Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Aquatic Photosynthetic Organisms
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1461610
This article is part of the Research Topic Biotechnological Advances in the Sustainable Exploitation of Coastal Photosynthetic Organisms View all articles

Machine learning-based predictive models unleash the enhanced production of fucoxanthin in Isochrysis galbana

Provisionally accepted
Janani Manochkumar Janani Manochkumar 1Annapurna Jonnalagadda Annapurna Jonnalagadda 2Aswani Kumar Cherukuri Aswani Kumar Cherukuri 3Brigitte Vannier Brigitte Vannier 4Dao Janjaroen Dao Janjaroen 5Rajasekaran Chandrasekaran Rajasekaran Chandrasekaran 1Ramamoorthy Siva Ramamoorthy Siva 1,6*
  • 1 School of Biosciences and Technology, Vellore Institute of Technology, Vellore, Tamil Nadu, India
  • 2 School of Computer Science and Engineering, VIT University, Vellore, Tamil Nadu, India
  • 3 School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, India
  • 4 University of Poitiers, Poitiers, Poitou-Charentes, France
  • 5 Chulalongkorn University, Bangkok, Bangkok, Thailand
  • 6 VIT University, Vellore, India

The final, formatted version of the article will be published soon.

    The marine microalgae, Isochrysis galbana is a prolific producer of fucoxanthin which is a xanthophyll carotenoid with substantial global market value boasting extensive applications in the food, nutraceutical, pharmaceutical, and cosmetic industries. This study presented a novel integrated experimental approach coupled with machine learning (ML) models to predict the fucoxanthin content in Isochrysis galbana by altering the type and concentration of phytohormone supplementation, thus overcoming the multiple methodological limitations of conventional fucoxanthin quantification. Morphological analysis of microalgal structure revealed the influence of type and concentration of phytohormones and the correlation between growth rate and fucoxanthin yield was further evidenced by statistical and ML models. The findings revealed that the Random Forest (RF) model was highly significant with a high 𝑅 2 of 0.809 and 𝑅𝑀𝑆𝐸 of 0.776 when hormone descriptors were excluded and the inclusion of hormone descriptors further improved prediction accuracy to 𝑅 2 of 0.839 making it a useful tool for predicting the fucoxanthin yield. The model which fitted to the experimental data indicated methyl jasmonate (0.2 mg l -1 ) as an effective phytohormone. In short, the estimation of fucoxanthin yield using prediction models is rapid, reliable, more efficient, and less expensive. This research highlights the potential of utilizing diverse ML models to optimize the parameters affecting microalgal growth, offering valuable insights to improve the fucoxanthin production efficiency in microalgae cultivation.

    Keywords: fucoxanthin, Isochrysis galbana, phytohormones, machine learning, prediction

    Received: 08 Jul 2024; Accepted: 23 Sep 2024.

    Copyright: © 2024 Manochkumar, Jonnalagadda, Cherukuri, Vannier, Janjaroen, Chandrasekaran and Siva. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Ramamoorthy Siva, VIT University, Vellore, India

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.