EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Response Surface Methodology for Bioprocesses Development Using Interpretable Machine Learning

Juan Federico Herrera-Ruiz iD, Juan Camilo Castaño-Sánchez iD, Oscar Andrés Prado-Rubio iD

ACS Omega · 10.11.2026 · 11 (44) · 69154-69166

DOI: 10.1021/acsomega.6c09217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Omega, online erschienen am 29.10.2026. Verfasst von Juan Federico Herrera-Ruiz und 2 weiteren Autor:innen. Beteiligte Einrichtung: Grupo de Investigación en Aplicación de Nuevas Tecnologías (GIANT) Departamento de Ingeniería Química, Universidad Nacional de Colombia sede Manizale…. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sistema General de Regal?as de Colombia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Response surface methodology (RSM) has been a cornerstone for experimental bioprocess optimization, yet its reliance on polynomial equations often fails to capture complex nonlinearities and requires extensive experimental data to attempt capturing them. This study evaluates the enhancement of RSM through machine learning (ML) techniques, specifically Gaussian Processes and Support Vector Machines, across three biological systems: succinic acid fermentation, biobutanol production, and continuous ethanol cultivation. To mitigate the “black-box” nature of ML, explainability measures such as Mutual Information (MI) and Local Interpretable Model-agnostic Explanations (LIME) were integrated to assess feature importance and ensure biological relevance. Results demonstrate that ML models consistently outperform traditional polynomials in predictive accuracy, even when having access to less experimental data for calibration and a reduced space of features, particularly on validation data sets where errors were significantly reduced (e.g., reaching MAPE lower than 1% in simulated experimental scenarios). Furthermore, the application of Model-Based Design of Experiments using Latin Hypercube Designs achieved optimal conditions with up to 50% fewer experimental runs compared to traditional factorial approaches. These findings suggest that coupling ML with explainability tools improves the reliability of finding optimal conditions for bioprocess development while also significantly enhancing operational efficiency by reducing experimental runs, time, and costs.

Autor:innen und Institutionen

  • Grupo de Investigación en Aplicación de Nuevas Tecnologías (GIANT) Departamento de Ingeniería Química, Universidad Nacional de Colombia sede Manizales, Campus La Nubia, Manizales 170003, Colombia.
  • TBI, Université de Toulouse, CNRS, INRAE, INSA, 135 Avenue de Rangueil, Toulouse (CEDEX 04) 31077, France.
  • Grupo de Investigación en Aplicación de NuevasTecnologías (GIANT) Departamento de Ingeniería Química, Universidad Nacional de Colombia sede Manizales, Campus La Nubia, Manizales 170003, Colombia.

ORCID-Profile: Juan Federico Herrera-Ruiz, Juan Camilo Castaño-Sánchez, Oscar Andrés Prado-Rubio

Förderung

  • Sistema General de Regal?as de Colombia

Zitieren

APA

Herrera-Ruiz, J. F., Castaño-Sánchez, J. C., & Prado-Rubio, O. A. (2026). Enhancing Response Surface Methodology for Bioprocesses Development Using Interpretable Machine Learning. ACS Omega, 11(44), 69154-69166. https://doi.org/10.1021/acsomega.6c09217

Vancouver

Herrera-Ruiz JF, Castaño-Sánchez JC, Prado-Rubio OA. Enhancing Response Surface Methodology for Bioprocesses Development Using Interpretable Machine Learning. ACS Omega. 2026;11(44):69154-69166. doi:10.1021/acsomega.6c09217

BibTeX
@article{HerreraRuiz2026,
  author = {Herrera-Ruiz, Juan Federico and Castaño-Sánchez, Juan Camilo and Prado-Rubio, Oscar Andrés},
  title = {Enhancing Response Surface Methodology for Bioprocesses Development Using Interpretable Machine Learning},
  journal = {ACS Omega},
  year = {2026},
  volume = {11},
  number = {44},
  pages = {69154--69166},
  doi = {10.1021/acsomega.6c09217}
}
Kostenlos starten →