In the past few years drugs have become one of the biggest problems in our community. Drug overdose death rates are shocking and the most frightening thing is that it seems compelling. That’s when we questioned ourselves: ‘How to deal with the drug problem?’ Fortunately, we live in a world where technology is constantly developing and improving.
Where is the proof?
Well, some UBC researchers have trained computers in order to predict the next designer drugs before they are even on the market which makes the newborn technology life saver.
At that moment all law enforcement agencies are doing their best to identify and control all of the new dangerous psychoactive drugs such as bath salts and synthetic opioids, even as illegal chemists work to synthesize and distribute new molecules with the same psychoactive effects as classical drugs of abuse.
Identifying these so-called “legal highs” can take months, but unfortunately, during that time thousands of people may have already used a new designer drug.
A new research however is already helping law enforcement agencies all over the world to cut identification time down from months to days in order to identify and control all the new versions of psychoactive drugs.
Dr. Michael Smith who is a UBC medical student says that an enormous number of these designer drugs have never been tested in humans and they are unregulated. Smith completed the research as a doctoral student at UBC’s Michael Smith Laboratories.
A Minority Report for new designer drugs
Dr. Skinnider and his colleagues used information of some well-known psychoactive substances to train an artificial intelligence algorithm on the structures of these drugs. The algorithm they used is inspired by the structure and function of the human brain.
Based on this training, the model then generated about 8.9 million potential designer drugs.
These molecules were tested against 196 new designer drugs that emerged on the illegal market after the model was trained. It turned out that more than 90% were present in the generated set.
Specifically, the model was able to predict nearly all of the new drugs discovered from the moment it was trained.
Identification in days instead of months
But how to identify completely unknown substances in an easier way? The researchers found out that the model had also learned which molecules were more likely to appear on the market, and which were less likely. The professor in the department of biochemistry at UBC – Dr. Leonard Foster says:
“We wondered whether we could use this probability to determine what an unknown drug is—based solely on its mass—which is easy for a chemist to measure for any pill or powder using mass spectrometry.”
Dr. Skinnider notes:
“It was shocking to us that the model performed this well, because elucidating entire chemical structures from just an accurate mass measurement is generally thought to be an unsolvable problem. And narrowing down a list of billions of structures to a set of 10 candidates could massively accelerate the pace at which new designer drugs can be identified by chemists.”
In his opinion there is an entire world of chemical ‘dark matter’. He thinks that this is the moment where the right AI tools can unveil this unknown chemical world.
