About this Research Topic
Due to the success of Microbiome and Machine Learning, which collected research results and perspectives of researchers working in the field of machine learning (ML) applied to the analysis of microbiome data, we are launching the second volume to collate any new findings in the field to further our understanding and encourage the participation of experts worldwide in the discussion.
The success of ML algorithms in the field is substantially due to their capacity to process high-dimensional data and deal with uncertainty and noise. However, to maximize the combinatory potential of these emerging fields (microbiome and ML), researchers have to deal with some aspects that are complex and inherently related to microbiome data. Microbiome data are convoluted, noisy and highly variable, and non-standard analytical methodologies are required to unlock their clinical and scientific potential. Therefore, although a wide range of statistical modelling and ML methods are available, their application is only sometimes optimal when dealing with microbiome data.
Thus, our invite is for manuscripts about the review, evaluation or application of ML-based models, software packages and web servers for specific prediction problems in microbiome data, as well as the development of novel ones. We welcome the submission of research articles that use machine learning as an underlying modelling strategy or primary data analysis tool in any microbiome data. Biomedical data is a must-have, but we are open to other fields, such as plant and environmental applications. The goal is to advance ML techniques in microbiome data and gain insight into current problems and methods.
The collection will include Original Research, Methods, Reviews, Technology and Code, and Perspective, describing machine learning novel tools or approaches for the analysis and classification of microbiome data, improving the interpretability of ML application results, or that employ Explainable AI so that experts and non-experts practitioners can correctly understand and interpret the ML/DL models and their decisions.
Specific topics may include, but are not limited to:
• Optimization of data preparation of microbiome data to use ML techniques
• Tools and pipelines to analyze microbiome data with ML methods, for experts and non-experts
• Latest ML algorithms with applications in taxa and gene function prediction
• ML models to extract potential microbiome-biomarkers
• ML approaches and applications for integrating multi-level omics data
• ML models for early disease prediction and prevention
• Studies based on dynamical and prospective models of microbiome
• Studies based on multi-omics data, e.g. the combination of genomic, transcriptomic, epigenomic, or proteomic data
The COST Action ML4Microbiome (CA18131) has been pioneering research in this relatively new field of ML application since February 2020, when the kick-off meeting of the Action was held. The idea for the publication of Volume II is part of its dissemination mission. The publication of this second volume is, as for the previous one, supported by the ML4Microbiome COST action network, where discovery-oriented microbiome researchers and data-driven ML experts have been working together to reach two main objectives: first to optimize and then standardize the best practice of ML techniques for human microbiome research (visit website here).
The success of ML algorithms in the field is substantially due to their capacity to process high-dimensional data and deal with uncertainty and noise. However, to maximize the combinatory potential of these emerging fields (microbiome and ML), researchers have to deal with some aspects that are complex and inherently related to microbiome data. Microbiome data are convoluted, noisy and highly variable, and non-standard analytical methodologies are required to unlock their clinical and scientific potential. Therefore, although a wide range of statistical modelling and ML methods are available, their application is only sometimes optimal when dealing with microbiome data.
Thus, our invite is for manuscripts about the review, evaluation or application of ML-based models, software packages and web servers for specific prediction problems in microbiome data, as well as the development of novel ones. We welcome the submission of research articles that use machine learning as an underlying modelling strategy or primary data analysis tool in any microbiome data. Biomedical data is a must-have, but we are open to other fields, such as plant and environmental applications. The goal is to advance ML techniques in microbiome data and gain insight into current problems and methods.
The collection will include Original Research, Methods, Reviews, Technology and Code, and Perspective, describing machine learning novel tools or approaches for the analysis and classification of microbiome data, improving the interpretability of ML application results, or that employ Explainable AI so that experts and non-experts practitioners can correctly understand and interpret the ML/DL models and their decisions.
Specific topics may include, but are not limited to:
• Optimization of data preparation of microbiome data to use ML techniques
• Tools and pipelines to analyze microbiome data with ML methods, for experts and non-experts
• Latest ML algorithms with applications in taxa and gene function prediction
• ML models to extract potential microbiome-biomarkers
• ML approaches and applications for integrating multi-level omics data
• ML models for early disease prediction and prevention
• Studies based on dynamical and prospective models of microbiome
• Studies based on multi-omics data, e.g. the combination of genomic, transcriptomic, epigenomic, or proteomic data
The COST Action ML4Microbiome (CA18131) has been pioneering research in this relatively new field of ML application since February 2020, when the kick-off meeting of the Action was held. The idea for the publication of Volume II is part of its dissemination mission. The publication of this second volume is, as for the previous one, supported by the ML4Microbiome COST action network, where discovery-oriented microbiome researchers and data-driven ML experts have been working together to reach two main objectives: first to optimize and then standardize the best practice of ML techniques for human microbiome research (visit website here).
Keywords: microbiome, machine learning, omics, statistics, modelling, machine, learning, data, software, web server, AI
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.
