Understanding the molecular mechanisms underlying plant adaptation and domestication is crucial to engineering more productive and resilient crops to feed our rising global population, especially under global climate change scenarios. Traditional methods focus on classical genetic variation including single-base variation and genomic structural variation. These variations have been generally considered to play an important role in the evolution of plants. Nevertheless, genetic diversity is limited and is now steadily disappearing, a phenomenon known as genetic erosion, and so its breeding potential is in decline. Recently, researches have shown that epigenetic variations such as DNA methylation and chromatin changes play critical roles in plant adaptation and domestication. This provides solutions for epigenetically modifying plants to gain desired traits. Yet, including epigenetic variations generates massive data sets which are noisy, heterogeneous, and require novel analysis methods. Machine learning, in recent years, has shown its power to integrate, analyze, and interpret large and complex data sets. They offer opportunities to decipher the genetic and epigenetic bases underlying agronomically important traits. The goal of this research topic is to explore the potential of machine learning methods in uncovering the epigenetic regulatory mechanisms that underlie plant domestication and adaptation.
This Research Topic includes, but is not limited to, the following:
－ Reviews of machine learning algorithms for plant epigenetic data sets.
－ Latest machine learning algorithms for plant epigenetic data sets.
－ Development of packages and web servers for mining epigenetic variations/markers using machine learning algorithms.
－ Development of epigenetic databases regarding plant adaptation and domestication with predictions using machine learning algorithms.
－ Novel genetic and epigenetic variations/markers associated with plant adaptation and domestication that are discovered with machine learning algorithms using experimental data.
Understanding the molecular mechanisms underlying plant adaptation and domestication is crucial to engineering more productive and resilient crops to feed our rising global population, especially under global climate change scenarios. Traditional methods focus on classical genetic variation including single-base variation and genomic structural variation. These variations have been generally considered to play an important role in the evolution of plants. Nevertheless, genetic diversity is limited and is now steadily disappearing, a phenomenon known as genetic erosion, and so its breeding potential is in decline. Recently, researches have shown that epigenetic variations such as DNA methylation and chromatin changes play critical roles in plant adaptation and domestication. This provides solutions for epigenetically modifying plants to gain desired traits. Yet, including epigenetic variations generates massive data sets which are noisy, heterogeneous, and require novel analysis methods. Machine learning, in recent years, has shown its power to integrate, analyze, and interpret large and complex data sets. They offer opportunities to decipher the genetic and epigenetic bases underlying agronomically important traits. The goal of this research topic is to explore the potential of machine learning methods in uncovering the epigenetic regulatory mechanisms that underlie plant domestication and adaptation.
This Research Topic includes, but is not limited to, the following:
－ Reviews of machine learning algorithms for plant epigenetic data sets.
－ Latest machine learning algorithms for plant epigenetic data sets.
－ Development of packages and web servers for mining epigenetic variations/markers using machine learning algorithms.
－ Development of epigenetic databases regarding plant adaptation and domestication with predictions using machine learning algorithms.
－ Novel genetic and epigenetic variations/markers associated with plant adaptation and domestication that are discovered with machine learning algorithms using experimental data.