A study conducted by
researchers at New York University (NYU) together with their
colleagues from National Taiwan University, Purdue University, and
the University of Illinois has found genes, through machine
learning, that help crops grow with less fertilizer and predict
additional traits in plants and disease outcomes in animals.
In the Nature Communications paper, it was
indicated that the research team used machine learning, a type of
artificial intelligence used to detect patterns in data. As a
proof-of-concept, the researchers showed that genes whose
responsiveness to nitrogen is evolutionarily conserved between two
diverse plant species�??Arabidopsis, and varieties of
corn�??significantly improved the ability of machine learning models
to predict genes of importance for how efficiently plants use
nitrogen, a crucial nutrient for plants and the main component of
fertilizer. Crops that use nitrogen more efficiently grow better
and require less fertilizer, which has economic and environmental
benefits.
Experiments validated
eight master transcription factors as genes of importance to
nitrogen use efficiency. They showed that altered gene expression
in Arabidopsis or corn could increase plant growth in low nitrogen
soils, which they tested both in the lab at NYU and in cornfields
at the University of Illinois. The researchers showed that machine
learning can be applied to other traits and species by predicting
additional traits in plants, including biomass and yield in both
Arabidopsis and corn. They also showed that this approach can
predict genes of importance to drought resistance in
rice, as well as disease outcomes in animals.
Machine
Learning Uncovers �??Genes of Importance�?� in Agriculture and
Medicine (nyu.edu)