AlphaFold's Database Grows Over 200x To Cover Nearly All Known Proteins
AlphaFold's protein database has expanded from 1 million to over 200 million catalogued protein structures - nearly all proteins known to science.
Created on August 1|Last edited on August 1
Comment
Since AlphaFold's public access release last year, researchers have used the protein structure predicting AI to further their understanding of the biological building blocks that make up life as we know it.
Thanks to the tireless work done with AlphaFold, and in collaboration with EMBL-EBI, DeepMind has announced the recent expansion of AlphaFold's predicted protein structure database from around 1 million structures to over 200 million.
What does AlphaFold's database expansion mean for the biological sciences?
Because AlphaFold was developed with the express purpose to support the biological sciences by providing open-source use and data, the database's expansion to fill nearly all known proteins will allow researchers in the field to know the structure of a protein without needing to run the AI model themselves.
Without the burden of computing power, and thus money, required to run AlphaFold for any given protein, researchers and scientists can get straight to the important developments with the already generated structure.
The number of species (animals, plants, and everything in between) represented in the database has grown from 10 thousand all the way up to 1 million.
The database is available for download free from Google Cloud, but for even more convenient access, all the protein structures have been added to protein cataloging websites like UniProt.
Find out more
Add a comment
Tags: ML News
Iterate on AI agents and models faster. Try Weights & Biases today.