Google’s parent company Alphabet announced the launch of a new company this week dedicated to applying deep learning methods to drug discovery.
The new company is called Isomorphic Laboratories and will be led by Demis Hassabis, also the CEO of DeepMind, the AI-research company that utilized its deep learning model, AlphaFold2, to predict more than 350,000 protein structures about a year ago. DeepMind released this database and the model’s code to the public earlier this year.
DeepMind’s database and code are valuable tools that can be utilized by drug companies to accelerate drug development. The fact that these assets were open-sourced is quite remarkable and represents an exceedingly generous dedication to the public benefit.
As CEO of both companies, Hassabis remarked to STAT News that “You can think of [Isomorphic] as a sort of sister company to DeepMind… The idea is to really forge ahead with the potential for computational AI methods to reimagine the whole drug discovery process.”
Isomorphic Labs will reportedly confront the problem of drug discovery differently than existing companies in the AI-drug discovery space. “A lot of pharma companies did come to us to discuss AlphaFold and how they could use it, and through that we understood a lot more about what other things they would need,” Hassabis reportedly said.
Isomorphic aims to build predictive models to anticipate how drugs will perform and possibly design novel molecules, and leverage this platform as a service meeting the needs of drug developers, rather than developing its own pipeline of drug candidates.
“Biology is far too complex and messy to ever be encapsulated as a simple set of neat mathematical equations,” Hassabis said. “But just as mathematics turned out to be the right description language for physics, biology may turn out to be the perfect type of regime for the application of AI.”
Isomorphic will be based in London and hire in the range of 30 people in a startup phase.
STAT News has a great writeup on this launch, as does Fierce Biotech and The Verge.
Disclaimer: The information contained in this posting does not, and is not intended to, constitute legal advice or express any opinion to be relied up legally, for investment purposes or otherwise. If you would like to obtain legal advice relating to the subject matter addressed in this posting, please consult with us or your attorney. The information in this post is also based upon publicly available information, presents opinions, and does not represent in any way whatsoever the opinions or official positions of the entities or individuals referenced herein