News for hackers. Stuff that matters.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by antipaul on Monday November 30, 2020 @08:10PM (#25261104)
As usual with ML, I now wonder how “similar” the test set is to the training set, compared to the examples that are neither in the training set, nor the test set:

TODO: 200 million - 170,000 training - 100 test ~= 199.8 million proteins

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by kxs on Tuesday December 01, 2020 @04:38AM (#25263822)
They trained on 170k sequences/ structures/ proteins, each sequence has 10s to 100s or even 1000s amino acids. Structure is much more conserved than sequence. Out of the 100 targets, roughly 1/4th have no similarity to known structures, so there shouldn't be an overlap for those with the training set. They did very well on those targets.