Machine learning has flooded the scientific world with success stories that span a variety of scientific fields. In many of these stories, machine learning has enabled the digestion of insurmountable amounts of data, and uncovered information that would have otherwise remained hidden. Microbiology is not an exception; high-throughput experimentation and simulation provide the fuel that machine learning needs - data. In this collection of articles, we wish to present and examine the latest advances and ways by which machine learning, simulation, and experiments can be combined, and the obstacles that must be overcome, to accelerate discovery in Systems Microbiology.
Computational model simulations can describe a microbial population from microbe-microbe local interactions and capture emergent phenomena at the population level. For example, recent advances in Agent-Based Modeling have made it possible to simulate populations with millions of microbes, enabling in-silico studies on temporal-spatial scales that approach experiments. Concomitantly, advances in high-throughput experiments using next-generation sequencing, mass spectrometry, nuclear magnetic resonance spectroscopy, and microscopy imaging, can now provide large amounts of data whose analysis is crucial to deliver insights that range from understanding microbe-microbe interactions to how these interactions affect the growth of the corresponding populations. Machine learning techniques can leverage all these developments and accelerate discovery in Systems Microbiology by gauging the accuracy of the computational models, classifying and analyzing the experimental data, and making strides in the development of autonomous experiments. This Research Topic will include manuscripts that combine machine learning with simulation, experiment, or both.
This topic is interested in manuscripts that describe recent developments and findings combining simulation and experiments in microbial populations with artificial intelligence and machine learning. Additionally, we welcome manuscripts that discuss the roadblocks that might exist in combining simulation and/or experiments with machine learning in microbiology, as well as the steps that could be taken to overcome them. This collection will accept the following article types: Original Research, Perspective, Review, and Mini-Review.
Please note that Systems Microbiology does not consider descriptive studies that are solely based on amplicon (e.g., 16S rRNA) profiles, unless they are accompanied by a clear hypothesis and experimentation and provide insight into the microbiological system or process being studied.
Machine learning has flooded the scientific world with success stories that span a variety of scientific fields. In many of these stories, machine learning has enabled the digestion of insurmountable amounts of data, and uncovered information that would have otherwise remained hidden. Microbiology is not an exception; high-throughput experimentation and simulation provide the fuel that machine learning needs - data. In this collection of articles, we wish to present and examine the latest advances and ways by which machine learning, simulation, and experiments can be combined, and the obstacles that must be overcome, to accelerate discovery in Systems Microbiology.
Computational model simulations can describe a microbial population from microbe-microbe local interactions and capture emergent phenomena at the population level. For example, recent advances in Agent-Based Modeling have made it possible to simulate populations with millions of microbes, enabling in-silico studies on temporal-spatial scales that approach experiments. Concomitantly, advances in high-throughput experiments using next-generation sequencing, mass spectrometry, nuclear magnetic resonance spectroscopy, and microscopy imaging, can now provide large amounts of data whose analysis is crucial to deliver insights that range from understanding microbe-microbe interactions to how these interactions affect the growth of the corresponding populations. Machine learning techniques can leverage all these developments and accelerate discovery in Systems Microbiology by gauging the accuracy of the computational models, classifying and analyzing the experimental data, and making strides in the development of autonomous experiments. This Research Topic will include manuscripts that combine machine learning with simulation, experiment, or both.
This topic is interested in manuscripts that describe recent developments and findings combining simulation and experiments in microbial populations with artificial intelligence and machine learning. Additionally, we welcome manuscripts that discuss the roadblocks that might exist in combining simulation and/or experiments with machine learning in microbiology, as well as the steps that could be taken to overcome them. This collection will accept the following article types: Original Research, Perspective, Review, and Mini-Review.
Please note that Systems Microbiology does not consider descriptive studies that are solely based on amplicon (e.g., 16S rRNA) profiles, unless they are accompanied by a clear hypothesis and experimentation and provide insight into the microbiological system or process being studied.
