http://www.digitaljournal.com/tech-and-science/science/ai-powered-drug-discovery-in-days-not-years/article/557215

AI-powered drug discovery in days, not years

Posted Sep 4, 2019 by Tim Sandle
A new study has found that artificial intelligence can drastically speed up drug discovery, from years to just days. This has significant implications for the discovery of new medicines for the pharmaceutical industry and healthcare sector.
File Photo: Dr. Scott Walper  a molecular biologist in the Naval Research Laboratory s (NRL) center ...
File Photo: Dr. Scott Walper, a molecular biologist in the Naval Research Laboratory's (NRL) center for Biomolecular Science and Engineering advises Ebony Stadler, a biomedical engineering rising senior from North Carolina Agricultural and Technical State University, as she performs an experiment in the lab.
Office of Naval Research (CC BY 2.0)
The company Insilico Medicine, a Honk Kong based biotech enterprise, has launched the results of their new artificial intelligence powered drug discovery process called GENTRL. This is an acronym for Generative Tensorial Reinforcement Learning) As described in the study, GENTRL was able to successfully identify six promising treatments for fibrosis in just 21 days, with one of the treatments found to be effective in treating mice with renal fibrosis (the thickening and scarring of connective tissue in the kidney).
Based on this, the study authors conclude that GENTRL promises to accelerate the drug discovery process, potentially saving the pharmaceutical industry billions, bringing affordable drugs to market faster and save lives as a result.
The reason why time savings are important when it comes to finding new medicines is because time equates to money and there is an estimated $2.6-billion price tag of developing a new treatment. Another reason for the high cost is because of the many false starts, which can occur at any stage of the development process through to clinical trial.
Advances in artificial intelligence are modernizing several aspects of our lives, deploying personified knowledge and learning from the solutions it produces to address not only specific but also complex problems. This also applies to pharmaceutical development, and evidence suggests that artificial intelligence can improve the efficiency of the drug development process and collaboration of pharmaceutical industry giants with AI-powered drug discovery firms.
According to BenchSci, artificial intelligence can aid pharmaceutical drug development by: Aggregating and synthesizing information, establishing suitable biomarkers, generating data and models, repurposing existing drugs, generating novel drug candidates, and through analyzing real world evidence.
With the new study, molecules "imagined" by the GENTRL techniques were rapidly synthesized, tested in enzymatic, cell-based fibrosis, metabolic stability, microsomal stability assays, and in mice. Insilico Medicine assessed the GENTRL system for drug discovery in cells and animals and was able to create six new molecules that could address diseases like fibrosis. The company required only 21 days to ideate and produce the new molecules. Of the six newly created molecules, four selectively blocked DDR1, a protein target involved in various disorders including fibrosis, at nanomolar concentration. This presents a promising new treatment for fibrosis.
Discussing this, Alex Zhavoronkov, CEO of Insilico Medicine says: "The development of these first six molecules as an experimental validation is just the start. By enabling the rapid discovery of novel molecules and by making GENTRL’s source code open source, we are ushering in new possibilities for the creation and discovery of new life-saving medicine for incurable diseases — and making such powerful technology more broadly accessible for the first time to the public."
The new research has been published in the journal Nature Biotechnology. The research paper is headed "Deep learning enables rapid identification of potent DDR1 kinase inhibitors."