Accelerate drug discovery using an AI-based screening approach

It takes decades and billions of dollars to develop life-saving drugs. However, scholars in University of Central Florida The UCF hopes to speed up this process with a new drug screening process focused on artificial intelligence (AI).

Image Credit: University of Central Florida

This technology incorporates natural language processing methods and replicates drug-protein interactions, achieving an accuracy of up to 97% in finding preferred candidate drugs. The results were recently reported in the journal Briefings in Bioinformatics.

The method indicates drug-protein interactions through words for each protein binding region and uses deep learning to derive features that control the multifaceted interactions between the two.

With AI becoming more available, this is becoming something that AI can tackle. You can experiment with many different forms of proteins and drug interactions and see which one is most likely to bind or not.

Ozlem Garibay, study co-author and assistant professor, Department of Industrial Engineering and Management Systems, University of Central Florida

The UCF model, known as AttentionSiteDTI, is the first model that can be decoded using the language of protein binding regions.

The study is vital because it will help drug engineers discover essential protein binding regions along with their functional features, which is critical to determining whether a drug will work.

The scientists achieved this by developing a self-attention mechanism that enables the model to learn which regions of the protein interact with drug compounds while achieving advanced prediction performance. The mechanism’s self-attention ability works by selectively focusing on the areas most relevant to the protein.

The model was confirmed using laboratory experiments that evaluated binding interactions between proteins and compounds and then compared the results with those whose model had been computationally estimated. As the drugs used to treat SARS-CoV-2 (COVID-19) are important, the trials also included testing and confirmation of drug compounds that would bind to the spike protein of the SARS-CoV-2 virus.

Garibai says that the exceptional agreement between lab results and computational estimates shows the potential for AttentionSiteDTI to pre-screen potentially effective drug compounds and accelerate the search for new drugs and the reuse of existing drugs.

This high-impact research was only possible due to the interdisciplinary collaboration between materials engineering, AI/ML, and computer scientists to tackle COVID-related discoveries.

Sudipta Seal, study co-author and chair, Department of Materials Science and Engineering, University of Central Florida

Mehdi Yazdani Jahromi, a doctoral student in the College of Engineering and Computer Science at the University of California, and lead author of the study, says the work adds a new path in drug prescreening.

This allows researchers to use AI to more accurately identify drugs to respond quickly to new diseases. This method also allows researchers to determine the best binding site for the virus protein to focus on in drug design. The next step in our research will be to design new drugs using the power of artificial intelligence. Of course, this could be the next step in preparing for a pandemic.

Mehdi Yazdani Jahromi, study lead author and PhD student, College of Engineering and Computer Science, University of Central Florida

The study received funding from UCF’s Seed Funding Program for Big Data and Internal Artificial Intelligence.

Study co-authors also included Nilufer Yousfi, a postdoctoral researcher in the UCF’s Complex Adaptive Systems Laboratory in the UCSD School of Engineering and Computer Science. Elayaraja Kolanthai, is a postdoctoral researcher in the Department of Materials Science and Engineering at the University of California. Aida El-Teibi, a doctoral student in the Department of Industrial Engineering and Management Systems at the University of California. and Craig Neal, a postdoctoral researcher in the University of California’s Department of Materials Science and Engineering.

Garibai completed her Ph.D. in Computer Science from UCLA, joined UCSD Department of Industrial Engineering and Management Systems in 2020, part of the College of Engineering and Computer Science, and earlier, worked for 16 years in the IT field at UCLA Research Office .

Journal reference:

Yazdani Jahromi, M. and others. (2022) AttentionSiteDTI: An interpretable graph-based model for predicting drug-target interaction using sentence-level relationship classification in NLP. Briefings in Bioinformatics. doi.org/10.1093/bib/bbac272.

source: