News for hackers. Stuff that matters.
Re:AlphaFold at CASP13: What just happened? by sanxiyn on Monday December 10, 2018 @04:39AM (#18646499)
Eh... no? If you look at abstracts, Zhang group (the second place) also used "deep-learning based contact predictor". Really, the usage of deep learning was kind of standard long before CASP13.

If you read OP, AlphaFold's main innovation is predicting distance instead of contact (regression instead of binary classification), which was also independently developed by Xu, and further, using probability distribution over distance instead of simply choosing the best distance.

Re:AlphaFold at CASP13: What just happened? by HarryHirsch on Monday December 10, 2018 @03:45PM (#18651028)
Yes, you wonder how Alphafold compares with the combined wisdom of Foldit. You start out with a secondary structure prediction from Zhang lab and ask a panel of experienced humans to fold up the protein into a plausible tertiary structure. As a human you have a good idea what larger pieces fit where, but AI still has problems with the large picture, cf. the leopard sofa problem.