Researchers at Meta (formerly Facebook, headquartered in Menlo Park, California) have used AI to predict the structures of some 600 million proteins from bacteria, viruses and other microorganisms that haven’t been characterized. These are the structures we know the least about. “These are incredibly mysterious proteins. I think they offer the potential for great insight into biology,” says Alexander Rives, the research lead of Meta AI’s protein team. The scientists generated the predictions — described in a 1 November preprint1 — using a ‘large language model’, a type of AI that can predict text from just a few letters or words.
Read more here.
This is a reminder to apply for the Instruct-ERIC R&D Pilot Call - get funding of up to €15,000!
Closing 14:00 CEST on 15 April, the Instruct-ERIC R&D Funding Call invites early career researchers to submit proposals to access Instruct technology, equipment, and expertise from our 27 facilities across Europe for small scale pilot research projects in integrated structural biology.
Register now for the 32nd edition of the Instruct-ERIC Structure Meets Function webinar series, taking place on Zoom, 17 April at 11:00 CEST.
The latest webinar will have two speakers who have accessed the Instruct-ERIC facilities, expertise, and machinery via the ISIDORe project.
Talk 1: Nikitas Georgiou - National and Kapodistrian University of Athens
Title: Potential anti-inflammatory drugs
Talk 2: Séverine Padiolleau - Université de Technologie de Compiègne
Title: Identification of aptamers interacting with a protein target involved in lyme disease