In a significant development, a Hong Kong-based health start-up has used Artificial Intelligence (AI) to design a drug in just 21 days. The drug showed potential treatments for fibrosis – a discovery that can speed up drug designing for various incurable diseases.
The AI system called generative tensorial reinforcement learning (GENTRL) helped design six promising treatments for fibrosis in 21 days.
Four compounds were active in biochemical assays, and two were validated in cell-based assays. One lead candidate was tested and demonstrated favourable pharmacokinetics in mice, the start-up stated in a paper published in the journal Nature Biotechnology.
The new technology leveraged the start-up’s ground-breaking academic research in 2016 about using modern AI techniques of generative adversarial networks (GAN) and generative reinforcement learning (RL) to accelerate drug discovery.
In the Nature Biotechnology paper titled “Deep learning enables rapid identification of potent DDR1 kinase inhibitors”, this marks the first time the generative reinforcement learning technology was used to generate novel small molecules for a protein target that were validated in vitro and in vivo in just 46 days.
In comparison, traditional drug discovery starts with the testing of thousands of small molecules in order to get to just a few lead-like molecules and only about one in 10 of these molecules pass clinical trials in human patients.
In a similar technique used by another company to outcompete human GO players, GENTRL – powered by generative chemistry that utilizes modern AI techniques – can rapidly generate novel molecular structures with specified properties.
The start-up has also made GENTRL’s source code available as open-source on a platform designed by an American company that provides hosting for software development version control using Git.
The development of these first six molecules as an experimental validation is just the start, the start-up’s CEO noted.
He also stated that this paper is a significant milestone in the start-up’s journey towards AI-driven drug discovery.
Now, this technology is going mainstream and the models developed a few years ago and producing molecules against simpler targets being validated experimentally in animals are welcomed.
When integrated into comprehensive drug discovery pipelines, these models work for many target classes.
The firm will continue working with the leading biotechnology companies to push the limits of generative chemistry and generative biology even further.
By enabling the rapid discovery of novel molecules and by making GENTRL’s source code open source, new possibilities for the creation and discovery of new life-saving medicine for incurable diseases are being ushered in.
The company and its scientists are dedicated to transforming the pharmaceutical industry by developing and applying the next-generation deep learning approaches to every step of the drug discovery and drug development process.
The start-up is constantly collaborating with the most innovative biopharmaceutical companies with disease-relevant assays to validate its solutions and generate high-quality machine-learnable data.
An expert noted that the reduction of cycle time and overall cost of goods is critical to the future success of Pharma drug discovery activities.
In its paper, the HK start-up highlights a novel AI-based technology (GAN-RL) which allowed them to identify lead molecules with efficacy in animal models in notably short timeframes. If this technology proves broadly useful it may well have transformational potential for future lead generation efforts, according to the Adjunct Professor, School of Pharmacy at a North Carolina university.