Protein Folding Article

[Pokey]

Google's DeepMind and Folding:

Ars Technica Article

 

[Endgame124]

So, does this make F@H obsolete?

 

[biodoc]

So, does this make F@H obsolete?

The short answer is no. F@H used to study folding dynamics of proteins but moved on to study protein function using molecular dynamics. For these studies, they need experimentally derived proteins structures. Check out this link.

From the above link:

"There are many experimental methods for determining protein structures. While extremely powerful, they only reveal a single snapshot of a protein’s usual shape. But proteins have lots of moving parts, so we really want to see the protein in action. The structures we can’t see experimentally may be the key to discovering a new therapeutic."

 

[biodoc]

This is a better commentary published in Nature.

A lot of the work at "folding@home" is using molecular dynamics to identify new sites for therapeutic intervention and screening drug-like molecules for binding in those sites (virtual screening). Perhaps the scientists at Deepmind could use a similar machine learning approach to develop better virtual screening algorithms.

 

[Endgame124]

Here is the folding at home commentary on deep mind:

Protein folding and related problems remain unsolved despite AlphaFold’s advance - Folding@home

TL;DR: DeepMind’s AlphaFold marks a tremendous advance in our ability to predict the dominant structure of a protein. How proteins get there, and many other problems related to protein folding,…

foldingathome.org