Genomics will move to the next level with AI and Pattern Recognition
We have all probably by now been to see the excellent film The Imitation Game where we watched Alan Turing and his team of decoders investing hours of their time trying to crack Nazi Germany’s messages by looking for patterns with the help of the computer they built.
In Disrupted Health, we have endeavoured to explained the importance of genomics to the revolution of healthcare. Genomics, in other words the sequencing of the human genome, is beginning to allow scientists to understand the code of the human body and therefore identify what components of that code, when defective, are the trigger for certain diseases such as cancer.
Similarly to the Enigma code cracking team in The Imitation Game, scientists and healthcare professionals seeking to diagnose and treat rare diseases will need to be able to compare the genome sequence data of one patient to other individuals’ data in order to identify patterns. This reference library of human genome information is therefore key to success.
The cost of sequencing a human genome has reached the point where it is now feasible for many of us to access this science. For example, 23andMe now has 800,000 individual records in their database. Unfortunately, the limitation in the science of genomics is that a great deal of this life-saving information, though already collected, is inaccessible. Much of this valuable data is siloed rendering the creation of reference library for genome sequence analysis a challenge.
In January this year, programmers in Toronto began testing a system for trading genetic information with other hospitals. These facilities, in locations including Miami, Baltimore, and Cambridge, U.K., also treat children with so-called Mendelian disorders, which are caused by a rare mutation in a single gene. The system, called MatchMaker Exchange, represents something new: a way to automate the comparison of DNA from sick people around the world.
Pressure is building to use technology to study many, many genomes at once and begin to compare that genetic information with medical records. That is because scientists think they’ll need to sort through a million genomes or more to solve rare disease cases that could involve a single rogue DNA letter, or to make discoveries about the genetics of common diseases that involve a complex combination of genes. No single academic centre currently has access to information that extensive, or the financial means to assemble it.
The success rate of solving rare diseases this way appears to be tailing off. We have reached the stage where the tougher cases are left, and they are getting solved only half as often as the others. “We don’t have two patients with the same thing anymore. That’s why we need the exchange,” Kim Boycott, head of the research team at the Children’s Hospital of Eastern Ontario, says. “We need more patients and systematic sharing to get the [success rate] back up.”
Privacy, of course, is another obstacle to sharing. People’s DNA data is protected because it can identify them, like a fingerprint—and their medical records are private too. Some countries don’t permit personal information to be exported for research. But a peer-to-peer network can sidestep some of these worries, since the data won’t move and access to it can be gated. More than half of Europeans and Americans say they’re comfortable with the idea of sharing their genomes, and some researchers believe patient consent forms should be dynamic, a bit like Facebook’s privacy controls, letting individuals decide what they’ll share and with whom—and then change their minds.
In many decades to come, our children are likely to be watching a new script entitled The Imitation Game of Genomics where the Alan Turing of genome sequencing will be racing against time to solve a rare disease conundrum with the help of a powerful computer looking for patterns across databases around the world.
By Julian De Salaberry