Genomic prediction of maize microphenotypes provides insights for optimizing selection and mining diversity

Abstract

Effective evaluation of millions of crop genetic stocks is an essential component of exploiting genetic diversity to achieve global food security. By leveraging genomics and data analytics, genomic prediction is a promising strategy to efficiently explore the potential of these gene banks by starting with phenotyping a small designed subset. Reliable genomic predictions have enhanced selection of many macroscopic phenotypes in plants and animals. However, the use of genomicprediction strategies for analysis of microscopic phenotypes is limited. Here, we exploited the power of genomic prediction for eight maize traits related to the shoot apical meristem (SAM), the microscopic stem cell niche that generates all the above-ground organs of the plant. With 435 713 genomewide single-nucleotide polymorphisms (SNPs), we predicted SAM morphology traits for 2687 diverse maize inbreds based on a model trained from 369 inbreds. An empirical validation experiment with 488 inbreds obtained a prediction accuracy of 0.37-0.57 across eight traits. In addition, we show that a significantly higher prediction accuracy was achieved by leveraging the U value (upper bound for reliability) that quantifies the genomic relationships of the validation set with the training set. Our findings suggest that double selection considering both prediction and reliability can be implemented in choosing selection candidates for phenotyping when exploring new diversity is desired. In this case, individuals with less extreme predicted values and moderate reliability values can be considered. Our study expands the turbocharging gene banks via genomic prediction from the macrophenotypes into the microphenotypic space.

Keywords: genetic diversity; genomic selection; genomics; maize; plant breeding; shoot apical meristem.

Figure 1

Study design of genomic prediction of maize shoot apical meristem (SAM). (a), Maize SAM contains a group of pluripotent stem cells that generate all above‐ground organs. Height and radius were two directly measured SAM traits. (b) The 369‐accession training set. A neighbour‐joining tree is presented to show the genetic diversity of this set. (c) Neighbour‐joining tree of the entire Ames Panel (n = 3056). The branches were colour‐coded by the associated maize groups. (d) The selected and phenotyped 488‐accession validation set. Both the 369‐accession training set and 488‐accession validation set are parts of the entire Ames Panel. Forward prediction, selection, validation and reverse prediction were performed progressively. U stands for upper bound for reliability. High‐U set has 244 accessions with high U values and likewise for low‐U set.

Figure 2

Prediction accuracy in the 369‐accession training set through cross‐validation. (a) Graphical illustrations of three SAM traits: height, radius and volume. Height (h) and radius (r) are directly measured under microscope; volume is calculated through a parabolic model. (b) Prediction accuracy is estimated through two‐, five‐ and 10‐fold cross‐validation.

Figure 3

Validation set selection and empirical validation of shoot apical meristem (SAM) volume. (a) The validation set was built with six parts indicated by different colours: (i) 50 accessions with the large predicted SAM volume and high U values (red); (ii) 50 accessions with the small SAM volume and high U values (violet); (iii) 150 random accessions from the remaining accessions with high U values (green); (iv) 50 accessions with the large SAM volume and low U values (orange); (v) 50 accessions with the small SAM volume and low U values (yellow); and (vi) 150 random accessions from the remaining accessions with low U values (blue). Not selected accessions are shown in grey. (b) Prediction accuracy for volume. (c) Prediction accuracy for height. (d) Prediction accuracy for radius. The accuracy was calculated from the 488‐accession set that were successfully phenotyped.

Figure 4

Prediction accuracy comparison by sampling accessions with different U values. (a) Graphical illustration of the sampling process. The sampling was performed along the y‐axis according to U value. Sample size ranges from 60 to 300 with increment of 10. For example, when n = 60, a contrast of two sets of materials was formed, including the high‐U set with the top 60 and the low‐U set with the bottom 60 dots. (b–d) Comparison of prediction accuracy between the high‐U set (solid circle) and low‐U set (open circle) for volume (b), height (c), and radius (d). Notice that for the high‐U set, increasing the sample size of the validation set leads to the inclusion of individuals with gradually smaller U values, thus reduced prediction accuracy.

Figure 5

Relationship among shoot apical meristem (SAM) traits, maize groups and upper bound for reliability (U). (a) SAM height and radius in the 488‐accession validation set. Dot size indicates SAM volume; dot colour indicates maize groups. The two inserts are two images of SAMs with different height and radius. Scale bar, 100 µm. (b) Different maize accessions have different U values. Colour intensity indicates the U value.