|
Integration of Machine Learning Algorithms in Identifying Genes and Molecular Pathways Related to Stresse Resistance in Transgenic Plants
|
Narjessadat Mousavimadani   , Akram Sadeghi * , Reza Sharafi |
| Department of Microbial Biotechnology, Agricultural Biotechnology Research Institute of Iran (ABRII), Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran |
|
|
Abstract: (73 Views) |
Throughout their life cycle, plants are exposed to a wide range of abiotic stresses, including salinity, drought, water deficit, temperature extremes, oxidative stress, heavy metal toxicity, as well as biotic stresses such as various pests and diseases. These stresses are major factors hindering crops from reaching their genetic potential and achieving optimal performance. This review article first examines the role of these stresses in limiting plant performance and explores biotechnological strategies for managing them. It then discusses the application of machine learning (ML) algorithms in identifying and prioritizing genes and molecular pathways associated with stress resistance, alongside both traditional and modern agricultural biotechnology tools. Artificial intelligence (AI) and ML, through the analysis of multilayered genomic, transcriptomic, and other omics datasets, enable the modeling of signaling and metabolic networks, the simulation of plant performance under stress conditions, and the interpretation of genetic and epigenetic interactions. This approach ultimately enhances research efficiency and reduces costs and time requirements. The article further presents ML algorithms such as Random Forest (RF), Support Vector Machines (SVM), and deep learning (DL) models for identifying key resistance factors and supporting breeding decisions. Finally, it reviews case studies on crops like rice, corn, and Arabidopsis, and discusses associated challenges and limitations, as well as biosafety, legal, and economic considerations.
|
|
| Keywords: Omics, Biotecchnology, Transgenic, Plant Stresses, Machine Learning |
|
|
Full-Text [PDF 937 kb]
(65 Downloads)
|
Type of Study: Review |
Subject:
Special
Received: 2026/01/11 | Accepted: 2026/04/9 | Published: 2026/05/20
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
