ORLANDO, FL – It takes millions, if not billions, of dollars to take a drug from the lab to the pharmacy. Last year out of thousands of drugs in clinical trials, the FDA approved 37, the fewest to pass regulatory scrutiny since 2016.
But now, artificial intelligence, or AI, may help to weed out the good from the bad, the drugs that will work and the ones that won’t, making the time a drug takes to get approval quicker than ever before.
Everywhere you look, everyone seems to be talking about AI. But it doesn’t just help write resumes and papers, AI is also changing the medical world.
“We can cut down the experiments as well as cut down the time,” said Sudipta Seal, a material scientist at the University of Central Florida.
On average, it takes 10 years to develop a new drug. Now, a team at the University of Central Florida is aiming to speed up that process using an AI-based drug screening method they’ve developed.
“We are working on, basically, trying to model drug and the target protein interactions and then predict their interactions,” UCF computer scientist Ozlem Garibay explained.
It translates the complex interactions at each drug protein binding site into words. The AI model, then, analyzes that language to learn which part of a virus protein a drug will bind to. With 97% accuracy, it can predict how well a drug will work.
“So, you can just, give it, for example, COVID protein and test it against all the FDA approved drugs and see whether or not they bind or not. That’s the beauty of this work,” said Mehdi Yazdani-Jahromi, a PhD student at UCF’s College of Engineering and Computer Science.
It’s called AttentionSiteDTI and is ready to be used right now, for free for anyone developing a new drug.
“I think it’s going to revolutionize medical fields in so many different ways,” Garibay said.
Another upside of using AI in drug discovery – the less time in the lab, the lower the cost to create it, and researchers believe that savings could be handed down to the consumer. As for this technology, researchers are now ready to create a website like ChatGPT, making it simple for other scientists to put in their data and see if their drug will work or not.
Published by News 4 Jax