With machine learning, a genomics company is moving into drug development, Technology Review reports.
Deep Genomics, which had been focusing on using its machine-learning tools to search for genetic changes that might be causal for certain diseases, is now setting its sights on developing drugs. According to Tech Review, Deep Genomics will first try its hand at developing drugs for Mendelian disorders.
Tech Review adds that there's been a push to incorporate artificial intelligence techniques into drug development that's been fed by both the development of new algorithms and cheaper genome sequencing. Deep learning approaches can then help uncover hidden patterns.
"There's going to be this really massive shake-up of pharmaceuticals," says Brendan Frey, the University of Toronto professor who started Deep Genomics. "In five years or so, the pharmaceutical companies that are going to be successful are going to have a culture of using these AI tools."
Other companies like BenevolentAI and Alphabet's Calico are also applying machine learning to drug development, Tech Review notes.
"Developing medicines is still a very lengthy, risky, and expensive process with high rates of attrition," adds Ken Mulvany, the founder of BenevolentAI. "[But] there is an enormous amount of untapped data located in pharma R&D organizations without any plans to develop it."