Multimodal deep learning methods enhance genomic prediction of wheat breeding.

While several statistical machine learning methods have been developed and studied for assessing the genomic prediction (GP) accuracy of unobserved phenotypes in plant breeding research, few methods have linked genomics and phenomics (imaging). Deep learning (DL) neural networks have been developed to increase the GP accuracy of unobserved phenotypes while simultaneously accounting for the complexity of genotype-environment interaction (GE); however, unlike conventional GP models, DL has not been investigated for when genomics is linked with phenomics. In this study we used 2 wheat data sets (DS1 and DS2) to compare a novel DL method with conventional GP models. Models fitted for DS1 were GBLUP, gradient boosting machine (GBM), support vector regression (SVR) and the DL method. Results indicated that for 1 year, DL provided better GP accuracy than results obtained by the other models. However, GP accuracy obtained for other years indicated that the GBLUP model was slightly superior to the DL. DS2 is comprised only of genomic data from wheat lines tested for 3 years, 2 environments (drought and irrigated) and 2-4 traits. DS2 results showed that when predicting the irrigated environment with the drought environment, DL had higher accuracy than the GBLUP model in all analyzed traits and years. When predicting drought environment with information on the irrigated environment, the DL model and GBLUP model had similar accuracy. The DL method used in this study is novel and presents a strong degree of generalization as several modules can potentially be incorporated and concatenated to produce an output for a multi-input data structure.

Precise estimation of genomic regions controlling lodging resistance using a set of reciprocal chromosome segment substitution lines in rice.

Severe lodging has occurred in many improved rice varieties after the recent strong typhoons in East and Southeast Asian countries. The indica variety Takanari possesses strong culm characteristics due to its large section modulus, which indicates culm thickness, whereas the japonica variety Koshihikari is subject to substantial bending stress due to its thick cortical fibre tissue. To detect quantitative trait loci (QTLs) for lodging resistance and to eliminate the effects of genetic background, we used reciprocal chromosome segment substitution lines (CSSLs) derived from a cross between Koshihikari and Takanari. The oppositional effects of QTLs for section modulus were confirmed in both genetic backgrounds on chromosomes 1, 5 and 6, suggesting that these QTLs are not affected by the genetic background and are controlled independently by a single factor. The candidate region of a QTL for section modulus included SD1. The section modulus of NIL-sd1 was lower than that of Koshihikari, whereas the section modulus of NIL-SD1 was higher than that of Takanari. This result indicated that those regions regulate the culm thickness. The reciprocal effects of the QTLs for cortical fibre tissue thickness were confirmed in both genetic backgrounds on chromosome 9 using CSSLs.