Using AI to determine drug compounds to curb the opioid crisis

Researchers have developed a computer model, that learns using AI, to identify potential drug compounds that can be used to block opioid receptors in the brain. 

Drugs in the opioid family – heroin, oxycodone, fentanyl, and morphine – work by activating µ-opioid receptors in the brain, which provides relief from pain and gives a state of euphoria. Alongside this however, is physical dependence on the opioid and decreased breathing rate, which in the event of an overdose can drop so dramatically as to cause death. 

Physical dependence has been shown to decrease when k-opioid receptors – the receptors that mediate brain rewards – are blocked, in preclinical studies. By discovering drug that block these receptors, there could be a real opportunity to tackle opioid dependence, and curb the crisis. 

Leslie Salas Estrada, part of the Filizola Lab, at the Icahn School of Medicine at Mount Sinai (NY, USA), will present her work on the subject at the 67th Annual Biophysical Society Meeting in San Diego, CA, USA in February.

“If you're addicted and you're trying to quit, at some point you will get withdrawal symptoms, and those can be really hard to overcome,” Salas Estrada explained, “after a lot of opioid exposure, your brain gets rewired to need more drugs. Blocking the activity of the kappa opioid receptor has been shown in animal models to reduce this need to use drugs in the withdrawal period.”

Unfortunately, to discover new drugs that do this can be like trying to find a needle in a haystack, which can be time consuming, costly, and fruitless, even when using computational models to screen compounds. This is where artificial intelligence (AI) comes in. 

“Artificial intelligence has the advantage of being able to take huge amounts of information and learn to recognize patterns from it. So, we believe that machine learning can help us to leverage the information that can be derived from large chemical databases to design new drugs from scratch. And in that way, we can potentially reduce the time and costs associated with drug discovery,” stated Salas Estrada.

By using what the researchers already know about the k-opioid receptor, and the existing drugs on the market, they can populate a computer model with this information, and use AI to manipulate the model, along with a learning algorithm that rewards compounds with properties that make them appealing as drug treatments, to generate prospective compounds.  

Using this method the team at Icahn School of Medicine at Mount Sinai have been able to identify numerous promising compounds, with the complimentary properties, with the hopes of testing them. This should be made possible once the drugs have been synthesised, their safety and efficacy in blocking k-opioid receptors assessed first in cell models and then in animal models. 

Salas Estrada concluded, “we hope we can help people struggling with addiction.”