Integrative Metabolomics and Machine Learning Approach to Uncover Scab Resistance Markers in Mature Pecan Trees

Area of Science:

• Plant Pathology
• Metabolomics
• Plant Breeding

Background:

• Pecan scab, caused by *Venturia effusa*, is a major threat to *Carya illinoinensis* production.
• Developing scab-resistant pecan cultivars is crucial for sustainable disease management.

Purpose of the Study:

• To identify metabolic biomarkers associated with pecan scab resistance.
• To understand the biochemical basis of resistance in *Carya illinoinensis*.

Main Methods:

• Pathway-based metabolomics was applied to 15 pecan cultivars with varied resistance levels.
• Machine learning models (SVM, Random Forest, Linear Regression) were used to identify predictive biomarkers.
• Metabolite profiles were analyzed in relation to plant-pathogen interaction pathways.

Main Results:

• Machine learning models achieved >97% accuracy in classifying resistant and susceptible cultivars.
• Resistant cultivars exhibited higher levels of lignin biosynthesis, energy metabolism, and antioxidant precursors (e.g., syringin, proline).
• Susceptible cultivars accumulated defense end-products but lacked sufficient precursor availability.

Conclusions:

• Metabolic profiles offer insights into pecan scab resistance mechanisms.
• Key metabolic precursors are indicative of a proactive defense strategy in resistant pecan trees.
• Identified metabolic traits can guide the breeding of disease-resilient pecan cultivars and enhance orchard management.