squares Optimization\nin Multivariate Analysis","author":"ten Berge","year":"1993"},{"key":"2026111910013519300_cit33","first-page":"23","article-title":"Introduction\nto Multivariate Regression Analysis","volume":"14","author":"Alexopoulos","year":"2010","journal-title":"Hippokratia"},{"issue":"10","key":"2026111910013519300_cit34","first-page":"203","article-title":"Support\nVector Regression","volume":"11","author":"Basak","year":"2007","journal-title":"Neural Inf. Proc., Lett.\nRev."},{"key":"2026111910013519300_cit35","unstructured":"Segal, M. R.\n          \n          Machine Learning\nBenchmarks and Random Forest Regression."},{"issue":"4","key":"2026111910013519300_cit36","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1080\/10485252.2012.715161","article-title":"Robustness of Random Forests for\nRegression","volume":"24","author":"Roy","year":"2012","journal-title":"J. Nonparametric Stat."},{"key":"2026111910013519300_cit37","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.cherd.2020.02.033","article-title":"Gaussian Process\nRegression with Heteroscedastic Noises\u2013A Machine-Learning Predictive\nVariance Approach","volume":"157","author":"Li","year":"2020","journal-title":"Chem. Eng. Res. Des."},{"key":"2026111910013519300_cit38","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-540-28650-9_4","article-title":"Gaussian Processes\nin Machine Learning","volume-title":"Advanced Lectures\non Machine Learning","author":"Rasmussen","year":"2004"},{"issue":"1","key":"2026111910013519300_cit39","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1039\/D5ME00126A","article-title":"Enhanced Thermophysical Property Prediction with Uncertainty\nQuantification Using Group Contribution-Gaussian Process Regression","volume":"11","author":"Agbodekhe","year":"2026","journal-title":"Mol. Syst. Des. Eng."},{"issue":"5","key":"2026111910013519300_cit40","doi-asserted-by":"publisher","first-page":"8091","DOI":"10.1007\/s11042-020-10139-6","article-title":"A Review on\nGenetic Algorithm: Past,\nPresent, and Future","volume":"80","author":"Katoch","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"2026111910013519300_cit41","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.neucom.2020.07.061","article-title":"On Hyperparameter Optimization of Machine Learning Algorithms: Theory\nand Practice","volume":"415","author":"Yang","year":"2020","journal-title":"Neurocomputing"},{"issue":"1","key":"2026111910013519300_cit42","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1080\/24709360.2017.1396742","article-title":"A Tutorial\non Kernel Density Estimation and Recent Advances","volume":"1","author":"Chen","year":"2017","journal-title":"Biostat. Epidemiol."}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.6c07721","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/45\/70383\/69051102\/acsomega.6c07721.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/45\/70383\/69051102\/acsomega.6c07721.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T15:27:22Z","timestamp":1795102042000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/45\/70383\/5462420\/Machine-Learning-Assisted-Optimization-of"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11,2]]},"references-count":42,"journal-issue":{"issue":"45","published-online":{"date-parts":[[2026,11,2]]},"published-print":{"date-parts":[[2026,11,17]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.6c07721","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1021\/acsomega.6c07721.s001","asserted-by":"subject"}]},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11,2]]}}}