AlphaFold: a solution to a 50-year-old grand challenge in biology

Post by aardvarkr » Mon, Nov 30, 2020, 4:38 PM UTC

dekhn wrote: post #82

comicjk wrote: post #60

CASP (Critical Assessment of protein Structure Prediction) is calling it a solution. To quote from the article: "We have been stuck on this one problem – how do proteins fold up – for nearly 50 years. To see DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts, wondering if we’d ever get there, is a very special moment." --Professor John Moult C…

It's an improvement- and a big one- but not a solution to the problem. It mainly shows just how stuck the community had gotten with their techniques and how recently improvements in DNNs and information theory methods can be exploited if you have lots of TPU time.

Post by entropicdrifter » Mon, Nov 30, 2020, 4:38 PM UTC

mdjt wrote: post #96

jeffbee wrote: post #53

Pretty interesting that they only used about $15k worth of resources (retail price) to achieve this. It's not a technique that would have been out of reach for other organizations based only on not being able to afford the compute.

Based on the going rate of a 32-core TPUv3 slice ($32/hr USD) running "for a few weeks", isn't this closer to $65k USD?

Post by shawnz » Mon, Nov 30, 2020, 4:38 PM UTC

Rochus wrote: post #75

candiodari wrote: post #58

Earlier quoted context omitted.

Given the DNA code for one of the "machines" that run cells, we can generate an atomic model of that machine. This means we can "compile" (one part of) the DNA code. It was already possible, but so slow that entire datacenters would spend months calculating this for a single protein and even then we can't use them on the really complex ones at all, necessitating things like neutron spectroscopy which are totally insa…

This is about proteins, not DNA.

Post by carlob » Mon, Nov 30, 2020, 4:40 PM UTC

derefr wrote: post #37

fabian2k wrote: post #26

Earlier quoted context omitted.

Protein folding is a big and important problem, so this is certainly big news if it works as well as it seems. But I wouldn't assume that this changes everything, we can already determine how proteins fold by experimental work. The disadvantage is that this is a lot of work, though the methods there also improved a lot. One question is how robust the predictions are that DeepMind produces. I would also assume that ri…

We can already determine how a few proteins (170k — which sounds like a lot, but which is only 0.09% of all currently-catalogued protein sequences) fold by experimental work. What an accurate model of protein folding allows us to do, is to take our big database of DNA, predict protein foldings for all of it, and then stand up a search index for this database, keying each amino-acid "row" by the "words" of its predict…

Post by foota » Mon, Nov 30, 2020, 4:41 PM UTC

woeirua wrote: post #97

asdfasgasdgasdg wrote: post #68

Earlier quoted context omitted.

> the outstanding question as far as to whether or not this is useful for evaluating novel proteins That is not an outstanding question. The test on which DeepMind scored high marks is a test of how well the algorithm folds novel proteins -- proteins whose ground-truth structure has not yet been published.

We’d have to see the distribution of GDT scores evaluated on unknown proteins to say anything about how confident we can be. If the distribution is tightly distributed around the median then great, this works really well. If the variance is large though then you’re going to have a hard time using this for meaningful predictions.