91Ƶ

Skip to content

UBC researchers91Ƶ algorithm helps ID designer drugs before they hit market

Model being used by U.S. Drug Enforcement Agency, UN and European law enforcement
27280523_web1_211123-BPD-UBC-Computers-Predict-Designer-Drugs_1
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 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 91Ƶtrained computers to predict the next designer drugs91Ƶ 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.

It91Ƶs not uncommon for illicit and deadly street drugs to also include legal substances mixed in. While recognizing the 91Ƶlegal highs91Ƶ 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 91Ƶknown psychoactive substances91Ƶ 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.

91ƵThese 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 set91Ƶ and 91Ƶthe model was able to predict nearly all of the new drugs discovered since it was trained,91Ƶ 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.

91ƵIt 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,91Ƶ Skinnider said.

91ƵAnd 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.91Ƶ

UBC91Ƶs 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:

Like us on and follow us on .



Karl Yu

About the Author: Karl Yu

I joined Black Press in 2010 and cover education, court and RDN. I am a Ma Murray and CCNA award winner.
Read more



(or

91Ƶ

) document.head.appendChild(flippScript); window.flippxp = window.flippxp || {run: []}; window.flippxp.run.push(function() { window.flippxp.registerSlot("#flipp-ux-slot-ssdaw212", "Black Press Media Standard", 1281409, [312035]); }); }