Scientists have developed an artificial intelligence (AI) system that can learn to design drug molecules from scratch, potentially accelerating the development of new medicines. The system, called Reinforcement Learning for Structural Evolution (ReLeaSE), comprises two neural networks which can be thought of as a teacher and a student. The teacher knows the syntax and linguistic rules behind the vocabulary of chemical structures for about 1.7 million known biologically active molecules.
By working with the teacher, the student learns over time and becomes better at proposing molecules that are likely to be useful as new medicines. "If we compare this process to learning a language, then after the student learns the molecular alphabet and the rules of the language, they can create new 'words,' or molecules," said Alexander Tropsha, from the University of North Carolina (UNC) at Chapel Hill in the US.
"If the new molecule is realistic and has the desired effect, the teacher approves. If not, the teacher disapproves, forcing the student to avoid bad molecules and create good ones," said Tropsha. ReLeaSE is a powerful innovation to virtual screening, the computational method widely used by the pharmaceutical industry to identify viable drug candidates. Virtual screening allows scientists to evaluate existing large chemical libraries, but the method only works for known chemicals. ReLeASE has the unique ability to create and evaluate new molecules.
"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, one of the creators of ReLeaSE. "We want to give scientists a grocery store and a personal chef who can create any dish they want," said Isayev. The team has used ReLeaSE to generate molecules with properties that they specified, such as desired bioactivity and safety profiles.
They also used the ReLeaSE method to design molecules with customized physical properties, such as melting point and solubility in water, and to design new compounds with inhibitory activity against an enzyme that is associated with leukemia.
"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.
Article Type: Report Sections: Science Technology Agencies: PTI Cities: Washington Tags: Artificial Intelligence Drugs medicine Reinforcement Learning for Structural Evolution release Thu, 2 Aug 2018-09:07am Date updated: Thursday, 2 August 2018 - 9:07am Article Images:
Short URL: dnai.in/fzbx Embargo: Syndicate: Hide lead image: Page views: 26 From Print Edition: Highlights: