A startup started by the University of Toronto in genomic medicine plans to revolutionize genomic understanding with deep learning. Deep genomics has already had a huge impact on computer vision and speech recognition, and it is making inroads in areas of science.
It plans to identify mutations and gene variants which has never been studied before and find out how these link to various diseases. And the company believes that it can create a new era of personalized medicine.
Genomic research is generally tough. Researchers have very little knowledge about our genes and how they interrelate with each other. Genomics is not only about small datasets but also about large datasets.
They mainly focus on:
- Interpretation of genetic variation
- Target bio-marker discovery
- Genome-based therapeutic development
- Risk assessment for complex disorders
- Molecular diagnostics and carrier screening
The first sequencing of a full human genome took 13 years (from 1990 to 2003). There are now many companies working to sequence many genomes at a time. One of the largest company working on genomics is “Illumina”.
Deep Genomics has built Spidex, which stores and makes sense of all these data. Spidex is basically a database that contains information about how different genetic variants affect or are likely to affect the RNA splicing. It is a crucial step in gene expression, which edits genes in different ways so that they can produce different kinds of proteins.
If RNA splicing goes wrong, it may result in cancer or some other genetic diseases. Spidex separates the harmless variants from the harmful ones and understands how they relate to other genetic processes.
The company aims to apply its deep learning algorithms to classifying and interpreting more data.
Brendan Frey, the CEO of the company, notes that the bulk of the variants are in the “junk DNA” part of the genetic code. This is the bit that scientists had previously written off as irrelevant, even though it forms the vast majority of the genome. “Most medical genetic analysis currently deals only with mutations in what are called ‘protein-coding segments’ in DNA, or ‘exons,’ Frey explains. “This makes up only 1.5 percent of the genome.”
Deep Genomics taps into that 98.5 percent of the genome that hasn’t been studied closely for mutations and looks for the disease consequences of any mutations it finds.
The main idea is to lay the foundation for computers to one day be in charge of predicting lab experiments and treatments and to guide drug development and personalized medicine. This might perhaps include reaching as low as your doctor’s office.
This is really just the beginning, but Frey tells us that Deep Genomics technology is already finding commercial use in medical diagnostics and drug development.
The original article was published in the newatlas.com