Orlando: Life-Saving Development Medicine It can cost billions of dollars and take decades, but researchers have developed a new artificial intelligence-based drug screening technique that they hope to shorten the process.
Using a method that models drug and target protein interactions using natural language processing techniques, the researchers achieved up to 97% accuracy in identifying promising drug candidates. The results were recently published in the journal Briefings in Bioinformatics.
This technique represents drug-protein interactions by terms for each protein binding site and uses deep learning to extract features that govern the complex interactions between the two.
“As AI has become more available, this has become something that AI can tackle,” says study co-author Ozlem Garibay, assistant professor in UCF’s Department of Industrial Engineering and Management Systems. “You can try many variations of protein-drug interactions and find out which ones are more likely to bind or not.”
The model they developed, called AttentionSiteDTI, is the first to be interpretable using the language of protein binding sites.
This work is important because it will help drug designers identify complex protein binding sites along with their functional properties, which are key to determining whether a drug will be effective.
The researchers achieved this by devising a self-healing method that teaches the model which parts of the protein interact with drug compounds, while achieving sophisticated predictive performance.
The mechanism’s self-focusing ability works by selectively focusing on the most relevant parts of the protein.
The researchers validated their model using laboratory experiments that measure the binding interactions between compounds and proteins and then compared the results to their model’s computational predictions. As drugs to treat Covid are still of interest, experiments also include testing and quantifying drug compounds that bind to the spike protein of the SARS-CoV2 virus.
Garibay says the high agreement between laboratory results and computational predictions demonstrates the potential of AttentionSiteDTI to pre-screen potentially effective drug combinations and accelerate the discovery of new drugs and the repurposing of existing drugs.
“This high-impact research is only possible because of the interdisciplinary collaboration between materials engineering and AI/ML and computer scientists to address discoveries related to Covid,” says Sudipta Seal, study co-author and chair of UCF’s Department of Materials Science and Engineering.
Mehdi Yazdani-Jahromi, a doctoral student in UCF’s College of Engineering and Computer Science and lead author of the study, says the work represents a new direction in drug pre-screening.
“This enables researchers to use AI to more accurately identify drugs to respond quickly to new diseases,” says Yazdani-Jahromi. This method also allows researchers to identify the best binding site of a virus protein to focus on in drug design.”
“The next step in our research is to use the power of AI to design new drugs,” he says. “This may be the next step in naturally preparing for a pandemic.”
