{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:57:09Z","timestamp":1790575029026,"version":"4.1.0"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"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. Bioeng. Biotechnol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Stability, yield, and interactions between variables in the process, combined with the risk of contamination, pose a challenge for optimization of microbial fermentation processes. In this work, FERM-AI, a novel risk-aware machine learning surrogate framework for benchmark evaluation of cellulase fermentation, is presented, comprising of yield prediction, contamination risk assessment and an interactive decision-support interface.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The framework was tested with a benchmark set of 1,000 runs of fermentation, consisting of 20 fermentation runs from experiments and 980 synthetic fermentation runs to develop the methods. Biologically relevant process optimality, stress responses and interaction effects were captured using domain-informed feature engineering, and features were then selected and expanded using polynomial feature expansion. Cellulase yield prediction was analysed using multiple regression models such as Ridge Regression, Bayesian Ridge Regression, Huber Regression, Partial Least Squares (PLS) Regression, Gradient Boosting, Extra Trees, XGBoost and ensemble models; and contamination risk was modelled using imbalance-aware classification with SMOTE and ensemble learning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The Huber Regressor outperformed the other algorithms with an R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.9998, while PLS Regression performed well with an R\n                      <jats:sup>2<\/jats:sup>\n                      of 0.9937, further validating the strength of the proposed feature representation. The soft voting ensemble classifier was 83.5% accurate and had an AUC-ROC of 0.9045 for the contamination prediction.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The integrated framework is a proof-of-concept showing the potential of simultaneously modelling productivity and contamination risks, which can aid in the evaluation of fermentation operating conditions in a risk-aware fashion. The data used in the benchmark is synthetic, so the predictive results are meant to show the validation of the proposed surrogate modelling framework, and not that the predictive ability of the framework is of industrial scale. The framework will be validated in the future with bigger fermentation datasets obtained from experiments and expanded to the real-world fermentation process optimization.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbioe.2026.1824449","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:14Z","timestamp":1790574254000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing microbial cellulase fermentation with FERM-AI: risk-aware machine learning framework for fermentation and contamination prediction"],"prefix":"10.3389","volume":"14","author":[{"given":"Ritu","family":"Chauhan","sequence":"first","affiliation":[{"name":"Artificial Intelligence and IoT Lab, Center for Computational Biology and Bioinformatics, Amity University","place":["Noida, Uttar Pradesh, India"]},{"name":"Malaysian Institute of Information Technology, Universiti Kuala Lumpur","place":["Kaula Lampur, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aarushi","family":"Mishra","sequence":"additional","affiliation":[{"name":"Malaysian Institute of Information Technology, Universiti Kuala Lumpur","place":["Kaula Lampur, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Megat F.","family":"Zuhairi","sequence":"additional","affiliation":[{"name":"Malaysian Institute of Information Technology, Universiti Kuala Lumpur","place":["Kaula Lampur, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek Kumar","family":"Gaur","sequence":"additional","affiliation":[{"name":"Amity Institute of Biotechnology, Amity University","place":["Noida, Uttar Pradesh, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"B2","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/10_2020_151","article-title":"Digital Twins for bioprocess control strategy development and realisation","volume-title":"Digital Twins: Applications to the Design and Optimization of Bioprocesses","author":"Appl","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","first-page":"101619","DOI":"10.1016\/j.bcab.2020.101619","article-title":"Comparative study on modeling by neural networks and response surface methodology for better prediction and optimization of fermentation parameters: application on thermo-alkaline lipase production by Nocardiopsis sp. strain NRC\/WN5","volume":"25","author":"Aziz","year":"2020","journal-title":"Biocatal. Agric. Biotechnol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1039\/d2su00066k","article-title":"Perspectives in growth production trade-off in microbial bioproduction","volume":"1","author":"Banerjee","year":"2023","journal-title":"RSC Sustain."},{"key":"B5","doi-asserted-by":"publisher","first-page":"118403","DOI":"10.1016\/j.foodres.2026.118403","article-title":"Critical assessment of machine learning approaches for classification, dynamic prediction and surrogate Modeling in food fermentation","volume":"229","author":"Campo-Manzanares","year":"2026","journal-title":"Food Res. Int."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1002\/ceat.202200029","article-title":"Fermentation process control and optimization","volume":"45","author":"Chai","year":"2022","journal-title":"Chem. Eng. and Technol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"3155","DOI":"10.1007\/s11144-022-02293-9","article-title":"Application of machine learning to predict the yield of alginate lyase solid-state fermentation by Cunninghamella echinulata: artificial neural networks and support vector machine","volume":"135","author":"De Farias Silva","year":"2022","journal-title":"React. Kinet. Mech. Catal."},{"key":"B10","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1007\/s13399-020-01227-6","article-title":"Current perspective on improved fermentative production and purification of fungal cellulases for successful biorefinery applications: a brief review","volume":"12","author":"Dey","year":"2022","journal-title":"Biomass Convers. Biorefinery"},{"key":"B11","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":"B12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.copbio.2020.07.004","article-title":"Control strategies to manage trade-offs during microbial production","volume":"66","author":"Han","year":"2020","journal-title":"Curr. Opinion Biotechnology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4625","DOI":"10.1021\/acs.iecr.1c04534","article-title":"Design and optimization of a penicillin fed-batch reactor based on a deep learning fault detection and diagnostic model","volume":"61","author":"Hematillake","year":"2022","journal-title":"Industrial and Eng. Chem. Res."},{"key":"B14","volume-title":"Digital Twins","author":"Herwig","year":"2021"},{"key":"B15","doi-asserted-by":"publisher","first-page":"3598","DOI":"10.3390\/en16083598","article-title":"Cellulases: from lignocellulosic biomass to improved production","volume":"16","author":"Ili\u0107","year":"2023","journal-title":"Energies"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2100212","DOI":"10.1002\/biot.202100212","article-title":"Synergisms of machine learning and constraint\u2010based modeling of metabolism for analysis and optimization of fermentation parameters","volume":"16","author":"Khaleghi","year":"2021","journal-title":"Biotechnol. J."},{"key":"B17","volume-title":"Fermentation Optimization","author":"Konwar","year":"2024"},{"key":"B19","doi-asserted-by":"publisher","first-page":"364","DOI":"10.3390\/en17020364","article-title":"Maximizing biogas yield using an optimized stacking ensemble machine learning approach","volume":"17","author":"Mukasine","year":"2024","journal-title":"Energies"},{"key":"B20","doi-asserted-by":"publisher","first-page":"30","DOI":"10.69987\/AIMLR.2023.40303","article-title":"Machine learning for real-time optimization of bioprocessing parameters: applications and improvements","volume":"4","author":"Pan","year":"2023","journal-title":"Artif. Intell. Mach. Learn. Rev."},{"key":"B21","doi-asserted-by":"publisher","first-page":"100702","DOI":"10.1016\/j.coche.2021.100702","article-title":"Bioprocess digital twins of mammalian cell culture for advanced biomanufacturing","volume":"33","author":"Park","year":"2021","journal-title":"Curr. Opin. Chem. Eng."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1002\/bit.28405","article-title":"Data\u2010driven prediction models for forecasting multistep ahead profiles of mammalian cell culture toward bioprocess digital twins","volume":"120","author":"Park","year":"2023","journal-title":"Biotechnol. Bioengineering"},{"key":"B23","doi-asserted-by":"publisher","first-page":"100832","DOI":"10.1016\/j.cogsc.2023.100832","article-title":"An overview of green processes and technologies, biobased chemicals and products for industrial applications","volume":"41","author":"Ramchuran","year":"2023","journal-title":"Curr. Opinion Green Sustainable Chemistry"},{"key":"B24","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/bs.mim.2024.12.004","article-title":"The role of AI in microbial fermentation: transforming industrial applications","volume":"56","author":"Srivastava","year":"2025","journal-title":"Methods Microbiol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"7287","DOI":"10.1007\/s13399-022-03163-z","article-title":"Bioethanol production optimization through machine learning algorithm approach: biomass characteristics, saccharification, and fermentation conditions for enzymatic hydrolysis","volume":"13","author":"Vinitha","year":"2023","journal-title":"Biomass Convers. Biorefinery"},{"key":"B27","doi-asserted-by":"publisher","first-page":"678","DOI":"10.3390\/ani13040678","article-title":"Rumen fermentation parameters prediction model for dairy cows using a stacking ensemble learning method","volume":"13","author":"Wang","year":"2023","journal-title":"Animals"},{"key":"B28","doi-asserted-by":"publisher","first-page":"133287","DOI":"10.1016\/j.biortech.2025.133287","article-title":"Artificial intelligence-driven fermentation optimization for \u03b1-amylase hyperproduction enabled by Raman monitoring and metabolic network analysis","volume":"439","author":"Wang","year":"2025","journal-title":"Bioresour. Technol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"118620","DOI":"10.1016\/j.measurement.2025.118620","article-title":"Integrating micro-hyperspectral imaging and machine learning to investigate mie scattering for early detection of microbial contamination in liquid fermentation cultures","volume":"257","author":"Wu","year":"2025","journal-title":"Measurement"},{"key":"B30","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3390\/fermentation11060323","article-title":"Smart fermentation technologies: microbial process control in traditional fermented foods","volume":"11","author":"Yee","year":"2025","journal-title":"Fermentation"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1016\/j.eng.2020.12.022","article-title":"Hybrid data-driven and mechanistic modeling approaches for multiscale material and process design","volume":"7","author":"Zhou","year":"2021","journal-title":"Engineering"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1824449\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:44:15Z","timestamp":1790574255000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1824449\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":26,"alternative-id":["10.3389\/fbioe.2026.1824449"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1824449","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"article-number":"1824449"}}