Eye on AI - October 1st, 2021
Welcome to Aigora's "Eye on AI" series, where we round up exciting news at the intersection of consumer science and artificial intelligence!
This week, we’ll be building on last week’s discussion by looking into the genomic evolution in agriculture, including a look at machine-learning uncovered ‘genes of importance’ and a collaborative program of agricultural experts that hopes to use AI to make future crops more resilient.
Enjoy!
Machine Learning Reveals Agricultural and Medical ‘Genes of Importance’
We begin with a look at the genomic data sets, which have long troubled researchers. The problem was never the amount of data that was collected, but rather how to discover ‘genes of importance’ within the endless datasets they had. According to the recent NYU article “Machine Learning Uncovers ‘Genes of Importance’ in Agriculture and Medicine”, that struggle may soon be at an end, as it was announced that researchers at NYU’s Department of Biology and Center for Genomics and Systems Biology recently succeeded in creating a new method of identifying complex patterns within genomic data using machine learning.
“We show that focusing on genes whose expression patterns are evolutionarily conserved across species enhances our ability to learn and predict ‘genes of importance’ to growth performance for staple crops, as well as disease outcomes in animals,” explained Gloria Coruzzi, Carroll & Milton Petrie Professor in NYU’s Department of Biology and Center for Genomics and Systems Biology and the paper’s senior author.
To prove their concept, NYU’s researcher team were able to show that genes whose responsiveness to nitrogen (essential in agriculture) are evolutionarily conserved between two diverse plant species—Arabidopsis, a small flowering plant widely used as a model organism in plant biology, and varieties of corn, America’s largest crop—significantly improved the ability of machine learning models to predict genes of importance for how efficiently plants use nitrogen. Further experiments showed that by altering gene expressions, researchers could increase plant growth in low nitrogen soils, which in turn would lower farming costs, reduce environmental pollution, and mitigate greenhouse gas emissions.
This news would certainly pique the attention of any agricultural farmer who knows the importance of nitrogen to farming. But the more headline-catching point is that these NYU researchers essentially proved that similar approaches can be used to predict traits in other organisms, potentially leading to many more positive and potentially mind-bending outcomes in plants, animals, and indeed humans.
“Because we showed that our evolutionarily informed pipeline can also be applied in animals, this underlines its potential to uncover genes of importance for any physiological or clinical traits of interest across biology, agriculture, or medicine,” added Coruzzi.
Farmers Look to AI to Strengthen Crops and Fix Food Systems
In related news, the Horti Daily, through their article “Plant scientists will use artificial intelligence to make crops more resilient,” announced this week that a team of university and company researchers and scientists has been given the green light and financial support by the Dutch Research Council (NWO) to further develop crop resilience using AI.
“With a budget of 50 million euros, the team aims to connect specialists in plant sciences, data sciences, artificial intelligence (AI), and breeding companies over the next ten years on a method to develop agricultural crops that can be grown in a climate-proof and sustainable manner,” writes Horti Daily’s editorial team.
Noted in their ten-year plan, called Plant-XR, the group aims to enable the development of new climate-resilient crops. Historically, agricultural crops have been bred to achieve higher yields, with less attention being paid to crop resilience. Those resilience traits have since faded as they were selectively bred out, thus making crops more susceptible to climate changes. Researchers are hoping that, in time, they’ll be able to reinsert those more resilient traits to help plants become future-proof.
“To make crops future-proof, it is first necessary to collect a great deal of data (on molecular and plant levels) about such systems in controlled experiments,” writes University of Amsterdam associate professor Harrold van den Burg of the Swammerdam Institute for Life Sciences. “We are also going to discuss with breeders which properties they expect crops will need most in ten years. And we will look at how we can best use the expertise in the field of AI that we already have here at the UvA to optimize the data analysis.”
While this is all positive, it is a long-term vision that is at its earliest stages of materialization. Yet at its heart, this program really boils down to being an enormous collaborative experiment between diverse teams of scientists, researchers, and agricultural experts that might not otherwise interact, and lays the foundation for an information-sharing system of efficiency, or so we hope –– more on that in ten years.
Other News
New startup’s profits prove NFTs can solve fundamental problems in finance
In the NFT art world where machine learning AI is holding the paintbrush
Dancing bears, drones, and clocks: the weirdest Alexa devices we've seen so far
That's it for now. If you'd like to receive email updates from Aigora, including weekly video recaps of our blog activity, click on the button below to join our email list. Thanks for stopping by!
