New AI System Know As ReLeaSE Can Design Drugs From Scratch

Navin Bondade 0 Comments Artificial Intelligence, Data Science, Deep Learning, Machine Learning

Have you remembered Walter White of Breaking Bad, the genius chemist who can make drugs of any kind? Yes! That genius friction character has now born into reality but in the form an AI machine.

Scientists of the University of North Carolina at Chapel Hill Eshelman School of Pharmacy has created an artificial intelligence system that can learn to design drug molecules from scratch.

The name of this system is Reinforcement Learning for Structural Evolution or we can simply say ReLeaSE.

The ReLeaSE is an interesting algorithm and a computer program that comprises not one but two neural networks. These two neural networks perform activities similar to a teacher and a student.

What that means, is that the both neural network can learn new things like a student and can teach and explain new things like a teacher. It very much like is a multipersonality creature.

As a teacher ReLeaSE knows the 1.7 million biologically active molecules (active molecules are the linguistic rules behind the vocabulary of chemical structures).

And as a student ReLeaSE works with other teachers and researchers to get better at proposing and explaining molecules that are likely to be useful as new medicines.

The team has train the AI with millions of molecules and compound data. The team has now using ReLeaSE method to design molecules with customized physical properties like solubility in water and melting point.

If the system succeeds in producing desired results, then can design new compounds with inhibitory activity against an enzyme. The scientists also using ReLeaSE method to generate molecules with properties that they specified such as desired bioactivity and safety profiles.

The ReLeaSE is a powerful innovation that can be used by the pharmaceutical industry to identify viable drug candidates. It is capable of virtual screening and the computational method.

With the help of Virtual screening, scientists can evaluate existing large chemical libraries.

“A scientist using virtual screening is like a customer ordering in a restaurant. What can be ordered is usually limited by the menu,” said Olexandr Isayev from UNC. “We want to give scientists a grocery store and a personal chef who can create any dish they want,” said Isayev.

The creator of ReLeaSE is Alexander Tropsha, Olexandr Isayev, and Mariya Popova.

They are all from the UNC Eshelman School of Pharmacy. The University has applied for a patent for the technology, and the team published a proof-of-concept study in the journal Science Advances last week.

The ReLeaSE will be is not be less than any revolution in the medicines industry. It has the ability to create and evaluate new molecules which can be a cure for many harmful diseases. In the future, a fully developed and trained ReLeaSE will definitely boost the development of new medicines.

Tropsha said “The ability of the algorithm to design new, and therefore immediately patentable, chemical entities with specific biological activities and optimal safety profiles should be highly attractive to an industry that is constantly searching for new approaches to shorten the time it takes to bring a new drug candidate to clinical trials,” said Tropsha.