Multi-omics assists genomic prediction of maize yield with machine learning approaches.

With the improvement of high-throughput technologies in recent years, large multi-dimensional plant omics data have been produced, and big-data-driven yield prediction research has received increasing attention. Machine learning offers promising computational and analytical solutions to interpret the biological meaning of large amounts of data in crops. In this study, we utilized multi-omics datasets from 156 maize recombinant inbred lines, containing 2496 single nucleotide polymorphisms (SNPs), 46 image traits (i-traits) from 16 developmental stages obtained through an automatic phenotyping platform, and 133 primary metabolites. Based on benchmark tests with different types of prediction models, some machine learning methods, such as Partial Least Squares (PLS), Random Forest (RF), and Gaussian process with Radial basis function kernel (GaussprRadial), achieved better prediction for maize yield, albeit slight difference for method preferences among i-traits, genomic, and metabolic data. We found that better yield prediction may be caused by various capabilities in ranking and filtering data features, which is found to be linked with biological meaning such as photosynthesis-related or kernel development-related regulations. Finally, by integrating multiple omics data with the RF machine learning approach, we can further improve the prediction accuracy of grain yield from 0.32 to 0.43. Our research provides new ideas for the application of plant omics data and artificial intelligence approaches to facilitate crop genetic improvements. Supplementary Information: The online version contains supplementary material available at 10.1007/s11032-024-01454-z.

Three types of genes underlying the Gametophyte factor1 locus cause unilateral cross incompatibility in maize.

Unilateral cross incompatibility (UCI) occurs between popcorn and dent corn, and represents a critical step towards speciation. It has been reported that ZmGa1P, encoding a pectin methylesterase (PME), is a male determinant of the Ga1 locus. However, the female determinant and the genetic relationship between male and female determinants at this locus are unclear. Here, we report three different types, a total of seven linked genes underlying the Ga1 locus, which control UCI phenotype by independently affecting pollen tube growth in both antagonistic and synergistic manners. These include five pollen-expressed PME genes (ZmGa1Ps-m), a silk-expressed PME gene (ZmPME3), and another silk-expressed gene (ZmPRP3), encoding a pathogenesis-related (PR) proteins. ZmGa1Ps-m confer pollen compatibility. Presence of ZmPME3 causes silk to reject incompatible pollen. ZmPRP3 promotes incompatibility pollen tube growth and thereby breaks the blocking effect of ZmPME3. In addition, evolutionary genomics analyses suggest that the divergence of the Ga1 locus existed before maize domestication and continued during breeding improvement. The knowledge gained here deepen our understanding of the complex regulation of cross incompatibility.