Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

deepmind.com

Post reply on HN
Print view View original

181–190 of 683 posts

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

#181

Post by WhompingWindows »

mabbo wrote: post #30

Sometimes announcements like this are a bit over-the-top. But what really, to me, cements the 'big-deal' of this is the "Median Free-Modelling Accuracy" graph half way down the page. Scores of 30-45 for 15 years. Now scores of 87-92. This isn't a minor improvement, it's a leap forward.

This reminds me of AlphaGo and AlphaZero. DeepMind was able to produce a very solid model on their first attempt, at both protein folding and at Go (and Starcraft2 as well). Their second models, however, seemed to blow their first out of the water.

This bodes extremely well for the future of computational biology, I'm very excited thinking about the prospects. If we know how a protein folds, we know its shape, meaning we know which shaped/charged molecules are needed to act as suppressors/enhancers of those proteins.

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

#182

Post by breatheoften »

Anyone care to muse about appropriate investment strategies based on the not previously feasible research approaches that might now be possible?

Should we expect to see faster progress in large well capitalized bioscience companies -- or a sudden increase in the viability of smaller biotech and/or biotech startups ...? Are we gonna see top talent fleeing the old biotech companies to start their own ventures with a new belief that the potential for huge reward might suddenly seem achievable?

What kind of companies do we think will be the first that are able to translate this new knowledge into profits?

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

#183

Post by asdfasgasdgasdg »

treis wrote: post #143
mabbo wrote: post #30

Sometimes announcements like this are a bit over-the-top. But what really, to me, cements the 'big-deal' of this is the "Median Free-Modelling Accuracy" graph half way down the page. Scores of 30-45 for 15 years. Now scores of 87-92. This isn't a minor improvement, it's a leap forward.

That is an impressive improvement, but I think you've missed the most important point: >a score of around 90 GDT is informally considered to be competitive with results obtained from experimental methods So DeepMind is to the point where it's a question of whether their generated model or the experimentally determined structure is closest to the actual physical structure.

I have a related question about this. If experimental methods produce results around a score of 90, what is the baseline we are comparing the DeepMind results against? If the experimental error is equal to the observed DeepMind error, how can we say which one is actually more erroneous?

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

#184

Post by flobosg »

jjk166 wrote: post #33

Now onto the much harder problem of doing the reverse: taking an arbitrary structure and determining an amino-acid sequence that will fold into it.

Deep learning methods are being applied here as well; see for example https://www.biorxiv.org/content/10.1101/2020.07.22.211482v1

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

#185

Post by dekhn »

dontbeevil1992 wrote: post #167
comicjk wrote: post #147

Earlier quoted context omitted.

Scientists can verify that an AlphaFold-predicted structure is correct, or at least useful, without being able to get the structure experimentally. For instance, we could use the AlphaFold-predicted structure to do protein-ligand binding calculations for a bunch of known molecules. If these calculations agree with experimental protein-ligand binding (which they generally do for proteins with known structures), then w…

does that mean that protein-folding is sort of in NP?

The way computer scientists do it, yes, it is. In the CS situation you define an energy function (in this case representing the physical behavior of the protein in water) and find a heuristic to approximate the coordinates of the lowest energy configuration; done, problem solved.

in reality, that's not how it works at all. The energy functions we have are crappy and require too much sampling before we can find the lowest energy configuration. And more importantly, it doesn't look like proteins typically fold to their lowest energy configuration (with the exception of some small fast two state folders), but rather explore a kinetically accessible region around there (or even somewhere else entirely, if the energy cost to transition is too high).

Methods like AF depend heavily on large amount of information correlation from evolutionary data, which has historically been of the highest value for making decisions about protein structure.

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

#186

Post by jhrmnn »

ClumsyPilot wrote: post #134
jhrmnn wrote: post #115

Earlier quoted context omitted.

By this metric, nothing has been ever solved in natural sciences. So this is not a useful metric.

Has it not? Neuton's laws of motion and Ohm's law are pretty om point

No, they are very crude (but useful!) models of reality. General relativity and quantum electrodynamics are much better corresponding models, respectively, and even those are just approximations.

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

#187

Post by mrDmrTmrJ »

dekhn wrote: post #78
asdfasgasdgasdg wrote: post #34

Earlier quoted context omitted.

I don't think anyone on HN is going to have more authority to qualify the results than the independent experts quoted in the linked article. Among whom are numbered a Nobel laureate, the president of the group that designs the tests of protein folding systems, and the former CEO of Genentech+current CEO of Calico.

Art's a smart guy and I have a lot of respect for his biological intuition, but his understanding of computational biology is very limited.

dekhn, in what way is Art's "understanding of computational biology very limited?"

I'd love to hear more. Specifically, what do you think that computational biology can do that you think Art doesn't understand or credit?

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

#188

Post by sanxiyn »

mwcampbell wrote: post #173
cs702 wrote: post #118

Two years ago, after DeepMind submitted its first set of predictions to CASP (Critical Assessment of protein Structure Prediction), Mohammed AlQuraishi, an expert in the field, asked, "What just happened?" https://moalquraishi.wordpress.com/2018/12/09/alphafold-casp... Now that the problem of static protein structure prediction has been solved (prediction errors are below the threshold that is considered acceptable i…

How far does the similarity extend? Specifically, the big question for me is whether AlphaFold will be freely available like ImageNet, or proprietary.

I expect this to be quickly replicated once published. Training data is public and training compute is not enormous and AlphaFold of 2018 did get replicated.

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

#189

Post by dekhn »

asdfasgasdgasdg wrote: post #110
dekhn wrote: post #94

Earlier quoted context omitted.

My main objection to Vivek (the Nobel Prize winner) is the prize in that case should have gone to my advisor, Harry Noller. John Moult... he's a nice guy but I think he's being a bit breathless here.

I see. The co-founder of the organization that tests protein folding is a "nice guy."

CASP is not "the organization that tests protein folding". It's an organization that every two years does a blind prediction and publishes the results (I've competed, some 20 years ago). John's a protein expert, no question about it. I knew him moderately well back in the day because our advisors moved in similar circles.
Post reply on HN