Using Machine Learning to Unlock the Secret of...Plants?
New research proposes a machine learning-based system to feed our growing population and preserve our natural habitat.
Join the DZone community and get the full member experience.Join For Free
In order to feed a growing population and preserve our natural habitat, it's crucial that we understand the plants we share the world with as much as possible. New research from Michigan State University proposes a machine learning-based system to do just that.
The researchers combined plant biology with machine learning to look through several thousand genes to understand which are responsible for the control of metabolites. Some of these are used to repel pests, while others attract pollinators, and understanding the makeup of the plant could potentially lead to improved plants and the development of plant-based pharmaceuticals.
"Plants are amazing — they are their own mini-factories, and we wanted to recreate what they do in a lab to produce synthetic chemicals to make drugs, disease-resistant crops, and even artificial flavors," the researchers say. "Our research found that it is possible to pick out the right gene by automating the process since machines are more capable of picking out minute differences among thousands of genes."
The researchers used machine learning to model the 30,000 or so genes contained in the Arabidopsis thaliana plant, which is commonly used in plant science experiments. The model borrowed from the approaches used in marketing to help forecast the behavior of consumers and target advertising effectively. It's an approach that produces patterns based upon our previous browsing and buying behavior to predict future behaviors. This approach was used to hone in on the specific genes related to metabolite function.
"Machine learning was a novel approach for us in plant biology, a new application of old software," the researchers explain. "It can now be applied to other plant species that produce medicinally or industrially useful compounds to speed up the process of discovering the genes responsible for their production."
Let me know your thoughts in the comments below.
Published at DZone with permission of Adi Gaskell, DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.