As part of London Tech Week this week, the formation of the OpenBind consortium was announced. Openbind aims to generate large data sets that can be utilized to train novel AI models ultimately identifying new drugs. This resource will give researchers an unparalleled ability to open up new fronts in the fight against disease- potentially slashing drug development costs by up to £100 billion, while simultaneously sparking the innovation and economic growth which underpins the government’s Plan for Change.
OpenBind will deploy automated chemistry and high-throughput X-ray crystallography to generate the world’s largest collection of data on how drugs interact with proteins; eventually generating more than 500,000 protein - ligand complex structures along with their affinity measurements. This would represent a 20-fold increase over all public data produced in the last half-century - filling a critical gap in the data ecosystem that has slowed the development and evaluation of modern generative models.
More news can be found on the GOV.UK page here.
OpenBind’s senior consortium principal investigators are:
- Professor Frank von Delft (Diamond Light Source and University of Oxford)
- Professor Charlotte Deane (University of Oxford)
- Dr John Chodera (Memorial Sloan Kettering Cancer Centre)
- Dr Mark Murcko (MIT and Disruptive Biomedical LLC)
- Professor Mohammed AlQuraishi (Columbia University)
- Professor David Baker (University of Washington)
- Dr Ed Griffen (MedChemica Limited)
- Professor Paul Brennan (University of Oxford)