Machine learning solutions for integrating partially overlapping genetic datasets and modelling host–endophyte effects in ryegrass (Lolium) dry matter yield estimation

Plant genetic evaluation often faces challenges due to complex genetic structures. Ryegrass (<i>Lolium</i>), a valuable species for pasture-based agriculture, exhibits heterogeneous genetic diversities among base breeding populations. Partially overlapping datasets from incompatible studies and commercial restrictions further impede outcome integration across studies, complicating the evaluation of key agricultural traits such as dry matter yield (DMY). To address these challenges: (1) we implemented a population genotyping approach to capture the genetic diversity in ryegrass base cultivars; (2) we introduced a machine learning-based strategy to integrate genetic distance matrices (GDMs) from incompatible genotyping approaches, including alignments using multidimensional scaling (MDS) and Procrustes transformation, as well as a novel evaluation strategy (BESMI) for the imputation of structural missing data. Endophytes complicate genetic evaluation by introducing additional variation in phenotypic expression. (3) We modelled the impacts of nine commercial endophytes on ryegrass DMY, enabling a more balanced estimation of untested cultivar-endophyte combinations. (4) Phylogenetic analysis provided a pseudo-pedigree relationship of the 113 ryegrass populations and revealed its associations with DMY variations. Overall, this research offers practical insights for integrating partially overlapping GDMs with structural missing data patterns and facilitates the identification of high-performing ryegrass clades. The methodological advancements-including population sequencing, MDS alignment via Procrustes transformation, and BESMI-extend beyond ryegrass applications.