Generative AI drug discovery breakthrough, with Alex Zhavoronkov

London Futurists

Alex Zhavoronkov is our first guest to make a repeat appearance, having first joined us in episode 12, last November. We are delighted to welcome him back, because he is doing some of the most important work on the planet, and he has some important news.

In 2014, Alex founded Insilico Medicine, a drug discovery company which uses artificial intelligence to identify novel targets and novel molecules for pharmaceutical companies. Insilico now has drugs designed with AI in human clinical trials, and it is one of a number of companies that are demonstrating that developing drugs with AI can cut the time and money involved in the process by as much as 90%.
Selected follow-ups:
https://insilico.com/
ARDD 2023: https://agingpharma.org/
Topics addressed in this episode include:
*) For the first time, an AI-generated molecule has entered phase 2 human clinical trials; it's a candidate treatment for IPF (idiopathic pulmonary fibrosis)
*) The sequence of investigation: first biology (target identification), then chemistry (molecule selection), then medical trials; all three steps can be addressed via AI
*) Pros and cons of going after existing well-known targets (proteins) for clinical intervention, versus novel targets
*) Pros and cons of checking existing molecules for desired properties, versus imagining (generating) novel molecules with these properties
*) Alex's experience with generative AI dates back to 2015 (initially with GANs - "generative adversarial networks")
*) The use of interacting ensembles of different AI systems - different generators, and different predictors, allocating rewards
*) The importance of "diversity" within biochemistry
*) A way in which Insilico follows "the Apple model"
*) What happens in Phase 2 human trials - and what Insilico did before reaching Phase 2
*) IPF compared with fibrosis in other parts of the body, and a connection with aging
*) Why probability of drug success is more important than raw computational speed or the cost of individual drug investigations
*) Recent changes in the AI-assisted drug development industry: an investment boom in the wake of Covid, spiced-up narratives devoid of underlying substance, failures, downsizing, consolidation, and improved understanding by investors and by big pharma
*) The AI apps created by Insilico can be accessed by companies or educational institutes
*) Insilico research into quantum computing: this might transform drug discovery in as little as two years
*) Real-world usage of quantum computers from IBM, Microsoft, and Google
*) Success at Insilico depended on executive management task reallocation
*) Can Longevity Escape Velocity be achieved purely by pharmacological interventions?
*) Insilico's Precious1GPT approach to multimodal measurements of biological aging, and its ability to suggest new candidate targets for age-associated diseases: "one clock to rule them all"
*) Reasons to mentally prepare to live to 120 or 150
*) Hazards posed to longevity research by geopolitical tensions
*) Reasons to attend ARDD in Copenhagen, 28 Aug to 1 Sept
*) From longevity bunkers to the longevity dividend
Music: Spike Protein, by Koi Discovery, available under CC0 1.0 Public Domain Declaration