Israeli researchers develop AI method to create antiviral drugs

JERUSALEM, April 8 (Xinhua) -- Israeli researchers have created an artificial intelligence (AI) method for developing drugs against several types of viruses, the Israel Institute of Technology (Technion) in northern Israel said Thursday.

Unlike antibiotics, antiviral drugs are typically designed to target one virus, making it uneconomical for drug companies to invest in developing new antiviral drugs for treating multiple infectious diseases.

In a study, published in the journal Nature Communication, researchers from the Technion and the Ben Gurion University demonstrated a combined method of synthetic biology and machine learning for developing such antiviral drugs.

This method is designed to discover molecules which can bind proteins from two distinct viruses.

The traditional method for identifying therapeutics is to apply a low-throughput and labor-intensive screen for molecules that might perform the required function.

The new approach, in contrast, maps the "space" of potential interactions so that molecules with the desired properties can be reliably predicted.

The researchers first generated a large dataset of various known and suspected potential virus-protein-binding molecules.

Then, using a neural network, they formed a mathematical function that can identify regions of high binding capability, and extract "predicted" molecules not previously tested.

These unseen or predicted molecules could then be synthesized and tested for the desired biological functionality for future antiviral drugs.