Background: Selecting a parsimonious set of informative genes to build highly generalized performance classifier is the most important task for the analysis of tumor microarray expression data. Many existing gene pair evaluation methods cannot highlight diverse patterns of gene pairs only used one strategy of vertical comparison and horizontal comparison, while individual-gene-ranking method ignores redundancy and synergy among genes. Results: Here we proposed a novel score measure named relative simplicity (RS). We evaluated gene pairs according to integrating vertical comparison with horizontal comparison, finally built RS-based direct classifier (RS-based DC) based on a set of informative genes capable of binary discrimination with a paired votes strategy. Nine multi-class gene expression datasets involving human cancers were used to validate the performance of new method. Compared with the nine reference models, RS-based DC received the highest average independent test accuracy (91.40 %), the best generalization performance and the smallest informative average gene number (20.56). Compared with the four reference feature selection methods, RS also received the highest average test accuracy in three classifiers (Naïve Bayes, k-Nearest Neighbor and Support Vector Machine), and only RS can improve the performance of SVM. Conclusions: Diverse patterns of gene pairs could be highlighted more fully while integrating vertical comparison with horizontal comparison strategy. DC core classifier can effectively control over-fitting. RS-based feature selection method combined with DC classifier can lead to more robust selection of informative genes and classification accuracy.

Lodging reduces rice yield, but increasing lodging resistance (LR) usually limits yield potential. Stem strength and leaf type are major traits related to LR and yield, respectively. Hence, understanding the genetic basis of stem strength and leaf type is of help to reduce lodging and increase yield in LR breeding. Here, we carried out an association analysis to identify quantitative trait locus (QTLs) affecting stem strength-related traits (internode length/IL, stem wall thickness/SWT, stem outer diameter/SOD, and stem inner diameter/SID) and leaf type-associated traits (Flag leaf length/FLL, Flag leaf angle/FLA, Flag leaf width/FLW, leaf-rolling/LFR and SPAD/Soil, and plant analyzer development) using a diverse panel of 550 accessions and evaluated over two years. Genome-wide association study (GWAS) using 4,076,837 high-quality single-nucleotide polymorphisms (SNPs) identified 89 QTLs for the nine traits. Next, through “gene-based association analysis, haplotype analysis, and functional annotation”, the scope was narrowed down step by step. Finally, we identified 21 candidate genes in 9 important QTLs that included four reported genes (TUT1, OsCCC1, CFL1, and ACL-D), and seventeen novel candidate genes. Introgression of alleles, which are beneficial for both stem strength and leaf type, or pyramiding stem strength alleles and leaf type alleles, can be employed for LR breeding. All in all, the experimental data and the identified candidate genes in this study provide a useful reference for the genetic improvement of rice LR.

Genetic improvement of grain quality is more challenging in hybrid rice than in inbred rice due to additional nonadditive effects such as dominance. Here, we describe a pipeline developed for joint analysis of phenotypes, effects, and generations (JPEG). As a demonstration, we analyze 12 grain quality traits of 113 inbred lines (male parents), five tester lines (female parents), and 565 (113×5) of their hybrids. We sequence the parents for single nucleotide polymorphisms calling and infer the genotypes of the hybrids. Genome-wide association studies with JPEG identify 128 loci associated with at least one of the 12 traits, including 44, 97, and 13 loci with additive effects, dominant effects, and both additive and dominant effects, respectively. These loci together explain more than 30% of the genetic variation in hybrid performance for each of the traits. The JEPG statistical pipeline can help to identify superior crosses for breeding rice hybrids with improved grain quality.

Background: Plant variety identification is the one most important of agricultural systems. Development of DNA marker profiles of released varieties to compare with candidate variety or future variety is required. However, strictly speaking, scientists did not use most existing variety identification techniques for “identification” but for “distinction of a limited number of cultivars,” of which generalization ability always not be well estimated. Because many varieties have similar genetic backgrounds, even some essentially derived varieties (EDVs) are involved, which brings difficulties for identification and breeding progress. A fast, accurate variety identification method, which also has good performance on EDV determination, needs to be developed.Results: In this study, with the strategy of “Divide and Conquer,” a variety identification method Conditional Random Selection (CRS) method based on SNP of the whole genome of 3024 rice varieties was developed and be applied in essentially derived variety (EDV) identification of rice. CRS is a fast, efficient, and automated variety identification method. Meanwhile, in practical, with the optimal threshold of identity score searched in this study, the set of SNP (including 390 SNPs) showed optimal performance on EDV and non-EDV identification in two independent testing datasets.Conclusion: This approach first selected a minimal set of SNPs to discriminate non-EDVs in the 3000 Rice Genome Project, then united several simplified SNP sets to improve its generalization ability for EDV and non-EDV identification in testing datasets. The results suggested that the CRS method outperformed traditional feature selection methods. Furthermore, it provides a new way to screen out core SNP loci from the whole genome for DNA fingerprinting of crop varieties and be useful for crop breeding.

Rice yield per plant has a complex genetic architecture, which is mainly determined by its three component traits: the number of grains per panicle (GPP), kilo-grain weight (KGW), and tillers per plant (TP). Exploring ideotype breeding based on selection for genetically less complex component traits is an alternative route for further improving rice production. To understand the genetic basis of the relationship between rice yield and component traits, we investigated the four traits of two rice hybrid populations (575 + 1495 F₁) in different environments and conducted meta-analyses of genome-wide association study (meta-GWAS). In total, 3589 significant loci for three components traits were detected, while only 3 loci for yield were detected. It indicated that rice yield is mainly controlled by minor-effect loci and hardly to be identified. Selecting quantitative trait locus/gene affected component traits to further enhance yield is recommended. Mendelian randomization design is adopted to investigate the genetic effects of loci on yield through component traits and estimate the genetic relationship between rice yield and its component traits by these loci. The loci for GPP or TP mainly had a positive genetic effect on yield, but the loci for KGW with different direction effects (positive effect or negative effect). Additionally, TP (Beta = 1.865) has a greater effect on yield than KGW (Beta = 1.016) and GPP (Beta = 0.086). Five significant loci for component traits that had an indirect effect on yield were identified. Pyramiding superior alleles of the five loci revealed improved yield. A combination of direct and indirect effects may better contribute to the yield potential of rice. Our findings provided a rationale for using component traits as indirect indices to enhanced rice yield, which will be helpful for further understanding the genetic basis of yield and provide valuable information for improving rice yield potential.

Enhancing early selection through genomic estimated breeding values is pivotal for reducing generation intervals and accelerating breeding programs. Recently, deep learning (DL) approaches have gained prominence in genomic prediction (GP). Here, we introduce a novel DL framework for GP based on Elastic Net feature selection and bidirectional encoder representations from transformer's embedding and multi-head attention pooling (EBMGP). EBMGP applies Elastic Net for the selection of features, thereby diminishing the computational burden and bolstering the predictive accuracy. In EBMGP, SNPs are treated as “words,” and groups of adjacent SNPs with similar LD levels are considered “sentences.” By applying bidirectional encoder representations from transformers embeddings, this method models SNPs in a manner analogous to human language, capturing complex genetic interactions at both the “word” and “sentence” scales. This flexible representation seamlessly integrates into any DL network and demonstrates a marked improvement in predictive performance for EBMGP and SoyDNGP compared to the widely used one-hot representation. We propose multi-head attention pooling, which can adaptively assign weights to features while learning features from multiple subspaces through multi-heads for a high level of semantic understanding. In a comprehensive comparative analysis across four diverse plant and animal datasets, EBMGP outperformed competing models in 13 out of 16 tasks, achieving accuracy gains ranging from 0.74 to 9.55% over the second-best model. These results underscore EBMGP’s robustness in genomic prediction and highlight its potential for deep learning applications in life sciences.