Application of Deep Learning in Plant-Microbiota Association Analysis

Engineering agricultural soil microbiomes and predicting plant phenotypes

Plant growth-promoting rhizobacteria (PGPR) can improve crop yields, nutrient use efficiency, plant tolerance to stressors, and confer benefits to future generations of crops grown in the same soil. Unlocking the potential of microbial communities in the rhizosphere and endosphere is therefore of great interest for sustainable agriculture advancements. Before plant microbiomes can be engineered to confer desirable phenotypic effects on their plant hosts, a deeper understanding of the interacting factors influencing rhizosphere community structure and function is needed. Dealing with this complexity is becoming more feasible using computational approaches. In this review, we discuss recent advances at the intersection of experimental and computational strategies for the investigation of plant-microbiome interactions and the engineering of desirable soil microbiomes.

Interpretable machine learning decodes soil microbiome's response to drought stress

BACKGROUND

Extreme weather events induced by climate change, particularly droughts, have detrimental consequences for crop yields and food security. Concurrently, these conditions provoke substantial changes in the soil bacterial microbiota and affect plant health. Early recognition of soil affected by drought enables farmers to implement appropriate agricultural management practices. In this context, interpretable machine learning holds immense potential for drought stress classification of soil based on marker taxa.

RESULTS

This study demonstrates that the 16S rRNA-based metagenomic approach of Differential Abundance Analysis methods and machine learning-based Shapley Additive Explanation values provide similar information. They exhibit their potential as complementary approaches for identifying marker taxa and investigating their enrichment or depletion under drought stress in grass lineages. Additionally, the Random Forest Classifier trained on a diverse range of relative abundance data from the soil bacterial micobiome of various plant species achieves a high accuracy of 92.3 % at the genus rank for drought stress prediction. It demonstrates its generalization capacity for the lineages tested.

CONCLUSIONS

In the detection of drought stress in soil bacterial microbiota, this study emphasizes the potential of an optimized and generalized location-based ML classifier. By identifying marker taxa, this approach holds promising implications for microbe-assisted plant breeding programs and contributes to the development of sustainable agriculture practices. These findings are crucial for preserving global food security in the face of climate change.

Customized plant microbiome engineering for food security

Plant microbiomes play a vital role in promoting plant growth and resilience to cope with environmental stresses. Plant microbiome engineering holds significant promise to increase crop yields, but there is uncertainty about how this can best be achieved. We propose a step-by-step approach involving customized direct and indirect methods to condition soils and to match plants and microbiomes. Although three approaches, namely the development of (i) 'plant- and microbe-friendly' soils, (ii) 'microbe-friendly' plants, and (iii) 'plant-friendly' microbiomes, have been successfully tested in isolation, we propose that the combination of all three may lead to a step-change towards higher and more stable crop yields. This review aims to provide knowledge, future directions, and practical guidance to achieve this goal via customized plant microbiome engineering.

Review: Research progress on seasonal succession of phyllosphere microorganisms

Phyllosphere microorganisms have recently attracted the attention of scientists studying plant microbiomes. The origin, diversity, functions, and interactions of phyllosphere microorganisms have been extensively explored. Many experiments have demonstrated seasonal cycles of phyllosphere microbes. However, a comprehensive comparison of these separate investigations to characterize seasonal trends in phyllosphere microbes of woody and herbaceous plants has not been conducted. In this review, we explored the dynamic changes of phyllosphere microorganisms in woody and non-woody plants with the passage of the season, sought to find the driving factors, summarized these texts, and thought about future research trends regarding the application of phyllosphere microorganisms in agricultural production. Seasonal trends in phyllosphere microorganisms of herbaceous and woody plants have similarities and differences, but extensive experimental validation is needed. Climate, insects, hosts, microbial interactions, and anthropogenic activities are the diverse factors that influence seasonal variation in phyllosphere microorganisms.

Exercise and microbiome: From big data to therapy

Exercise is a vital component in maintaining optimal health and serves as a prospective therapeutic intervention for various diseases. The human microbiome, comprised of trillions of microorganisms, plays a crucial role in overall health. Given the advancements in microbiome research, substantial databases have been created to decipher the functionality and mechanisms of the microbiome in health and disease contexts. This review presents an initial overview of microbiomics development and related databases, followed by an in-depth description of the multi-omics technologies for microbiome. It subsequently synthesizes the research pertaining to exercise-induced modifications of the microbiome and diseases that impact the microbiome. Finally, it highlights the potential therapeutic implications of an exercise-modulated microbiome in intestinal disease, obesity and diabetes, cardiovascular disease, and immune/inflammation-related diseases.

Comparative analysis of tissue-specific genes in maize based on machine learning models: CNN performs technically best, LightGBM performs biologically soundest

Introduction: With the advancement of RNA-seq technology and machine learning, training large-scale RNA-seq data from databases with machine learning models can generally identify genes with important regulatory roles that were previously missed by standard linear analytic methodologies. Finding tissue-specific genes could improve our comprehension of the relationship between tissues and genes. However, few machine learning models for transcriptome data have been deployed and compared to identify tissue-specific genes, particularly for plants. Methods: In this study, an expression matrix was processed with linear models (Limma), machine learning models (LightGBM), and deep learning models (CNN) with information gain and the SHAP strategy based on 1,548 maize multi-tissue RNA-seq data obtained from a public database to identify tissue-specific genes. In terms of validation, V-measure values were computed based on k-means clustering of the gene sets to evaluate their technical complementarity. Furthermore, GO analysis and literature retrieval were used to validate the functions and research status of these genes. Results: Based on clustering validation, the convolutional neural network outperformed others with higher V-measure values as 0.647, indicating that its gene set could cover as many specific properties of various tissues as possible, whereas LightGBM discovered key transcription factors. The combination of three gene sets produced 78 core tissue-specific genes that had previously been shown in the literature to be biologically significant. Discussion: Different tissue-specific gene sets were identified due to the distinct interpretation strategy for machine learning models and researchers may use multiple methodologies and strategies for tissue-specific gene sets based on their goals, types of data, and computational resources. This study provided comparative insight for large-scale data mining of transcriptome datasets, shedding light on resolving high dimensions and bias difficulties in bioinformatics data processing.

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

MOTIVATION

Single-cell RNA-sequencing (scRNA-seq) technologies provide an opportunity to infer cell-specific gene regulatory networks (GRNs), which is an important challenge in systems biology. Although numerous methods have been developed for inferring GRNs from scRNA-seq data, it is still a challenge to deal with cellular heterogeneity.

RESULTS

To address this challenge, we developed an interpretable transformer-based method namely STGRNS for inferring GRNs from scRNA-seq data. In this algorithm, gene expression motif technique was proposed to convert gene pairs into contiguous sub-vectors, which can be used as input for the transformer encoder. By avoiding missing phase-specific regulations in a network, gene expression motif can improve the accuracy of GRN inference for different types of scRNA-seq data. To assess the performance of STGRNS, we implemented the comparative experiments with some popular methods on extensive benchmark datasets including 21 static and 27 time-series scRNA-seq dataset. All the results show that STGRNS is superior to other comparative methods. In addition, STGRNS was also proved to be more interpretable than "black box" deep learning methods, which are well-known for the difficulty to explain the predictions clearly.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/zhanglab-wbgcas/STGRNS.

Compositionality, sparsity, spurious heterogeneity, and other data-driven challenges for machine learning algorithms within plant microbiome studies

The plant-associated microbiome is a key component of plant systems, contributing to their health, growth, and productivity. The application of machine learning (ML) in this field promises to help untangle the relationships involved. However, measurements of microbial communities by high-throughput sequencing pose challenges for ML. Noise from low sample sizes, soil heterogeneity, and technical factors can impact the performance of ML. Additionally, the compositional and sparse nature of these datasets can impact the predictive accuracy of ML. We review recent literature from plant studies to illustrate that these properties often go unmentioned. We expand our analysis to other fields to quantify the degree to which mitigation approaches improve the performance of ML and describe the mathematical basis for this. With the advent of accessible analytical packages for microbiome data including learning models, researchers must be familiar with the nature of their datasets.

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

Unveiling how genetic variations lead to phenotypic variations is one of the key questions in evolutionary biology, genetics, and biomedical research. Deep mutational scanning (DMS) technology has allowed the mapping of tens of thousands of genetic variations to phenotypic variations efficiently and economically. Since its first systematic introduction about a decade ago, we have witnessed the use of deep mutational scanning in many research areas leading to scientific breakthroughs. Also, the methods in each step of deep mutational scanning have become much more versatile thanks to the oligo-synthesizing technology, high-throughput phenotyping methods and deep sequencing technology. However, each specific possible step of deep mutational scanning has its pros and cons, and some limitations still await further technological development. Here, we discuss recent scientific accomplishments achieved through the deep mutational scanning and describe widely used methods in each step of deep mutational scanning. We also compare these different methods and analyze their advantages and disadvantages, providing insight into how to design a deep mutational scanning study that best suits the aims of the readers' projects.

Accurate determination of causalities in gene regulatory networks by dissecting downstream target genes

Accurate determination of causalities between genes is a challenge in the inference of gene regulatory networks (GRNs) from the gene expression profile. Although many methods have been developed for the reconstruction of GRNs, most of them are insufficient in determining causalities or regulatory directions. In this work, we present a novel method, namely, DDTG, to improve the accuracy of causality determination in GRN inference by dissecting downstream target genes. In the proposed method, the topology and hierarchy of GRNs are determined by mutual information and conditional mutual information, and the regulatory directions of GRNs are determined by Taylor formula-based regression. In addition, indirect interactions are removed with the sparseness of the network topology to improve the accuracy of network inference. The method is validated on the benchmark GRNs from DREAM3 and DREAM4 challenges. The results demonstrate the superior performance of the DDTG method on causality determination of GRNs compared to some popular GRN inference methods. This work provides a useful tool to infer the causal gene regulatory network.

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

Presently, agriculture worldwide is facing the major challenge of feeding the increasing population sustainably. The conventional practices have not only failed to meet the projected needs, but also led to tremendous environmental consequences. Hence, to ensure a food-secure and environmentally sound future, the major thrust is on sustainable alternatives. Due to challenges associated with conventional means of application of biocontrol agents in the management of biotic stresses in agro-ecosystems, significant transformations in this context is needed. The crucial role played by soil microbiomes in efficiently and sustainably managing the agricultural production has unfolded a newer approach of rhizospheric engineering that shows immense promise in mitigating biotic stresses in an eco-friendly manner. The strategy of generating synthetic microbial communities (SynCom), by integrating omics approaches with traditional techniques of enumeration and in-depth analysis of plant-microbe interactions, is encouraging. The review discusses the significance of the rhizospheric microbiome in plant's fitness, and its manipulation for enhancing plant attributes. The focus of the review is to critically analyze the potential tools for the design and utilization of SynCom as a sustainable approach for rhizospheric engineering to ameliorate biotic stresses in plants. Further, based on the synthesis of reports in the area, we have put forth possible solutions to some of the critical issues that impair the large-scale application of SynComs in agriculture.

Plant-Microbiota Interactions in Abiotic Stress Environments

Abiotic stress adversely affects cellular homeostasis and ultimately impairs plant growth, posing a serious threat to agriculture. Climate change modeling predicts increasing occurrences of abiotic stresses such as drought and extreme temperature, resulting in decreasing the yields of major crops such as rice, wheat, and maize, which endangers food security for human populations. Plants are associated with diverse and taxonomically structured microbial communities that are called the plant microbiota. Plant microbiota often assist plant growth and abiotic stress tolerance by providing water and nutrients to plants and modulating plant metabolism and physiology and, thus, offer the potential to increase crop production under abiotic stress. In this review, we summarize recent progress on how abiotic stress affects plants, microbiota, plant-microbe interactions, and microbe-microbe interactions, and how microbes affect plant metabolism and physiology under abiotic stress conditions, with a focus on drought, salt, and temperature stress. We also discuss important steps to utilize plant microbiota in agriculture under abiotic stress.[Formula: see text] Copyright © 2022 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.