AlphaFold reveals the structure of the protein universe

Re:AlphaFold reveals the structure of the protein universe by flobosg on Thursday July 28, 2022 @11:56AM (#32266070)

> It ultimately relies on mapping sequence to structure.

So does every structural prediction method.

> if you give it a brand new fold with no relation to other folds, it cannot predict it

That will depend on the number of effective sequences, not the actual fold.

> I work in organisms that have virtually 0 sequence identity.

Then the problem is low sequence coverage, not the protein fold. On a side note, there are sensitive homology search protocols that rely very little on actual sequence identity.

[ Parent | on HN ]

Re:AlphaFold reveals the structure of the protein universe by bamboozled on Thursday July 28, 2022 @04:13PM (#32269552)

So then based on your counter arguments to the OP, have they mapped the entire protein universe ? Or should it say, the “already known protein universe” ?

[ Parent | on HN ]

Re:AlphaFold reveals the structure of the protein universe by flobosg on Thursday July 28, 2022 @05:17PM (#32270228)

Neither the protein sequence nor structure spaces have been fully explored, and the sequence set of UniProt does not represent every single extant protein. My answer is “no”.

[ Parent | on HN ]