AlphaFold 2: open code and database, biology accelerates
In one sentence DeepMind publishes AlphaFold 2 code and weights on GitHub and, with EMBL-EBI, releases a database with predicted structures for 350,000 human and model-organism proteins.
Six months after winning the CASP14 protein-folding challenge, DeepMind puts two things online: the AlphaFold 2 code, and a database with the structures of hundreds of thousands of proteins already computed.
It means a biologist, pharmacologist, or any researcher no longer has to wait months and pay for expensive experimental techniques to know how a protein folds: they look it up or compute it from home.
One of the few times an AI model immediately, visibly changes the daily work of an entire scientific community.
Companies
DeepMind, EMBL-EBI
Tools
AlphaFold 2
Tags
Sources