DeepMind CASP results

Started by beta_helix

beta_helix Staff Lv 1

Hello everyone!

You might have heard about DeepMind's results at CASP 14 this week, where AlphaFold2 significantly outperformed all other protein structure prediction methods at this past summer's CASP experiment.

We plan to discuss this in more detail once these CASP 14 results are published, but this is a very exciting result that hopefully advances the field of protein structure determination (which was always the ultimate goal of structure prediction).

Many of you who have been here since Foldit's participation in CASP 11 have noticed how our focus has shifted from structure prediction and refinement, to fitting electron density and protein design. This has been particularly evident this year with all your coronavirus efforts.
It is not yet clear how DeepMind's methods will perform with protein design, but the Rosetta community has already incorporated AlphaFold's methods from CASP 13 and we plan to integrate these into Foldit soon.

Lastly, we want to congratulate all of you as DeepMind's co-founder and CEO revealed that Foldit was an inspiration for AlphaFold! Today they gave the keynote talk at the CASP meeting, with an entire slide about Foldit.

Keep up the great folding and keep inspiring everyone!

John McLeod Lv 1

Title: Recent Economist bit mentions Foldit

" … [co-founder] Dr Hassabis recalls being struck by the ability of human amateurs to achieve good results with FoldIt, a science-oriented video game launched in 2008 that invites its players to try folding proteins themselves, and which has generated a clutch of papers and discoveries. … Getting players of FoldIt to explain exactly what they have been up to, though, is tricky."

Bruno Kestemont Lv 1

Is that it's a company holded by Google. Hopefully they will succeed to keep in public domain what comes from public, humans, all of us, skills. May be with the help of US laws.

They shared their algorythm on github here, aknowledging that they used the big archived public domain protein databases:
https://github.com/deepmind/deepmind-research/tree/master/alphafold_casp13

Hopefully they will succeed to keep their pure "research for the common good" attitude, as they curently do during the Covid crisis.

beta_helix Staff Lv 1

That was the exact question I asked them at the conference when they presented their results on Tuesday.