Transfer learning method predicts genomic mutations in livestockTransfer learning method predicts genomic mutations in livestock
Researchers develop new computational method that predicts harmful mutations in mammalian species.
April 16, 2018
Researchers at Peter the Great St. Petersburg Polytechnic University (SPbPU) in Russia have developed a new computational method that predicts harmful mutations in mammalian species, according to a recent announcement.
As more and more livestock producers are using genetic tests to improve their herds, this method will help optimize and guide the animal breeding programs as well as increase the profitability and yields of livestock, SPbPU said.
Published in Evolutionary Applications, the method follows closely in the footsteps of the most recent innovations in human genomics and translates the knowledge about genetic risk factors in humans to companion animals, thus having a transformative potential for genetics and genomics of livestock species, the announcement said.
Efficient selection in farm animals that will produce offspring with desirable phenotypes and ensure less reliance on hormones and antibiotics has been in the spotlight of many livestock genomic and gene editing projects, SPbPU said. However, their success has been hindered by unknown effects produced by genomic variants.
Led by professors Maria Samsonova, Sergey Nuzhdin and Lev Utkin in SPbPU's Mathematical Biology & Bioinformatics Lab and Machine Learning Group, the researchers took full advantage of available information on human variation with deleterious potential and used transfer learning methods to enable classification of damaging mutations in other mammalian species, the announcement said.
The approach was validated extensively using dog and mice models, where functional annotation of mutations has been the focus of major international initiatives such as International Mouse Phenotyping Consortium.
"The developed methodology could be used to identify deleterious, unwanted mutations in genomes of other farm animals, thus facilitating the design of finely tuned metabolic pathways that allow animals to thrive under a wide range of conditions," explained Samsonova, head of the Laboratory of Mathematical Biology & Bioinformatics at SPbPU.
Selection for desirable characteristics or traits in livestock -- or, conversely, selection against undesirable phenotypes -- has been practiced since the domestication of wild animals, the researchers noted. A side effect of controlled breeding is rapid accumulation of harmful mutations when genomic variants with negative potential are not counter-weighted by an inflow of "good" genes from external populations. Over time, this leads to an overall reduction in the fitness of cattle and other farm animals, they added.
Sustainable agriculture and the industry's ability to provide people with higher-quality, healthier and lower-cost farm products with richer varieties relies heavily on the knowledge of functional effects induced by either naturally occurring or technologically introduced mutations and the ability to eliminate harmful ones from future breeds, the researchers concluded.
You May Also Like
House passes rail contract, mandates sick timeJan 12, 2023
Current Conditions for
New York, NY
Enter a zip code to see the weather conditions for a different location.
DeLaval adds to its robotic milking offering in the U.S.Oct 03, 2023
Road to better animal welfare and its future impactOct 04, 2023
Dairy markets, exports: What's ahead?Oct 03, 2023
China demand props up wheat pricesAug 01, 2023