Sept 24 (UPI) – Humans and plants have thousands of genes. Traditionally, studying the function of a single gene or group of genes requires extensive experiments.
However, computers and access to large genomic databases allow researchers to study gene functions more efficiently. However, extracting large amounts of genomic data is challenging even for the most powerful computers.
In a new discovery, researchers in the United States and Taiwan have developed a machine-learning algorithm to more efficiently identify “critical genes” in agriculture and medicine.
Machine learning algorithm, described on Friday In Nature CommunicationsIt could help scientists better predict how plants and animals will respond to changes in nutrition, toxins or pathogens, allowing researchers to develop more resistant crops, diagnose rare diseases, or predict the next pandemic.
“We show that focusing on genes whose expression patterns are evolutionarily conserved in all species improves our ability to learn and predict ‘genes important’ for basic crop growth performance, as well as disease outcomes in animals,” said study lead author Gloria. Korosi, professor of biology at New York University’s Center for Genomics and Systems Science, said in a press release.
Essentially, the researchers have found a way to reduce the genetic noise that the algorithm is exposed to.
“We have shown that reducing our genome information to genes whose expression patterns are conserved within and between species is a biology-based method for reducing the dimensionality of genomic data, which greatly improves the ability of our machine learning models to identify important genes,” the author said. Principal Chia Yi-cheng, a researcher at the Center for Genomics and Systems Biology and National Taiwan University, “for a trait.”
In a proof-of-concept experiment, the researchers showed that nitrogen-reactive genes are evolutionarily conserved between two diverse plant species: Arabidopsis, a small flowering plant and botanical model popular among botanists and many varieties of corn. With lower input data noise, the new algorithm identified genes important for efficient and successful nitrogen processing.
Nitrogen uptake is essential for plant growth. Plants designed to absorb and use nitrogen more efficiently can reduce fertilizer use. Excessive nitrogen use has been linked to a variety of environmental problems, including Nutrient loading, harmful algal blooms And coral bleaching.
In follow-up experiments, the researchers confirmed the importance of the genes identified by their algorithm. Botanists were able to increase the genes of corn cultivars to increase nitrogen uptake and promote plant growth in nitrogen-poor soils.
“Now that we can more accurately predict which hybrids of corn are best to use nitrogen fertilizer in the field, we can rapidly improve this trait,” said co-author Stephen Moss, professor of agricultural sciences at the University of Illinois at Urbana-Champaign. “Increasing the efficiency of nitrogen use in corn and other crops provides three major benefits: reduced costs to farmers, reduced environmental pollution, and reduced greenhouse gas emissions from agriculture.”
In addition to identifying genes relevant to different crop traits, the researchers suggest that their algorithm could be used to predict genes relevant to disease outcome in mouse models, which could inspire the development of new therapeutics and diagnostic techniques.
“Because we have shown that our informed evolutionary line can also be applied to animals, this highlights their ability to detect genes of interest for any physiological or clinical trait of interest in biology, agriculture or medicine,” Korozi said.
“Award-winning zombie scholar. Music practitioner. Food expert. Troublemaker.”