TrG2P: A transfer-learning-based tool integrating multi-trait data for accurate prediction of crop yield.

Yield prediction is the primary goal of genomic selection (GS)-assisted crop breeding. Because yield is a complex quantitative trait, making predictions from genotypic data is challenging. Transfer learning can produce an effective model for a target task by leveraging knowledge from a different, but related, source domain and is considered a great potential method for improving yield prediction by integrating multi-trait data. However, it has not previously been applied to genotype-to-phenotype prediction owing to the lack of an efficient implementation framework. We therefore developed TrG2P, a transfer-learning-based framework. TrG2P first employs convolutional neural networks (CNN) to train models using non-yield-trait phenotypic and genotypic data, thus obtaining pre-trained models. Subsequently, the convolutional layer parameters from these pre-trained models are transferred to the yield prediction task, and the fully connected layers are retrained, thus obtaining fine-tuned models. Finally, the convolutional layer and the first fully connected layer of the fine-tuned models are fused, and the last fully connected layer is trained to enhance prediction performance. We applied TrG2P to five sets of genotypic and phenotypic data from maize (Zea mays), rice (Oryza sativa), and wheat (Triticum aestivum) and compared its model precision to that of seven other popular GS tools: ridge regression best linear unbiased prediction (rrBLUP), random forest, support vector regression, light gradient boosting machine (LightGBM), CNN, DeepGS, and deep neural network for genomic prediction (DNNGP). TrG2P improved the accuracy of yield prediction by 39.9%, 6.8%, and 1.8% in rice, maize, and wheat, respectively, compared with predictions generated by the best-performing comparison model. Our work therefore demonstrates that transfer learning is an effective strategy for improving yield prediction by integrating information from non-yield-trait data. We attribute its enhanced prediction accuracy to the valuable information available from traits associated with yield and to training dataset augmentation. The Python implementation of TrG2P is available at https://github.com/lijinlong1991/TrG2P. The web-based tool is available at http://trg2p.ebreed.cn:81.

A Colletotrichum tabacum Effector Cte1 Targets and Stabilizes NbCPR1 to Suppress Plant Immunity.

Colletotrichum tabacum, causing anthracnose in tobacco, is a notorious plant pathogen threatening tobacco production globally. The underlying mechanisms of C. tabacum effectors that interfere with plant defense are not well known. Here, we identified a novel effector, Cte1, from C. tabacum, and its expression was upregulated in the biotrophic stage. We found that Cte1 depresses plant cell death initiated by BAX and inhibits reactive oxygen species (ROS) bursts triggered by flg22 and chitin in Nicotiana benthamiana. The CTE1 knockout mutants decrease the virulence of C. tabacum to N. benthamiana, and the Cte1 transgenic N. benthamiana increase susceptibility to C. tabacum, verifying that Cte1 is involved in the pathogenicity of C. tabacum. We demonstrated that Cte1 interacted with NbCPR1, a Constitutive expresser of Plant Resistance (CPR) protein in plants. Silencing of NbCPR1 expression attenuated the infection of C. tabacum, indicating that NbCPR1 negatively regulates plant immune responses. Cte1 stabilizes NbCPR1 in N. benthamiana. Our study shows that Cte1 suppresses plant immunity to facilitate C. tabacum infection by intervening in the native function of NbCPR1. [Formula: see text] The author(s) have dedicated the work to the public domain under the Creative Commons CC0 "No Rights Reserved" license by waiving all of his or her rights to the work worldwide under copyright law, including all related and neighboring rights, to the extent allowed by law, 2024.

Four closely related endornaviruses each with a low incidence in the phytopathogenic fungi Exserohilum turcicum or Bipolaris maydis.

Endornaviruses are known to occur widely in plants, fungi, and oomycetes, but our understanding of their diversity and distribution is limited. In this study, we report the discovery of four endornaviruses tentatively named Setosphaeria turcica endornavirus 1 (StEV1), Setosphaeria turcica endornavirus 2 (StEV2), Bipolaris maydis endornavirus 1 (BmEV1), and Bipolaris maydis endornavirus 2 (BmEV2). StEV1 and StEV2 infect Exserohilum turcicum, while BmEV1 and BmEV2 infect Bipolaris maydis. The four viruses encode a polyprotein with less than 40 % amino acid sequence identity to other known endornaviruses, indicating that they are novel, previously undescribed endornaviruses. However, StEV1 and BmEV1 share a sequence identity of 78 % at the full-genome level and 87 % at the polyprotein level, suggesting that they may belong to the same species. Our study also found that each of the four endornaviruses has an incidence of approximately 3.5 % to 5.5 % in E. turcicum or B. maydis. Interestingly, BmEV1 and BmEV2 were found to be unable to transmit between hosts of different vegetative incompatibility groups, which may explain their low incidence.

The complete chloroplast genome of Scutellaria barbata D. Don 1825 revealed the phylogenetic relationships of the Scutellaria genus.

Scutellaria barbata D. Don 1825 is an important medicinal plant distributed in wetlands about 2000 m above sea level and used to treat various diseases. The complete chloroplast genome of S. barbata is 152,050 bp with four subregions consisting of a large single-copy region (84,053 bp), a small single-copy region (17,517 bp), and a pair of inverted repeats (25,240 bp). In the chloroplast genome of S. barbata, 131 genes were detected, comprising 87 protein-encoding genes, eight ribosomal RNA (rRNA) genes, and 36 transfer RNA (tRNA) genes. Phylogenetic analysis based on the complete chloroplast genome and protein-coding DNA sequences of 27 related taxa of the genus (out group included Holmskioldia sanguinea and Tinnea aethiopica) indicates that S. barbata was made a clade with S. orthocalyx, and S. meehanioides was a sister to them. The first chloroplast genome of S. barbata was reported in this work, serving as a potential reference for important medicinal plants within the Scutellaria genus.

Four distinct isolates of a novel polymycovirus identified in Setosphaeria turcica.

Isolation and analysis of double-stranded RNA (dsRNA) from the phytopathogenic fungus Setosphaeria turcica f. sp. zeae revealed the presence of a new double-stranded RNA (dsRNA) virus, tentatively named "Setosphaeria turcica polymycovirus 2" (StPmV2). The genome of StPmV2 consists of five segments (dsRNA1-5), ranging in size from 965 bp to 2462 bp. Each dsRNA contains one open reading frame (ORF) flanked by 5' and 3' untranslated regions (UTRs) with conserved terminal sequences. The putative protein encoded by dsRNA1 shows 64.52% amino acid sequence identity to the RNA-dependent RNA polymerase (RdRp) of the most closely related virus, Cladosporium cladosporioides virus 1, which belongs to the family Polymycoviridae. dsRNAs 2-4 encode the putative coat protein, methyltransferase (MTR), and proline-alanine-serine-rich protein (PASrp), respectively, and dsRNA5 encodes a protein of unknown function. Phylogenetic analysis based on the RdRp protein indicated that StPmV2 clustered with members of the family Polymycoviridae and is therefore a new mycovirus belonging to the genus Polymycovirus in the family Polymycoviridae. In addition, three other distinct isolates of StPmV2 were identified: one isolated from S. turcica f. sp. zeae and two from S. turcica f. sp. sorghi. To our knowledge, this is the first report of a polymycovirus infecting both S. turcica f. sp. zeae and S. turcica f. sp. sorghi.

A variety test platform for the standardization and data quality improvement of crop variety tests.

Variety testing is an indispensable and essential step in the process of creating new improved varieties from breeding to adoption. The performance of the varieties can be compared and evaluated based on multi-trait data from multi-location variety tests in multiple years. Although high-throughput phenotypic platforms have been used for observing some specific traits, manual phenotyping is still widely used. The efficient management of large amounts of data is still a significant problem for crop variety testing. This study reports a variety test platform (VTP) that was created to manage the whole workflow for the standardization and data quality improvement of crop variety testing. Through the VTP, the phenotype data of varieties can be integrated and reused based on standardized data elements and datasets. Moreover, the information support and automated functions for the whole testing workflow help users conduct tests efficiently through a series of functions such as test design, data acquisition and processing, and statistical analyses. The VTP has been applied to regional variety tests covering more than seven thousand locations across the whole country, and then a standardized and authoritative phenotypic database covering five crops has been generated. In addition, the VTP can be deployed on either privately or publicly available high-performance computing nodes so that test management and data analysis can be conveniently done using a web-based interface or mobile application. In this way, the system can provide variety test management services to more small and medium-sized breeding organizations, and ensures the mutual independence and security of test data. The application of VTP shows that the platform can make variety testing more efficient and can be used to generate a reliable database suitable for meta-analysis in multi-omics breeding and variety development projects.