Dataset Information

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

ABSTRACT: Phenomics technologies allow quantitative assessment of phenotypes across a larger number of plant genotypes compared to traditional phenotyping approaches. The utilization of such technologies has enabled the generation of multidimensional plant traits creating big datasets. However, to harness the power of phenomics technologies, more sophisticated data analysis methods are required. In this study, Aphanomyces root rot (ARR) resistance in 547 lentil accessions and lines was evaluated using Red-Green-Blue (RGB) images of roots. We created a dataset of 6,460 root images that were annotated by a plant breeder based on the disease severity. Two approaches, generalized linear model with elastic net regularization (EN) and convolutional neural network (CNN), were developed to classify disease resistance categories into three classes: resistant, partially resistant, and susceptible. The results indicated that the selected image features using EN models were able to classify three disease categories with an accuracy of up to 0.91 ± 0.004 (0.96 ± 0.005 resistant, 0.82 ± 0.009 partially resistant, and 0.92 ± 0.007 susceptible) compared to CNN with an accuracy of about 0.84 ± 0.009 (0.96 ± 0.008 resistant, 0.68 ± 0.026 partially resistant, and 0.83 ± 0.015 susceptible). The resistant class was accurately detected using both classification methods. However, partially resistant class was challenging to detect as the features (data) of the partially resistant class often overlapped with those of resistant and susceptible classes. Collectively, the findings provided insights on the use of phenomics techniques and machine learning approaches to provide quantitative measures of ARR resistance in lentil.

SUBMITTER: Marzougui A

PROVIDER: S-EPMC7870103 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

Marzougui Afef A Ma Yu Y McGee Rebecca J RJ Khot Lav R LR Sankaran Sindhuja S

Plant phenomics (Washington, D.C.) 20201113

Phenomics technologies allow quantitative assessment of phenotypes across a larger number of plant genotypes compared to traditional phenotyping approaches. The utilization of such technologies has enabled the generation of multidimensional plant traits creating big datasets. However, to harness the power of phenomics technologies, more sophisticated data analysis methods are required. In this study, Aphanomyces root rot (ARR) resistance in 547 lentil accessions and lines was evaluated using Red ...[more]

PMID: 33575665

Similar Datasets

Project description:Aphanomyces root rot (ARR) is a soil-borne disease that results in severe yield losses in lentil. The development of resistant cultivars is one of the key strategies to control this pathogen. However, the evaluation of disease severity is limited to visual scores that can be subjective. This study utilized image-based phenotyping approaches to evaluate Aphanomyces euteiches resistance in lentil genotypes in greenhouse (351 genotypes from lentil single plant/LSP derived collection and 191 genotypes from recombinant inbred lines/RIL using digital Red-Green-Blue/RGB and hyperspectral imaging) and field (173 RIL genotypes using unmanned aerial system-based multispectral imaging) conditions. Moderate to strong correlations were observed between RGB, multispectral, and hyperspectral derived features extracted from lentil shoots/roots and visual scores. In general, root features extracted from RGB imaging were found to be strongly associated with disease severity. With only three root traits, elastic net regression model was able to predict disease severity across and within multiple datasets (R 2 = 0.45-0.73 and RMSE = 0.66-1.00). The selected features could represent visual disease scores. Moreover, we developed twelve normalized difference spectral indices (NDSIs) that were significantly correlated with disease scores: two NDSIs for lentil shoot section - computed from wavelengths of 1170, 1160, 1270, and 1280 nm (0.12 ≤ |r| ≤ 0.24, P < 0.05) and ten NDSIs for lentil root sections - computed from wavelengths in the range of 630-670, 700-840, and 1320-1530 nm (0.10 ≤ |r| ≤ 0.50, P < 0.05). Root-derived NDSIs were more accurate in predicting disease scores with an R 2 of 0.54 (RMSE = 0.86), especially when the model was trained and tested on LSP accessions, compared to R 2 of 0.25 (RMSE = 1.64) when LSP and RIL genotypes were used as train and test datasets, respectively. Importantly, NDSIs - computed from wavelengths of 700, 710, 730, and 790 nm - had strong positive correlations with disease scores (0.35 ≤r ≤ 0.50, P < 0.0001), which was confirmed in field phenotyping with similar correlations using vegetation index with red edge wavelength (normalized difference red edge, 0.36 ≤ |r| ≤ 0.57, P < 0.0001). The adopted image-based phenotyping approaches can help plant breeders to objectively quantify ARR resistance and reduce the subjectivity in selecting potential genotypes.

Project description:Trichoderma species are opportunistic plant symbionts that are common in the root and rhizosphere ecosystems. Many Trichoderma species may enhance plant growth, nutrient acquisition, and disease resistance, and for these reasons, they are widely used in agriculture as biofertilizers or biocontrol agents. Host plant genotype and other microorganisms, such as root pathogens, may influence the efficacy of Trichoderma inoculants. Aphanomyces euteiches is an important soil-borne oomycete in western Canada that causes root rot in legume crops such as lentil and pea, and there is not yet any significantly resistant varieties or effective treatments available to control the disease. In this study, the composition of root-associated fungal communities and the abundance of Trichoderma species, T. harzianum strain T-22 and T. virens strain G41, was determined in the roots of eight Lens genotypes based on internal transcribed spacer (ITS) Illumina MiSeq paired-end sequencing, both in the presence and the absence of the root rot pathogen Aphanomyces euteiches. Biocontrol effects of T. harzianum on A. euteiches was also examined. Significant genotypic variations were observed in the composition of root-associated fungal communities and the abundance of the different Trichoderma species in the lentil roots. The presence of A. euteiches altered the composition of Trichoderma found associated to the lentil genotypes. Biocontrol of A. euteiches by T. harzianum T22 species was observed in vitro and positive correlations between the abundance of Trichoderma and plant root and shoot biomass were observed in vivo. These findings revealed that lentil genotype and infection by the phytopathogen A. euteiches greatly influenced the colonization of root-associated fungi and the abundance of the Trichoderma species, as well as the effect on plant growth promotion. The multipartite interactions observed among lentil genotypes, Trichoderma species and A. euteiches suggest possibilities to select compatible host-beneficial microbe combinations in lentil breeding programs and to develop application strategies to harness the beneficial effects of Trichoderma inoculants in sustainable crop production systems.

Project description:BackgroundRegularized generalized linear models (GLMs) are popular regression methods in bioinformatics, particularly useful in scenarios with fewer observations than parameters/features or when many of the features are correlated. In both ridge and lasso regularization, feature shrinkage is controlled by a penalty parameter λ. The elastic net introduces a mixing parameter α to tune the shrinkage continuously from ridge to lasso. Selecting α objectively and determining which features contributed significantly to prediction after model fitting remain a practical challenge given the paucity of available software to evaluate performance and statistical significance.ResultseNetXplorer builds on top of glmnet to address the above issues for linear (Gaussian), binomial (logistic), and multinomial GLMs. It provides new functionalities to empower practical applications by using a cross validation framework that assesses the predictive performance and statistical significance of a family of elastic net models (as α is varied) and of the corresponding features that contribute to prediction. The user can select which quality metrics to use to quantify the concordance between predicted and observed values, with defaults provided for each GLM. Statistical significance for each model (as defined by α) is determined based on comparison to a set of null models generated by random permutations of the response; the same permutation-based approach is used to evaluate the significance of individual features. In the analysis of large and complex biological datasets, such as transcriptomic and proteomic data, eNetXplorer provides summary statistics, output tables, and visualizations to help assess which subset(s) of features have predictive value for a set of response measurements, and to what extent those subset(s) of features can be expanded or reduced via regularization.ConclusionsThis package presents a framework and software for exploratory data analysis and visualization. By making regularized GLMs more accessible and interpretable, eNetXplorer guides the process to generate hypotheses based on features significantly associated with biological phenotypes of interest, e.g. to identify biomarkers for therapeutic responsiveness. eNetXplorer is also generally applicable to any research area that may benefit from predictive modeling and feature identification using regularized GLMs. The package is available under GPL-3 license at the CRAN repository, https://CRAN.R-project.org/package=eNetXplorer .

Project description:The cultivation of vining pea (Pisum sativum) faces a major constraint with root rot diseases, caused by a complex of soil-borne pathogens including the oomycetes Aphanomyces euteiches and Phytophtora pisi. Disease resistant commercial varieties are lacking but the landrace PI180693 is used as a source of partial resistance in ongoing pea breeding programs. In this study, the level of resistance and their interaction with A. euteiches virulence levels of six new back-crossed pea breeding lines, deriving from the cross between the susceptible commercial cultivar Linnea and PI180693, were evaluated for their resistance towards aphanomyces root rot in growth chamber and green house tests. Resistance towards mixed infections by A. euteiches and P. pisi and commercial production traits were evaluated in field trials. In growth chamber trials, pathogen virulence levels had a significant effect on plant resistance, as resistance was more consistent against A. euteiches strains exhibiting high or intermediate virulence compared with lowly virulent strains. In fact, line Z1701-1 showed to be significantly more resistant than both parents when inoculated with a lowly virulent strain. In two separate field trials in 2020, all six breeding lines performed equally well as the resistant parent PI180693 at sites only containing A. euteiches, as there were no differences in disease index. In mixed infections, PI180693 exhibited significantly lower disease index scores than Linnea. However, breeding lines displayed higher disease index scores compared with PI180693, indicating higher susceptibility towards P. pisi. Data on seedling emergence from the same field trials suggested that PI180693 was particularly sensitive towards seed decay/damping off disease caused by P. pisi. Furthermore, the breeding lines performed equally well as Linnea in traits important for green pea production, again emphasizing the commercial potential. In summary, we show that the resistance from PI180693 interacts with virulence levels of the pathogen A. euteiches and is less effective towards root rot caused by P. pisi. Our results show the potential use of combining PI180693 partial resistance against aphanomyces root rot with commercially favorable breeding traits in commercial breeding programs.

Dataset Information

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

Publications

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets