Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

New molecules designed by AI are validated in mice

Insilico Medicine, a company using artificial intelligence (AI) for drug discovery, published a paper on Monday describing new machine learning techniques designed to substantially accelerate and improve the drug discovery process.

The paper, which was published in  Nature Biotechnology, is titled “Deep learning enables rapid identification of potent DDR1 kinase inhibitors.”

The findings describe a timed challenge where the new AI system called Generative Tensorial Reinforcement Learning (GENTRL) had to determine new molecules for drug discovery.

The GENTRL program managed to design six novel inhibitors of DDR1, a kinase target implicated in fibrosis and other diseases, in 21 days.

According to the research, four compounds were active in biochemical assays, and two were validated in cell-based assays. One lead candidate, in particular, was tested and demonstrated favourable pharmacokinetics in mice.

The news comes after the authors of the news study pioneered the field of generative chemistry with seminal publications three years ago.

“This paper is a significant milestone in our journey towards AI-driven drug discovery,” said Alex Zhavoronkov, PhD, and founder and CEO of Insilico Medicine. “We work in generative chemistry since 2015 and when Insilico’s and Alán’s theoretical papers were published in 2016 everyone was very sceptical.

“Now, this technology is going mainstream and we are happy to see the models developed a few years ago and producing molecules against simpler targets being validated experimentally in animals.”

Traditional drug discovery begins with the testing of thousands of small molecules in order to get to just some lead-like molecules, of which a very small percentage pass clinical trials in human patients. 

The fact that molecules generated by GENTRL were validated so quickly, therefore, represents a valuable milestone on the path to more efficient drug discovery powered by artificial intelligence.

Insilico Medicine was founded in 2014 and has so far raised $14.3M in funding. The company is trying to develop a comprehensive drug discovery pipeline utilising artificial intelligence to generate novel molecules with the specified properties for a variety of target classes.

“When integrated into comprehensive drug discovery pipelines,” Zhavoronkov added, “these models work for many target classes and we work with the leading biotechnology companies to push the limits of generative chemistry and generative biology even further.” 

Image via Eucalyp on Flaticon.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter