Decoding RNA N6-Methyladenosine Methylome of Wheat Using Machine Learning and Nanopore Direct RNA Sequencing.

Area of Science:

• Plant molecular biology
• Epitranscriptomics
• Bioinformatics

Background:

• N6-methyladenosine (m6A) is a key RNA modification regulating plant processes.
• Nanopore direct RNA sequencing (DRS) offers single-base resolution for m6A detection.
• Existing tools struggle with complex plant genomes due to training limitations.

Purpose of the Study:

• To develop a robust computational framework (CatMOD) for m6A detection in plant DRS data.
• To generate the first genome-wide m6A atlas for allohexaploid wheat (Triticum aestivum L.).
• To investigate m6A distribution and its relationship with subgenome expression in wheat.

Main Methods:

• Developed CatMOD, an ensemble machine learning framework integrating ionic current and non-signal features.
• Implemented an evidence-based positive sampling strategy for improved generalizability.
• Applied CatMOD to Nanopore DRS data from wheat seedlings.

Main Results:

• Generated the first single-base resolution m6A atlas for wheat.
• Observed variations in m6A site numbers across wheat's A, B, and D subgenomes.
• Found potential associations between m6A patterns and subgenome expression plasticity.

Conclusions:

• CatMOD provides accurate m6A detection in diverse plant species, especially polyploids.
• The wheat m6A atlas offers insights into epitranscriptomic regulation in complex genomes.
• Established a scalable framework for plant epitranscriptome analysis using Nanopore DRS.