A new breakthrough for the drug industry come with thanks to AI genomics company, Deep Genomics.
The company is looking to use machine learning techniques to trace possible genetic causes for disease in order to develop a specialized treatment for the patient. Deep Genomics is a Canadian-based company that was founded by Brendan Frey, a professor at the University of Toronto who specializes in genomic medicine and machine learning.
The company’s main goal is to produce powerful drugs by uncovering just a subtle signal in the genomic data.
The way it works is by using deep learning techniques to analyze the patient’s genomic data. Then, once the researchers have identified one or more genes that are responsible for a disease they can begin to develop a drug that will correct the faulty gene.
To begin with, the company will focus purely on early-stage development of drugs for those inherited diseases that result from a single genetic mutation. The mad rush to apply AI to medicine comes partly from the development of new algorithms, but also by the cost effectiveness of sequencing genomes.
“There’s an opening of a new era of data-rich, information-based medicine. There’s a lot of different kinds of data you can obtain. And the best technology we have for dealing with large amounts of data is machine learning and artificial intelligence,” says Frey. “There’s going to be this really massive shake-up of pharmaceuticals,” Frey continues. “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.”
Deep Genomics has also published work demonstrating how deep learning can be used to identify patterns in DNA that may contribute to certain disease including nonpolyposis cancer and spinal muscular atrophy. Other companies that are also pushing forward with the combine machine learning with drug development include a subsidiary of Alphabet called Calico, and a British AI company called BenevolentAI.