1
|
Chen C, Bhuiyan SA, Ross E, Powell O, Dinglasan E, Wei X, Atkin F, Deomano E, Hayes B. Genomic prediction for sugarcane diseases including hybrid Bayesian-machine learning approaches. FRONTIERS IN PLANT SCIENCE 2024; 15:1398903. [PMID: 38751840 PMCID: PMC11095127 DOI: 10.3389/fpls.2024.1398903] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Accepted: 04/15/2024] [Indexed: 05/18/2024]
Abstract
Sugarcane smut and Pachymetra root rots are two serious diseases of sugarcane, with susceptible infected crops losing over 30% of yield. A heritable component to both diseases has been demonstrated, suggesting selection could improve disease resistance. Genomic selection could accelerate gains even further, enabling early selection of resistant seedlings for breeding and clonal propagation. In this study we evaluated four types of algorithms for genomic predictions of clonal performance for disease resistance. These algorithms were: Genomic best linear unbiased prediction (GBLUP), including extensions to model dominance and epistasis, Bayesian methods including BayesC and BayesR, Machine learning methods including random forest, multilayer perceptron (MLP), modified convolutional neural network (CNN) and attention networks designed to capture epistasis across the genome-wide markers. Simple hybrid methods, that first used BayesR/GWAS to identify a subset of 1000 markers with moderate to large marginal additive effects, then used attention networks to derive predictions from these effects and their interactions, were also developed and evaluated. The hypothesis for this approach was that using a subset of markers more likely to have an effect would enable better estimation of interaction effects than when there were an extremely large number of possible interactions, especially with our limited data set size. To evaluate the methods, we applied both random five-fold cross-validation and a structured PCA based cross-validation that separated 4702 sugarcane clones (that had disease phenotypes and genotyped for 26k genome wide SNP markers) by genomic relationship. The Bayesian methods (BayesR and BayesC) gave the highest accuracy of prediction, followed closely by hybrid methods with attention networks. The hybrid methods with attention networks gave the lowest variation in accuracy of prediction across validation folds (and lowest MSE), which may be a criteria worth considering in practical breeding programs. This suggests that hybrid methods incorporating the attention mechanism could be useful for genomic prediction of clonal performance, particularly where non-additive effects may be important.
Collapse
Affiliation(s)
- Chensong Chen
- Center for Animal Science, The Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, QLD, Australia
| | - Shamsul A. Bhuiyan
- Sugar Research Australia, Woodford, QLD, Australia
- Queensland Micro- and Nanotechnology Centre, Griffith University, Nathan, QLD, Australia
| | - Elizabeth Ross
- Center for Animal Science, The Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, QLD, Australia
| | - Owen Powell
- Center for Crop Science, The Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, QLD, Australia
| | - Eric Dinglasan
- Center for Animal Science, The Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, QLD, Australia
| | - Xianming Wei
- Sugar Research Australia, Indooroopilly, QLD, Australia
| | | | - Emily Deomano
- Sugar Research Australia, Indooroopilly, QLD, Australia
| | - Ben Hayes
- Center for Animal Science, The Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, QLD, Australia
| |
Collapse
|
2
|
Jabran M, Ali MA, Zahoor A, Muhae-Ud-Din G, Liu T, Chen W, Gao L. Intelligent reprogramming of wheat for enhancement of fungal and nematode disease resistance using advanced molecular techniques. FRONTIERS IN PLANT SCIENCE 2023; 14:1132699. [PMID: 37235011 PMCID: PMC10206142 DOI: 10.3389/fpls.2023.1132699] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/27/2022] [Accepted: 04/19/2023] [Indexed: 05/28/2023]
Abstract
Wheat (Triticum aestivum L.) diseases are major factors responsible for substantial yield losses worldwide, which affect global food security. For a long time, plant breeders have been struggling to improve wheat resistance against major diseases by selection and conventional breeding techniques. Therefore, this review was conducted to shed light on various gaps in the available literature and to reveal the most promising criteria for disease resistance in wheat. However, novel techniques for molecular breeding in the past few decades have been very fruitful for developing broad-spectrum disease resistance and other important traits in wheat. Many types of molecular markers such as SCAR, RAPD, SSR, SSLP, RFLP, SNP, and DArT, etc., have been reported for resistance against wheat pathogens. This article summarizes various insightful molecular markers involved in wheat improvement for resistance to major diseases through diverse breeding programs. Moreover, this review highlights the applications of marker assisted selection (MAS), quantitative trait loci (QTL), genome wide association studies (GWAS) and the CRISPR/Cas-9 system for developing disease resistance against most important wheat diseases. We also reviewed all reported mapped QTLs for bunts, rusts, smuts, and nematode diseases of wheat. Furthermore, we have also proposed how the CRISPR/Cas-9 system and GWAS can assist breeders in the future for the genetic improvement of wheat. If these molecular approaches are used successfully in the future, they can be a significant step toward expanding food production in wheat crops.
Collapse
Affiliation(s)
- Muhammad Jabran
- State Key Laboratory for Biology of Plant Diseases, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Muhammad Amjad Ali
- Department of Plant Pathology, University of Agriculture, Faisalabad, Pakistan
| | - Adil Zahoor
- Department of Biotechnology, Chonnam National University, Yeosu, Republic of Korea
| | - Ghulam Muhae-Ud-Din
- State Key Laboratory for Biology of Plant Diseases, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Taiguo Liu
- State Key Laboratory for Biology of Plant Diseases, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Wanquan Chen
- State Key Laboratory for Biology of Plant Diseases, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Li Gao
- State Key Laboratory for Biology of Plant Diseases, Institute of Plant Protection, Chinese Academy of Agricultural Sciences, Beijing, China
| |
Collapse
|
3
|
Gouka L, Raaijmakers JM, Cordovez V. Ecology and functional potential of phyllosphere yeasts. TRENDS IN PLANT SCIENCE 2022; 27:1109-1123. [PMID: 35842340 DOI: 10.1016/j.tplants.2022.06.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/20/2021] [Revised: 05/20/2022] [Accepted: 06/14/2022] [Indexed: 05/20/2023]
Abstract
The phyllosphere (i.e., the aerial parts of plants) harbors a rich microbial life, including bacteria, fungi, viruses, and yeasts. Current knowledge of yeasts stems primarily from industrial and medical research on Saccharomyces cerevisiae and Candida albicans, both of which can be found on plant tissues. For most other yeasts found in the phyllosphere, little is known about their ecology and functions. Here, we explore the diversity, dynamics, interactions, and genomics of yeasts associated with plant leaves and how tools and approaches developed for model yeasts can be adopted to disentangle the ecology and natural functions of phyllosphere yeasts. A first genomic survey exemplifies that we have only scratched the surface of the largely unexplored functional potential of phyllosphere yeasts.
Collapse
Affiliation(s)
- Linda Gouka
- Department of Microbial Ecology, Netherlands Institute of Ecology, Wageningen, The Netherlands
| | - Jos M Raaijmakers
- Department of Microbial Ecology, Netherlands Institute of Ecology, Wageningen, The Netherlands; Institute of Biology, Leiden University, Leiden, The Netherlands
| | - Viviane Cordovez
- Department of Microbial Ecology, Netherlands Institute of Ecology, Wageningen, The Netherlands.
| |
Collapse
|