SaGP: identifying plant saline-alkali tolerance genes based on machine learning techniques

Area of Science:

• Plant Biology
• Genetics
• Bioinformatics

Background:

• Identifying genes for agronomical traits is vital for crop improvement, food security, and biodiversity.
• Traditional wet experiments for gene discovery are costly and time-consuming.
• Machine learning offers a more efficient and cost-effective approach to accelerate gene discovery.

Purpose of the Study:

• To develop a machine learning model for identifying plant saline-alkali tolerance genes.
• To create a user-friendly web service for large-scale gene identification.
• To provide a framework for developing automated tools for crop breeding and conservation.

Main Methods:

• Development of SaGP (Saline-alkali Genes Prediction), a novel machine learning model.
• Utilizing sequencing data as input for gene prediction.
• Validation of SaGP against traditional tools (e.g., BLAST) and recently published genes.

Main Results:

• SaGP outperformed traditional computational tools in identifying saline-alkali tolerance genes.
• SaGP accurately identified the functions of recently published genes (GhAG2, MdBPR6, TaCCD1).
• A freely accessible web service platform based on SaGP was developed.

Conclusions:

• SaGP is effective for large-scale identification of plant saline-alkali tolerance genes.
• The SaGP model serves as a foundation for developing automated tools in plant biology.
• The developed web service facilitates efficient gene discovery for crop breeding and conservation.