About this Research Topic
In recent decades, the interplay between the microbiome and the plant phenotype has become a crucial research focus in many microbiome-driven breeding programs. However, the conventional analyzing methods are underpowered to explore, analyze, predict, and exploit data derived from high throughput technologies such as meta-genomics, meta-transcriptomics, meta-proteomics, etc. These multi-omics analyses are prone to false positive errors and unable to detect the interaction effect between different variables, leading to a lack of insight into how the microbiome impacts the plant phenotype. To tackle this issue, researchers have developed advanced data analysis techniques to effectively integrate and analyze the data from multiple omics sources.
With the advent of machine-learning (ML) algorithms, the study of plant-associated microbiomes has taken a great leap forward, enabling researchers to gain deeper insight into the intricate relationships between plants, microbes, and their environment. These algorithms are designed for recognition, classification, and prediction of microbial composition, or engineering of microbiomes to produce desired phenotypic traits and improve productivity. ML models are capable of handling the challenging structure of microbiome data, which is characterized by compositionality, sparsity, and high dimensionality, to generate the most accurate predictions for targeted traits.
The aim of this special issue is to gather experts from the fields of plant microbiome, plant breeding, and computational biology, to discuss the latest progress and advancements in sophisticated approaches to comprehend plant-microbiome interactions and their role in improving crop yield and productivity. Moreover, we hope that this special issue will act as a catalyst for further exploring the potential of these tools for plant breeding programs, the development of sustainable agricultural practices, and for generating new ideas and strategies to unravel the complexities of plant-microbiome interactions. We are glad to invite all types of submissions, including original research articles, reviews, mini-reviews, and methodologies in this background which include but are not limited to:
• The use of ML algorithms to predict the dynamics and functions of plant-associated microbiomes.
• The use of ML algorithms to picture/recognize the assemblies of plant-associated microbiomes under diverse environmental conditions.
• Potential use of ML algorithm in microbiome engineering.
• Advanced models of ML for plant phenotyping.
• The contribution of computer vision, and ML methods to correlating plant microbiome and its phenotypic traits.
• Big data and predictive analytics in plant-microbiome interactions and characteristics.
• Contribution of ML methods to the development of sustainable agricultural practices.
We look forward to receiving your contributions to this special issue.
Keywords: plant phenotyping, plant breeding, machine learning models, metagenomics, high throughput sequencing, crop production, sustainable agricultural practices, plant-associated microbiomes
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.