Machine learning for genomic and pedigree prediction in sugarcane.

Sugarcane (Saccharum spp.) plays a crucial role in global sugar production; however, the efficiency of breeding programs has been hindered by its heterozygous polyploid genomes. Considering non-additive genetic effects is essential in genome prediction (GP) models of crops with highly heterozygous polyploid genomes. This study incorporates non-additive genetic effects and pedigree information using machine learning methods to track sugarcane breeding lines and enhance the prediction by assessing the degree of association between genotypes. This study measured the stalk biomass and sugar content of 297 clones from 87 families within a breeding population used in the Japanese sugarcane breeding program. Subsequently, we conducted analyses based on the marker genotypes of 33,149 single-nucleotide polymorphisms. To validate the accuracy of GP in the population, we first predicted the prediction accuracy of the best linear unbiased prediction (BLUP) based on a genomic relationship matrix. Prediction accuracy was assessed using two different cross-validation methods: repeated 10-fold cross-validation and leave-one-family-out cross-validation. The accuracy of GP of the first and second methods ranged from 0.36 to 0.74 and 0.15 to 0.63, respectively. Next, we compared the prediction accuracy of BLUP and two machine learning methods: random forests and simulation annealing ensemble (SAE), a newly developed machine learning method that explicitly models the interaction between variables. Both pedigree and genomic information were utilized as input in these methods. Through repeated 10-fold cross-validation, we found that the accuracy of the machine learning methods consistently surpassed that of BLUP in most cases. In leave-one-family-out cross-validation, SAE demonstrated the highest accuracy among the methods. These results underscore the effectiveness of GP in Japanese sugarcane breeding and highlight the significant potential of machine learning methods.

A Data-Driven Approach to Sugarcane Breeding Programs with Agronomic Characteristics and Amino Acid Constituent Profiling.

Sugarcane (Saccharum spp. hybrids) and its processed products have supported local industries such as those in the Nansei Islands, Japan. To improve the sugarcane quality and productivity, breeders select better clones by evaluating agronomic characteristics, such as commercially recoverable sugar and cane yield. However, other constituents in sugarcane remain largely unutilized in sugarcane breeding programs. This study aims to establish a data-driven approach to analyze agronomic characteristics from breeding programs. This approach also determines a correlation between agronomic characteristics and free amino acid composition to make breeding programs more efficient. Sugarcane was sampled in clones in the later stage of breeding selection and cultivars from experimental fields on Tanegashima Island. Principal component analysis and hierarchical cluster analysis using agronomic characteristics revealed the diversity and variability of each sample, and the data-driven approach classified cultivars and clones into three groups based on yield type. A comparison of free amino acid constituents between these groups revealed significant differences in amino acids such as asparagine and glutamine. This approach dealing with a large volume of data on agronomic characteristics will be useful for assessing the characteristics of potential clones under selection and accelerating breeding programs.

Genome-scale CRISPR-Cas9 screen identifies host factors as potential therapeutic targets for SARS-CoV-2 infection.

Although many host factors important for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection have been reported, the mechanisms by which the virus interacts with host cells remain elusive. Here, we identified tripartite motif containing (TRIM) 28, TRIM33, euchromatic histone lysine methyltransferase (EHMT) 1, and EHMT2 as proviral factors involved in SARS-CoV-2 infection by CRISPR-Cas9 screening. Our result suggested that TRIM28 may play a role in viral particle formation and that TRIM33, EHMT1, and EHMT2 may be involved in viral transcription and replication. UNC0642, a compound that specifically inhibits the methyltransferase activity of EHMT1/2, strikingly suppressed SARS-CoV-2 growth in cultured cells and reduced disease severity in a hamster infection model. This study suggests that EHMT1/2 may be a therapeutic target for SARS-CoV-2 infection.

RENGE infers gene regulatory networks using time-series single-cell RNA-seq data with CRISPR perturbations.

Single-cell RNA-seq analysis coupled with CRISPR-based perturbation has enabled the inference of gene regulatory networks with causal relationships. However, a snapshot of single-cell CRISPR data may not lead to an accurate inference, since a gene knockout can influence multi-layered downstream over time. Here, we developed RENGE, a computational method that infers gene regulatory networks using a time-series single-cell CRISPR dataset. RENGE models the propagation process of the effects elicited by a gene knockout on its regulatory network. It can distinguish between direct and indirect regulations, which allows for the inference of regulations by genes that are not knocked out. RENGE therefore outperforms current methods in the accuracy of inferring gene regulatory networks. When used on a dataset we derived from human-induced pluripotent stem cells, RENGE yielded a network consistent with multiple databases and literature. Accurate inference of gene regulatory networks by RENGE would enable the identification of key factors for various biological systems.