A predicted structure of the SARS-CoV-2 membrane protein. Credit: DeepMind
DeepMind’s AlphaFold system has been used to produce structural predictions of understudied proteins of SARS-CoV-2, the virus that causes COVID-19.
These structures have now been made freely available to the research community – a move supported by Crick researchers including Steve Gamblin, Director of Scientific Platforms.
Knowing a protein’s structure provides an important resource for understanding how it functions, but experiments to determine the structure can take months or longer and are not always successful.
AlphaFold, DeepMind’s deep learning system, predicts protein structures when no structures of similar proteins are available. This prediction system is still being developed to improve its accuracy.
The proteins released today are only those for which there is a lack of suitable templates or are otherwise difficult for template modelling. While these understudied proteins are not the main focus of current therapeutic efforts, they may add to researchers’ understanding of SARS-CoV-2.
The initial results have been shared with structural biologists and virologists at the Crick who have supported the move to release the structures rapidly and under an open licence.
Commenting on the release of the structures, Steve Gamblin said: “Responding to the emergence of COVID-19 is clearly a research priority. Making these protein structures freely available will provide an important resource to the global research community in understanding the disease process and developing approaches to combat it.”