Application of Deep Learning in Plant-Microbiota Association Analysis.

Zhiyu Deng,Jinming Zhang,Junya Li,Xiujun Zhang

doi:10.3389/fgene.2021.697090

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.

Highlights

The plant-associated microbiota refers to the whole microorganisms colonizing inside the plant organs and on the plant surface, which includes rhizosphere, phyllosphere, and endophyte microbiome (Muller et al, 2016)
We summarize the progress of deep learning (DL) methods and its advantages compared with the classical machine learning (ML) methods and the pipelines for extracting the microbiome trait and perceiving its link to important plant agricultural phenotypes
The association study between plant microbiome and host plant phenotype can be considered as a data mining strategy that extracts composition and quantity features from microbiome sequence data

Summary

INTRODUCTION

The plant-associated microbiota refers to the whole microorganisms colonizing inside the plant organs and on the plant surface, which includes rhizosphere, phyllosphere, and endophyte microbiome (Muller et al, 2016). Deep Learning for Plant-Microbiota Associations and predict the host phenotype in advance. Metagenomic shotgun sequencing makes the acquisition of functional information possible (Breitwieser et al, 2019). By means of identification of microbial composition, comparison of different communities, inference of microbial functions, and the metagenome-wide association studies (MWAS) can dig out the associations between communities and plant phenotypes (Wang and Jia, 2016). To identify significant associated microbes, the p-values of associations are first estimated by Wilcoxon rank-sum test and computed by multiple testing adjustments (Xu et al, 2019) In this narrative review, we talk about the present researches of associations between the microbiome and plant productivity or resistance to stress. The functional evidences indicating causalities or interactions in plant–microbe network under complex and varied environmental conditions would be found (Toju et al, 2018b)

Methods for Microbiome Data Analysis

Findings

CONCLUSION