Pioneering AI drug development, with Alex Zhavoronkov

This episode discusses progress at Insilico Medicine, the AI drug development company founded by our guest, longevity pioneer Alex Zhavoronkov.1.20 In Feb 2022, Insilico got an IPF drug into phase 1 clinical trials: a first for a wholly AI-developed drug1.50  Insilico is now well-funded; its software is widely used in the pharma industry2.30 How drug development works. First you create a hypothesis about what causes a disease4.00 Pandaomics is Insilico’s software to generate hypotheses. It combines 20+ AI models, and huge public data repositories6.00 This first phase is usually done in academia. It usually costs $ billions to develop a hypothesis. 95% of them fail6.50 The second phase is developing a molecule which might treat the disease7.15 This is the job of Insilico’s Chemistry 42 platform7.30 The classical approach is to test thousands of molecules to see if they bind to the target protein7.50 AI, by contrast, is able to "imagine" a novel molecule which might bind to it8.00 You then test 10-15 molecules which have the desired characteristics8.20 This is done with a variety of genetic algorithms, Generative Adversarial Networks (GANs), and some Transformer networks8.35 Insilico has a “zoo” of 40 validated models10.40 Given the ten-fold improvement, why hasn’t the whole drug industry adopted this process?10.50 They do all have AI groups and they are trying to change, but they are huge companies, and it takes time11.50 Is it better to invent new molecules, or re-purpose old drugs, which are already known to be safe in humans?13.00 You can’t gain IP with re-purposed drugs: either somebody else “owns” them, or they are already generic15.00 The IPF drug was identified during aging research, using aging clocks, and a deep neural net trained on longitudinal data17.10 The third phase is where Insilico’s other platform, InClinico, comes into play17.35 InClinico predicts the results of phase 2 (clinical efficacy) trials18.15 InClinico is trained on massive data sets about previous trials19.40 InClinico is actually Insilico’s oldest system. Its value has only been ascertained now that some drugs have made it all the way through the pipeline22.05 A major pharma company asked Insilico to predict the outcome of ten of its trials22.30 Nine of these ten trials were predicted correctly23.00 But the company decided that adopting this methodology would be too much of an upheaval; it was unwilling to rely on outsiders so heavily24.15 Hedge funds and banks have no such qualms24.25 Insilico is doing pilots for their investments in biotech startups26.30 Alex is from Latvia originally, studied in Canada, started his career in the US, but Insilico was established in Hong Kong. Why?27.00 Chinese CROs, Contract Research Organisations, enable you to do research without having your own wetlab 28.00 Like Apple, Insilico designs in the US and does operations in China. You can also do clinical studies there28.45 They needed their own people inside those CROs, so had to be co-located29.10 Hong Kong still has great IP protection, financial expertise, scientific resources, and is a beautiful place to live29.40 Post-Covid, Insilico also had to set up a site in Shanghai30.35 It is very frustrating how much opposition has built up against international co-operation32.00 Anti-globalisation ideas and attitudes are bad for longevity research, and all of biotech33.20 Insilico has all the data it needs. Its bottleneck is talent35.00 Another requirement is co-operation from governments and regulators, who often struggle to sort the chaff from the wheat in self-proclaimed AI companies37.00 Longevity research is the most philanthropic activity in the world37.30 Longevity Medicine Course is available to get clinical practitioners up to speed with the sectorC-Suite PerspectivesElevate how you lead with insight from today’s most influential executives.Listen on: Apple Podcasts   Spotify