Application of Deep Learning in Plant–Microbiota Association Analysis

Abstract

Unraveling the association between microbiome and plant phenotype can illustrate the effect of microbiome on host and then guide the agriculture management. Adequate identification of species and appropriate choice of models are two challenges in microbiome data analysis. Computational models of microbiome data could help in association analysis between the microbiome and plant host. The deep learning methods have been widely used to learn the microbiome data due to their powerful strength of handling the complex, sparse, noisy, and high-dimensional data. Here, we review the analytic strategies in the microbiome data analysis and describe the applications of deep learning models for plant–microbiome correlation studies. We also introduce the application cases of different models in plant–microbiome correlation analysis and discuss how to adapt the models on the critical steps in data processing. From the aspect of data processing manner, model structure, and operating principle, most deep learning models are suitable for the plant microbiome data analysis. The ability of feature representation and pattern recognition is the advantage of deep learning methods in modeling and interpretation for association analysis. Based on published computational experiments, the convolutional neural network and graph neural networks could be recommended for plant microbiome analysis.

Deep mutational scanning: A versatile tool in systematically mapping genotypes to phenotypes

“…Nevertheless, endogenous DMS will become available soon with improved precision in genome editing technologies and transformation/transfection efficiencies. While DMS has been applied to various organisms, including humans, viruses, bacteria and yeast, interestingly, there is no DMS research on plant genes, even though mapping genotypes to phenotypes on the plant is both important and challenging ( Voichek and Weigel, 2020 ; Deng et al, 2021 ). The reason could be the technical challenges in developing a high throughput phenotyping assay with the designed mutation pools.…”

Combating biotic stresses in plants by synthetic microbial communities: Principles, applications and challenges

“…The platform can be designed to run multiple trials over a stipulated period to predict the optimum combinations of SynCom for a given objective. Deng et al (2021b) probed into the potential of deep learning and its potential as a more powerful tool compared to conventional ML in understanding the interactions in a microbiome. They proposed a combination of amplicon sequencing and shotgun sequencing for gaining a comprehensive understanding to engineer the plant microbiome for offering services under stress.…”

STGRNS: an interpretable transformer-based method for inferring gene regulatory networks from single-cell transcriptomic data

“…Secondly, this procedure is time-consuming, and since it alters the format of scRNA-seq data, the outcomes predicted by these computational approaches utilizing CNNs cannot be wholly elucidated. Nevertheless, CNN-based models have achieved notable success in various biological tasks ( Deng et al 2021 ; Greener et al 2022 ). In general, CNN-like models lack of ability to capture global information due to their limited receptive ( Khan et al 2020 ).…”