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

461–470 of 683 posts

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

#461

Post by Rochus »

Rochus wrote: post #29

Great. So then farewell CARA ( http://cara.nmr.ch/doku.php ), we had a good time.

After I had some time to think about it, I come to a different conclusion. Contrary to my first assumption, Bio NMR (in contrast to crystallography) will become more and more important, since the method allows to study the dynamic properties of proteins. With the structure predicted by DNNs, the chemical shifts to be expected in the NMR spectra can be calculated; the assignment problem is thus largely eliminated. Bio NMR can then be used specifically to study the "parts that move".

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

#464

Post by dang »

All: there are multiple pages of comments; if you're curious to read them, click More at the bottom of the page, or like this:

https://news.ycombinator.com/item?id=25253488&p=2

We changed the URL from https://predictioncenter.org/casp14/zscores_final.cgi to the blog post, which has more background info.

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

#465

Post by uoaei »

deeviant wrote: post #399
uoaei wrote: post #325

Earlier quoted context omitted.

"Pedantry" implies that the distinction is not meaningful. This is true if you're only paying attention to how this system can be utilized to answer questions posed to it. This achievement by itself, however, does not do much to push the science of protein folding much further. Those advances will come when people poke, prod, and break the model to develop a unified theory for protein folding.

The "science" of protein folding has a primary goal: to predict the structure of a protein given it's constituent parts. This is what alphaFold does, and it's been verified to produce results at an apparent accuracy at or above something like X-ray protein crystallography. The advances will come, after these results are validated and accepted by the scientific community as whole, simply when groups start using this t…

This model will be an amazing tool toward a science of protein folding, but we have not "solved" protein folding as long as that remains elusive.

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

#466

Post by dekhn »

gfodor wrote: post #430
dekhn wrote: post #54

Earlier quoted context omitted.

100% accuracy is "solved".

You can't get 100% accuracy on something for which you don't or can't know the ground truth.

The protein folding problem is predicated on the idea that there is a ground truth (a single static set of atomic coordinates with positional variances). If your point is that even experimental methods can't truly reach 100% (due either to underlying motion in the protein, or can't determine the structure), that's more or less what Moult is saying (they more or less arbitrarily define ~1A resoution and GDT of 90 as the "threshold at which the problem is solved").

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

#467

Post by klmr »

whimsicalism wrote: post #349
klmr wrote: post #337

Earlier quoted context omitted.

I meant, which specifics are you thinking of? > Genetics is amenable because it is a sequence Not sure what you mean by that. Genetics is a field of research. The genome is a sequence. And yes, that sequence can be modelled for various purposes but without a specific purpose there’s no point in doing so (and furthermore doing so without specific purpose is trivial — e.g. via markov chains or even simpler stochastic p…

> Not sure what you mean by that I spoke loosely, my mind skipped ahead of my writing, and I didn't realize that we were parsing so closely. "Genetics (the field) is amenable because the object of its study (the genome) is a sequence" would have been more correct but I thought it was implied. > without a specific purpose there’s no point in doing so Well yes, prior to the success of transfer learning I could see why…

Thanks for the paper, I’ll check it out; this isn’t my speciality so I’m definitely learning something. Just one minor clarification:

> Maybe read the paper … before assuming that it doesn't work

I don’t assume that. In fact, I know that using ML works on many problems in genetics. What I’m less convinced by is that we can expect a breakthrough due to ML any time soon, partly because conventional techniques (including ML) already have a handle on some current problems in genetics, and because there isn’t really a specific (or flashy) hard, algorithmic problem like there is in structural biology. Rather, there’s lots of stuff where I expect to see steady incremental improvement. In fact, in Wikipedia’s list of unsolved biological problems [1] there isn’t a single one that I’d characterise specifically as a question from the field of genetics (as a geneticist, that’s slightly depressing).

But my question was even more innocent than that: I’m not even that sceptical, I’m just not aware of anything and genuinely wanted an answer. And the paper you’ve posted might provide just that, so go and do my research now.

[1] https://en.wikipedia.org/wiki/List_of_unsolved_problems_in_b...

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

#468

Post by ashtonbaker »

The_rationalist wrote: post #435
ashtonbaker wrote: post #91

Earlier quoted context omitted.

> To me Are you a domain expert? Because: > According to Professor Moult, a score of around 90 GDT is informally considered to be competitive with results obtained from experimental methods.

but experimental methods have not solved protein folding either. AlphaFold has'nt solved protein folding but I can't wait to see their progress for ALphaFold 3. What would be informatively useful would be to know how much accuracy is needed on average for drug engineers, I'd say that 99% is more likely to be the minimum to make solid inferences

> but experimental methods have not solved protein folding either.

I might be missing something here, but isn't "experimental methods" just shorthand for "our best knowledge of a protein's structure, obtained via NMR or X-ray crystallography"? In that case, I'm not sure what "solving" protein folding even means - literally zero mean error? We can't know/solve anything beyond our best knowledge, that's tautological.

> What would be informatively useful would be to know how much accuracy is needed on average for drug engineers.

Yeah that would be interesting, but:

> I'd say that 99% is more likely to be the minimum to make solid inferences

...what are you basing this on?

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

#469

Post by sgillen »

maxlamb wrote: post #442
dluan wrote: post #425

I worked in the lab that helped develop folding@home, as well as the game where the crowd was the chaotically trained machine that folded and unfolded one amino acid at a time. This feels like a pretty significant new chapter in the humanity movie. A few times, I get immense pangs of jealousy for younger people a generation or a half before me. And I'm only 30! This is one of those times.

Is the team really that young? 20 year olds?

I think he means that those who are in their teens / even younger now will get to experience immensely cool tech in their lifetime.

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

#470

Post by kovek »

dang wrote: post #464

All: there are multiple pages of comments; if you're curious to read them, click More at the bottom of the page, or like this: https://news.ycombinator.com/item?id=25253488&p=2 We changed the URL from https://predictioncenter.org/casp14/zscores_final.cgi to the blog post, which has more background info.

I've seen you mention this [More] comment a few times now. I like it, though what if you change the design of the More functionality?
Post reply on HN