Self-taught AI system designs drugs from scratch

Self-taught AI system designs drugs from scratch

Researchers at University of North Carolina at Chapel Hill use an artificial intelligence approach that can teach itself to design new drug molecules from scratch. ReLeaSE stands for Reinforcement Learning for Structural Evolution, and its creators say they believe this application of machine learning can dramatically accelerate the design of new drug candidates.

ReLeaSE is an algorithm and computer program developed at the UNC Eshelman School of Pharmacy. It comprises two neural networks: 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, said K. H. Lee Distinguished Professor Alexander Tropsha, Ph.D., one of the creators of the new AI system. “After learning the molecular alphabet and the rules of the language, the student starts creating new ‘words’, or molecules,” Tropsha said. “If the new word-molecule is realistic and has the desired meaning, the teacher approves. If not, the teacher disapproves, forcing the student to avoid bad words and create good ones.”

By working with the teacher, the student gets better and better at proposing molecules that are likely to be useful as new medicines.

Tropsha and Research Assistant Professor Olexandr Isayev, Ph.D., are the corresponding authors on the study. The lead author is Mariya Popova, a graduate student the School’s Division of Chemical Biology and Medicinal Chemistry and Laboratory for Molecular Modeling.

Isayev said that 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 had is usually limited by the menu,” Isayev said. “We want to give scientists a grocery store and a personal chef who can create any dish they want.”

The UNC-Chapel Hill researchers have been able to use ReLeaSE to generate molecules with properties that they specified, such as desired bioactivity and safety profiles. “We have used the ReLeaSE method to design chemical libraries of molecules with many different properties,” Popova said. “We were able to customize physical properties, such as melting point and solubility in water, and more relevant to drug discovery, design new compounds with inhibitory activity against Janus protein kinase 2, an enzyme that is associated with leukemia.”

Tropsha said he believes that ReLeaSE should be of great interest to the pharmaceutical industry. “The ability of the algorithm to design new, and therefore immediately patentable, chemical entities with specific biological activities and optimal safety profile 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,” he said.

Subscribe to our newsletter

Related articles

Designing better antibody drugs with machine learning

Designing better antibody drugs with machine learning

Artificial intelligence could help to optimise the development of antibody drugs. This leads to active substances with improved properties, also with regard to tolerability in the body.

Using AI to find new uses for existing medications

Using AI to find new uses for existing medications

Scientists have developed a machine learning method that crunches massive amounts of data to help determine which existing medications could improve outcomes in diseases for which they are not prescribed.

Machine learning predicts anti-cancer drug efficacy

Machine learning predicts anti-cancer drug efficacy

With the advent of pharmacogenomics, machine learning research is well underway to predict patients' drug response that varies by individual from the algorithms derived from previously collected data on drug responses.

Network medicine makes drug repurposing effective

Network medicine makes drug repurposing effective

Artificial intelligence can increase the effectiveness of drug repositioning or repurposing research.

Enabling AI-driven advances without sacrificing privacy

Enabling AI-driven advances without sacrificing privacy

Secure AI Labs is expanding access to encrypted health care data to advance AI-driven innovation in the field.

Will we grow and eat your own vaccines?

Will we grow and eat your own vaccines?

The future of vaccines may look more like eating a salad than getting a shot in the arm.

Expanding human-robot collaboration in manufacturing

Expanding human-robot collaboration in manufacturing

To enhance human-robot collaboration, researchers at Loughborough University have trained an AI to detect human intention.

AI finds out what makes human tick

AI finds out what makes human tick

Scientists have developed a machine learning technology to understand how gene expression regulates an organism's circadian clock.

Machine learning improves when social factors are included

Machine learning improves when social factors are included

Machine learning can accurately predict cardiovascular disease and guide treatment — but models that incorporate social determinants of health better capture risk and outcomes for diverse groups.

Popular articles

Subscribe to Newsletter