Researchers have developed new artificial intelligence screening techniques that can help in quickening the process of drug discovery. Developing life-saving drugs can cost a lot of money and time, thus, it is a new hope for shortening 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 of the drug test candidates were published recently in the journal Briefings in Bioinformatics.
AttentionSiteDTI model for drug discovery
The technique shows drug-protein interactions using words for every protein binding part and deep learning to know about the features that guide the complex interactions between these two. The model they developed is known as AttentionSiteDTI, and is the first one to be interpretable through the language medium of protein binding parts.
Study co-author Ozlem Garibay, an assistant professor in UCF’s Department of Industrial Engineering and Management Systems, said, "With AI becoming more available, this has become something that AI can tackle. You can try out so many variations of proteins and drug interactions and find out which are more likely to bind or not."
They achieved the milestone by following a self-attention mechanism that makes the model know about the parts of protein interaction with the drug compounds, while attaining state-of-the-art performance. The mechanism’s capability is to particularly focus on the most important sites of the protein. The researchers then got a confirmation for their model through lab experiments that tracked binding interactions between compounds and proteins and then compared the conclusions with the ones their model had predicted with AI.
Sudipta Seal, study co-author and chair of UCF’s Department of Materials Science and Engineering, said, "This high impact research was only possible due to interdisciplinary collaboration between materials engineering and AI/ML and Computer Scientists to address COVID related discovery."
Mehdi Yazdani-Jahromi, a doctoral student in UCF’s College of Engineering and Computer Science and the study’s lead author, said that the work is a new direction towards drug pre-screening. "This enables researchers to use AI to identify drugs more accurately to respond quickly to new diseases. This method also allows the researchers to identify the best binding site of a virus’s protein to focus on in drug design. The next step of our research is going to be designing novel drugs using the power of AI. This naturally can be the next step to be prepared for a pandemic," he added.