Back to all available

Integrating co-expression network analysis and machine learning to reveal the regulatory landscape of GPD genes in Chlamydomonas reinhardtii under salinity stress

bioinformatics
cell-biology
molecular-biology
plant-science
data-mining-and-machine-learning

Abstract

Background. Understanding how organisms adapt to environmental stress remains a central challenge in biology, with implications for both ecosystem resilience and biotechnological innovation. Chlamydomonas reinhardtii is a powerful model for exploring transcriptional responses to salinity, where glycerol biosynthesis plays a critical osmoprotective role mediated by glycerol-3-phosphate dehydrogenase (GPD) enzymes. While GPD2 and GPD3 are known salt-responsive genes sharing high sequence identity and similar metabolic functions, the regulatory mechanisms governing their expression remain poorly characterized. In this study, we employed a novel integrative framework that allows the reuse of publicly available time-course RNA-seq data to address previously unexplored regulatory differences between these genes, combining network analysis and machine learning to reveal unique transcriptional regulatory programs.

Methods. Weighted Gene Co-expression Network Analysis (WGCNA) was performed on Chlamydomonas reinhardtii transcriptomes under salt stress and control conditions. Modules containing GPD genes were analyzed for functional enrichment, transcription factor associations, and cis-regulatory elements, while network robustness was assessed using a Random Forest classifier to validate gene-to-module assignment.

Results. GPD2 and GPD3 clustered into distinct co-expression modules with contrasting temporal and functional profiles. GPD2 showed early induction and co-expression with bZIP and GATA factors, whereas GPD3 displayed delayed responses and association with MYB, SBP, and ALFIN-like factors. Distinct promoter motifs supported these regulatory differences, and Random Forest validation (95.4 % accuracy) confirmed the biological coherence of the network.

Conclusions. Our integrative approach demonstrates that, despite their high sequence similarity, GPD2 and GPD3 are embedded in fundamentally distinct regulatory networks during salt stress. To our knowledge, this study represents the first application of supervised machine learning to validate WGCNA modules in microalgae, providing a rigorous framework for assessing co-expression network robustness. This work proposes a methodological strategy that integrates data reuse, network analysis, and machine learning validation to enhance the study of gene regulation in microalgae and other organisms.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].