Therefore, structures are often determined as part of targeted scientific investigations, but no project so far has systematically determined structures for all proteins made by the body.
In fact, only 17% of the proteome is covered by an experimentally confirmed structure.
Commenting on AlphaFold's predictions, Professor McGeehan said: "This is just the vitesse - the fact that it took us six months per structure and now it takes a few minutes. We couldn't really have predicted it would happen so quickly. "
" When we first sent our seven sequences to the DeepMind team, two of which we already had the experimental structures. We were therefore able to test them on their return. It was one of those times - to be honest - when the hairs stood on end on my neck because the [AlphaFold] structures produced were identical. "
Professor Edith Heard, of EMBL said: "This will transform our understanding of how life works. This is because proteins represent the fundamental building blocks from which living organisms are made. "
" Applications are only limited by our understanding. "
These applications that we can now consider to develop new drugsnts and treatments against diseases, to design future crops capable of resisting climate change or enzymes capable of breaking down the plastic that permeates the environment.
Professor McGeehan's group is already using data from AlphaFold to help develop enzymes to break down plastic faster. He said the program provided predictions for proteins of interest whose structures could not be determined experimentally - helping to speed up their "multi-year " project.
Dr Ewan Birney, director of the European Institute of Bioinformatics at EMBL, said the structures predicted by AlphaFold were "one of the most important datasets since mapping the human genome " .
DeepMind has partnered with EMBL to make AlphaFold code and protein structure predictions freely available to the global scientific community.
DrHassabis said DeepMind plans to dramatically expand coverage in to almost every sequenced protein known to science - over 100 million structures.
Follow Paul on Twitter.