Illinois scientists to test modernized genetic model for optimized crop breeding
image:
The University of Illinois Urbana-Champaign's Alex Lipka (left) and Colorado State University's Geoffrey Morris (right) will test the omnigenic model for its utility in crop breeding, thanks to new funding from the National Science Foundation.
view moreCredit: University of Illinois Urbana-Champaign and Colorado State University
URBANA, Ill. — The National Science Foundation (NSF) has funded University of Illinois Urbana-Champaign research that aims to connect the dots between quantitative and molecular genetics and improve crop breeding.
The four-year, $795,000 grant investigates new theories on how genetics influence complex crop traits, such as yield or grain quality. These traits are controlled by lots of different genes — sometimes hundreds or thousands — which makes untangling their contributions difficult. Crop breeders use a host of advanced genetic tools to predict and select desirable complex traits, but these tools rely on outdated genetic understanding, believes project leader Alex Lipka.
“The theory used to quantify genetic contributions to traits in statistical models stems back from 1918. In 1918, they didn’t have the central dogma of molecular biology, so they didn’t even know that DNA had two strands. There are over a century of advancements that have not been incorporated into the most widely used models to quantify genetic architecture,” said Lipka, an associate professor in the Department of Crop Sciences, part of the College of Agricultural, Consumer and Environmental Sciences (ACES) at Illinois.
An emerging genetic framework called the omnigenic model incorporates modern advances in molecular biology into classical genetic theory. The omnigenic model divides all the genes in an organism’s genome into two components: core genes and peripheral genes. According to the model, the core genes directly control the trait of interest. If, for example, several core genes for plant height are switched on, the plant should be taller.
Peripheral genes, on the other hand, do not directly control the trait but can still subtly impact it. These genes are involved in cellular processes that influence how the core genes direct the trait. For example, a peripheral gene might produce a protein that can travel within the cell and change the activity of a plant height core gene. While the effects of the peripheral genes may be small individually, added together they can contribute even more to genetic variability than core genes.
If the omnigenic model is correct, Lipka believes that incorporating peripheral genes could advance breeding tools. “If we can harness the collective effects of the peripheral genes, then there can be really powerful ramifications for getting and selecting for optimal trait values,” Lipka said.
Lipka and his collaborator Geoffrey Morris at Colorado State University, who also received an NSF grant for this project, will develop statistical methods for testing the omnigenic model in crops.
“We don’t currently have the statistical tools to properly assess evidence of the omnigenic model,” Lipka said. “We’re going to develop these tools and test them out in a biologically rigorous manner.”
They plan to use a software package previously developed by Lipka’s team to simulate how core genes, peripheral genes, and the interaction between genes could affect complex traits in a simulated crop population. Their simulations will be informed with data from Arabidopsis, a model plant species, and sorghum, a climate-resilient crop widely eaten in areas of the world with food insecurity.
"It's difficult for plant breeders to keep pace with a changing climate and increasing food demand," said Morris, whose team supports plant breeding programs around the world. "In this project, new methods will first be rigorously tested with data sets from ongoing breeding partnerships in the U.S., Senegal, and Haiti. Ultimately, though, our goal is to see these methods deployed by plant breeders to identify high-yielding, climate-resilient varieties."
They will simulate multiple populations with different types of selection and selection intensity, repeat this for several generations, and ultimately quantify evidence for or against the omnigenic model. By the end of the project, they will put all of their work into a new software package that other researchers can use to test and apply the model.
“In some of the preliminary studies, the omnigenic model actually seems like it might be working, which is just really cool,” Lipka said.
Lipka is also affiliated with the College of Liberal Arts and Sciences, the Carl R. Woese Institute for Genomic Biology, and the National Center for Supercomputing Applications at Illinois.
New machine learning model offers simple solution to predicting crop yield
Feature engineering improves upon genotype-by-environmental interaction model
image:
Sam Fernandes, left, assistant professor of agricultural statistics and quantitative genetics with the Arkansas Agricultural Experiment Station, and Igor Fernandes, statistics and analytics master's student, have worked to improve a crop yield prediction model using environmental data.
view moreCredit: U of A System Division of Agriculture photo by Paden Johnson
By John Lovett
U of A System Division of Agriculture
FAYETTEVILLE, Ark. — A new machine-learning model for predicting crop yield using environmental data and genetic information can be used to develop new, higher-performing crop varieties.
Igor Fernandes, a statistics and analytics master’s student at the University of Arkansas, entered agriculture studies with a data science background and some exposure to agronomy as an undergraduate assistant for Embrapa, the Brazilian Agricultural Research Corporation. With an outsider’s perspective and a history working with environmental data through one of his former advisers, he developed a novel approach to forecasting how crop varieties will perform in the field.
His interest in the subject led to a recently published study co-authored with his adviser, Sam Fernandes, an assistant professor of agricultural statistics and quantitative genetics with the Arkansas Agricultural Experiment Station, the research arm of the University of Arkansas System Division of Agriculture.
The study, published in the Theoretical and Applied Genetics journal, is titled “Using machine learning to combine genetic and environmental data for maize grain yield predictions across multi-environment trials.”
“Igor came in from statistics with no genetics background,” Sam Fernandes said. “So, he had this idea that was not at all what we would use in genetics, and it was just surprising that it worked well.”
Igor Fernandes’ model, which focused on environmental data, led him to a close second in this year’s international Genome to Fields competition. Co-authors of the study that stemmed from the competition entry included Caio Vieira, an assistant professor of soybean breeding for the experiment station, and Kaio Dias, assistant professor in the department of general biology at the Federal University of Viçosa in Brazil.
Environment and genetics
While the competition entry showed environmental data alone worked better than expected at predicting crop yield, the researchers saw an opportunity to build a comprehensive study that compared the novel approach to established prediction models used in genomic breeding.
Genomic breeding, a process of screening thousands of candidates for field trials based on DNA alone, can save time and resources needed to develop a new plant variety, such as growing better in drought conditions. An important part of genomic breeding involves genomic prediction to estimate a plant’s yield using its DNA.
“Let’s say you have thousands of candidates, and you get the DNA from all of them,” Sam Fernandes explains. “Based on the DNA along with information from previous field trials, you are able to tell which one will be the highest yielding without planting it in the field. So, you’re saving resources that way. This is genomic prediction.”
Adding information into a model on how that plant would interact with environmental conditions increases the accuracy of the genomic prediction and is becoming more common as more environmental data from testing centers becomes available. The practice is called “enviromics.” Still, there is no consensus on the best machine learning approach to combine environmental and genetic data.
“One advantage of including the environment information in the models is that you can address what we call genotype-by-environmental interaction,” Sam Fernandes said. “Since the environment does not affect all of the individuals in the same way, we try to account for all of that, so we are able to select the best individual. And the best individual can be different depending on the place and season.”
The study used the same data on corn plots from the Genomes to Fields Initiative that were used in the competition, but the researchers adjusted inputs as genetic, environmental, or a combination of both in “additive” and “multiplicative” manners. When including environmental and genetic data in a more straightforward “additive” manner, the prediction accuracy was better than the more complicated “multiplicative” manner.
The simpler model took less time for the computer to process, and the mean prediction accuracy improved 7 percent over the established model. The experiment was validated in three scenarios typically encountered in plant breeding.
“One of the unique things that Igor did is how he processed the environmental data,” Sam Fernandes said. “There are fancier models that people can throw in all sorts of information. But what Igor did is a simple, yet efficient way of combining the genetic and environmental data using feature engineering to process the information and get a summary of variables that is more informative.”
Collectively, the researchers say the results are promising, especially with the increasing interest in combining environmental features and genetic data for prediction purposes. Their immediate goal is to apply it to increase the capability of screening genotypes for field trials.
To learn more about Division of Agriculture research, visit the Arkansas Agricultural Experiment Station website. Follow on 𝕏 at @ArkAgResearch. To learn more about the Division of Agriculture, visit uada.edu. Follow us on 𝕏 at @AgInArk. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit uaex.uada.edu.
About the Division of Agriculture
The University of Arkansas System Division of Agriculture’s mission is to strengthen agriculture, communities, and families by connecting trusted research to the adoption of best practices. Through the Agricultural Experiment Station and the Cooperative Extension Service, the Division of Agriculture conducts research and extension work within the nation’s historic land grant education system.
The Division of Agriculture is one of 20 entities within the University of Arkansas System. It has offices in all 75 counties in Arkansas and faculty on five system campuses.
The University of Arkansas System Division of Agriculture offers all its Extension and Research programs and services without regard to race, color, sex, gender identity, sexual orientation, national origin, religion, age, disability, marital or veteran status, genetic information, or any other legally protected status, and is an Affirmative Action/Equal Opportunity Employer.
Journal
Theoretical and Applied Genetics
Method of Research
Data/statistical analysis
Subject of Research
Not applicable
Article Title
Using machine learning to combine genetic and environmental data for maize grain yield predictions across multi‑environment trials
No comments:
Post a Comment