University of British Columbia has developed an algorithm which helps predict the next designer drugs before they hit the street. (U.S. Attorneys Office for Utah via AP, File)

University of British Columbia has developed an algorithm which helps predict the next designer drugs before they hit the street. (U.S. Attorneys Office for Utah via AP, File)

UBC researchers’ algorithm helps ID designer drugs before they hit market

Model being used by U.S. Drug Enforcement Agency, UN and European law enforcement

University of British Columbia researchers have developed a computer-based solution they hope will lend a hand to law enforcement across the world in curbing the number of new kinda of illicit drugs hitting the streets.

In a study released this month, the researchers say they developed an algorithm that essentially “trained computers to predict the next designer drugs” even before they hit the market.

This could be a game changer for police and other officials, who are seeking to identify and regulate new forms of illicit drugs, such as bath salts and synthetic opioids, in order to keep pace with illegal drug manufacturers.

It’s not uncommon for illicit and deadly street drugs to also include legal substances mixed in. While recognizing the “legal highs” in confiscated pills and powders can take months, the researchers said they are seeing that time reduced to days.

Medical student Dr. Michael Skinnider, along with his colleagues, utilized a directory of “known psychoactive substances” from across the globe to equip an artificial intelligence algorithm with drug structure information. The algorithm is inspired by the function and structure of the human brain.

The model was able to identify close to nine million potential designer drugs.

“These molecules were then tested against 196 new designer drugs that emerged on the illicit market after the model was trained. The researchers found more than 90 per cent were present in the generated set” and “the model was able to predict nearly all of the new drugs discovered since it was trained,” the news release said.

In addition, researchers also discovered the algorithm could determine which molecules were more likely, or less likely, to appear on the market with an accuracy of 72 to 86 per cent of the time.

“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,” Skinnider said.

“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.”

UBC’s model is being used by the U.S. Drug Enforcement Agency, United Nations Office of Drugs and Crime, European Monitoring Centre of Drugs and Drug Addiction and Federal Criminal Police Office of Germany, the press release said.

READ ALSO: B.C. applies to decriminalize personal possession of illicit drugs

Like us on Facebook and follow us on Twitter.

opioid addictionstreet drugsUBC

Be Among The First To Know

Sign up for a free account today, and receive top headlines in your inbox Monday to Saturday.

Sign Up with google Sign Up with facebook

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Reset your password

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

A link has been emailed to you - check your inbox.



Don't have an account? Click here to sign up
Pop-up banner image