Within the longevity research community, Alex Zhavoronkov is well-known for his relentless focus. He works seven days a week and takes no holidays. The hard work is paying off: In February, Insilico Medicine, the AI drug development company he founded, announced the first phase 1 clinical trials for a wholly AI-developed drug. Following a series of investment rounds in the rest of the year, the company is now well-funded, and its software is widely used in the pharma industry. Alex explains the company’s progress in the latest episode of the London Futurist Podcast.
Three phases of drug development
Drug development is a long and complicated business, but you can break it down into three phases. First you create a hypothesis about what causes a disease. The culprit is usually a protein, or a set of them. There are more than 60,000 targets to go after, and 10,000 diseases. This first phase is the most important of the three, and is usually done in academia, where it costs billions of dollars to develop a hypothesis, and 95% of them turn out to be false. Insilico has created a software platform called Pandaomics to generate these hypotheses. It comprises more than twenty AI models, which are trained on huge public data repositories.
The second phase is developing a molecule which might treat the disease. Insilico’s platform for this second phase is called Chemistry 42. Where traditional drug companies will test thousands of molecules to see if they bind to the target protein, AI allows you to look at how a protein folds, and imagine a molecule which might bind to it. You then only need to test a dozen or so molecules which have the desired characteristics. Insilico does this with a variety of Generative Adversarial AI Networks, or GANs, and also some Transformer models. Alex describes its collection of 40 validated models as a “zoo”.
The third phase in drug development is testing for efficacy and safety. Insilico’s platform for this is called InClinico, and it re-uses some of the AI models from the other two platforms, although it is actually the company’s oldest platform. It is trained on massive data sets about previous clinical trials, and has been validated on drugs which have made it all the way through the pipeline.
Massive savings of time and money
Insilico and other companies using AI to develop drugs have cut the time and money involved in the process by as much as 90%. Even more important, they have increased the success rate of candidate drugs. So why hasn’t the whole drug industry adopted their processes? Alex says that the big pharma companies do all have AI groups, and they are trying to change, but they are huge organisations, and it takes time.
He offers the example of a major drug company which validated InClinico over several months, but decided to stop using it because it could not bring itself to allow outsiders to determine the fate of its multi-billion development programmes. There are no such concerns, however, in the hedge funds and banks which are betting on biotech startups, so for the moment, this is the sweet spot for Insilico.
One way to shorten the timeline of drug development is to re-purpose existing drugs for new diseases, since they are already known to be safe for human use. The problem with this is that either somebody else owns the intellectual property (IP) in these drugs, and you have to license them, or they are already generic, which means there is little prospect of earning a commercial return on the development costs.
Global is good
Insilico is very much a global organisation. Alex was born in Latvia, he studied in Canada, he started his career in the US, and he established Insilico in Hong Kong. Using Contract Research Organisations (CROs) in China enabled Insilico to do research without having its own wetlab. It is also easier in some ways to do clinical studies in China, although the company has to duplicate them in other territories which may not accept foreign data. Alex reports that Hong Kong still has great IP protection, deep financial expertise, world-class scientific resources, and is a beautiful place to live. Post-Covid, Insilico has also set up a site in Shanghai.
Alex is frustrated by the growing resistance to international co-operation in pharmaceutical research. Large research projects need all the world’s money and talent, and when successful, they help the whole world. To Alex’s mind, the most important of these large-scale research projects is understanding and preventing aging. It is vital, he argues, to get clinicians up to speed with longevity research, and to this end, he and some colleagues have developed the Longevity Medicine Course. Alex’s relentless focus is sustained by his conviction that longevity research is the world’s most valuable philanthropic activity.
