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

Chemistry Nobel: Computational protein design and protein structure prediction

nobelprize.org

Post reply on HN
Print view View original

291–300 of 343 posts

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#291

Post by j7ake »

flobosg wrote: post #222
nextos wrote: post #221

Earlier quoted context omitted.

AlphaFold is excellent engineering, but I struggle calling this a breakthrough in science. Take T cell receptor (TCR) proteins, which are produced pseudo-randomly by somatic recombination, yielding an enormous diversity. AlphaFold's predictions for those are not useful. A breakthrough in folding would have produced rules that are universal. What was produced instead is a really good regressor in the space of proteins…

> A breakthrough in folding would have produced folding rules that are universal. Protein folding ≠ protein structure prediction > I think those who invented pairwise and multiple alignment dynamic programming algorithms deserved some recognition I would add BLAST as well but that ship has sailed, I’m afraid.

If blast used a neural network it may have had a chance!

The question is: has blast made more of an impact than alpha fold? I think so at the moment.

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#292

Post by trott »

jhbadger wrote: post #152
trott wrote: post #82

Earlier quoted context omitted.

> There are few approaches that will accelerate the field of drug development and chemistry as a whole in a way that the works of these three people will. As the author of one such approach, I'm skeptical. AlphaFold 2 just predicts protein structures. The thing about proteins is that they are often related to each other. If you are trying to predict the structure of a naturally occurring protein, chances are that the…

Protein structures are similar to each other because of evolution (protein families exist because of shared ancestry of protein coding genes). It's not a weird coincidence that helps ML; it's inherent in the problem. Same with drug design -- very, very, few drugs are "novel" as opposed to being analogues of something naturally in the body.

> It's not a weird coincidence that helps ML; it's inherent in the problem.

This depends on the application. If you are trying to design new proteins for something, unconstrained by evolution, you may want a method that does well on novel inputs.

> Same with drug design

Not by a long shot. There are maybe on the order of 10,000 known 3D protein-ligand structures. Meanwhile, when doing drug discovery, people scan drug libraries with millions to billions of molecules (using my software, oftentimes). These molecules will be very poorly represented in the training data.

The theoretical chemical space of interest to drug discovery is bigger still, with on the order of 1e60 molecules in it: https://en.wikipedia.org/wiki/Chemical_space

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#293

Post by ggm »

As a computer scientist who is oppositional to AGI boom-bubble mania, it was easy to decry the Nobel in physics. But, contextually given who Murray Gell-Mann was and what field he was in (astrophysics) I feel a very strong Gell-Mann Effect here because I am happy to accept THIS use of computational systems to advance (bio)chemistry is worthy, and I find myself wondering why I am so uncritical about it?

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#294

Post by nextos »

dekhn wrote: post #290
flobosg wrote: post #222

Earlier quoted context omitted.

> A breakthrough in folding would have produced folding rules that are universal. Protein folding ≠ protein structure prediction > I think those who invented pairwise and multiple alignment dynamic programming algorithms deserved some recognition I would add BLAST as well but that ship has sailed, I’m afraid.

The value in BLAST wasn't in its (very fast) alignment implementation but in the scoring function, which produced calibrated E-values that could be used directly to decide whether matches were significant or not. As a postdoc I did an extremely careful comparison of E-values to true, known similarities, and the E-values were spot on. Apparently, NIH ran a ton of evolution simulations to calibrate those parameters. Fo…

BLAST estimates are derived from extreme value theory and large deviations, which is a very elegant area of probability and statistics.

That's the key part, I think, being able to estimate how unique each alignment is without having to simulate the null distribution, as it was done before with FASTA.

The index also helps, but the speedup comes mostly from the other part.

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#295

Post by a_bonobo »

jltsiren wrote: post #269
roughly wrote: post #240

Earlier quoted context omitted.

It also proved that deep learning models are a valid approach to bioinformatics - for all its flaws and shortcomings, AlphaFold solves arbitrary protein structure in minutes on commodity hardware, whereas previous approaches were, well, this: https://en.wikipedia.org/wiki/Folding@home A gap between biological research and biological engineering is that, for bioengineering, the size of the potential solution space and…

> It also proved that deep learning models are a valid approach to bioinformatics A lot of bioinformatics tools using deep learning appeared around 2017-2018. But rather than being big breakthroughs like AlphaFold, most of them were just incremental improvements to various technical tasks in the middle of a pipeline.

and since a lot of those tools are incremental improvements they disappeared again, imho - what's the point for 2% higher accuracy when you need a GPU you don't have?

Not many DL based tools I see these days regularly applied in genomics. Maybe: Tiara for 'high level' taxonomic classification, DeepVariant in some papers for SNP calling, that's about it? Some interesting gene prediction tools coming up like Tiberius. AlphaFold, of course.

Lots of papers but not much day-to-day usage from my POV.

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#296

Post by puzzledobserver »

I see a number of comments here about giving awards to organizations rather than individuals, and counter-comments pointing out that Nobel's will disallowed it.

How is the Nobel Prize actually administered? For how long is the Nobel committee bound to follow Alfred Nobel's will? And aren't there laws against perpetual trusts? Or is the rule against awarding the technical awards to organizations one that the committee maintains out of deference to Nobel's original intentions?

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#297

Post by YeGoblynQueenne »

pelorat wrote: post #172
YeGoblynQueenne wrote: post #139

Looks like science is out, black box prediction is in. It's like the era of epicycles all over again. Oh well. Fellow realists, see you all 1500 years from now!

There are things so complex in science that a human mind can never understand them, but a large neural network can.

Conjecture, that. Even if true I think it will be very hard to find any definition of science along the lines of "training deep neural nets to do the understanding in our stead".

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#298

Post by lysozyme »

For those like myself who design proteins for a living, the open secret is that well before AlphaFold, it was pretty much possible to get a good-enough structure of any particular protein you really cared about (from say 2005) by other means, namely Baker’s Rosetta.

I constantly use AlphaFold structures today [1]. And AlphaFold is fantastic. But it only replaces one small step in solving any real-world problem involving proteins such as designing a safe, therapeutic protein binder to interrupt cancer-associated protein-protein interactions or designing an enzyme to degrade PFAS.

I think the primary achievement is that it gets protein structures in front of a lot more smart eyes, and for a lot more proteins. For “everyone else” who never needed to master computational protein structure prediction workflows before, they now have easy access to the rich, function-determinative structural information they need to understand and solve their problem.

The real tough problem in protein design is how to use these structure predictions to understand and ultimately create proteins we care about.

1. https://alexcarlin.bearblog.dev/multistate-protein-design-wi...

Re: Chemistry Nobel: Computational protein design and protein structure prediction

#300

Post by refurb »

paulwetzel wrote: post #4

While I am skeptical about yesterdays award in physics, these are totally deserved and spot on. There are few approaches that will accelerate the field of drug development and chemistry as a whole in a way that the works of these three people will. Congratulations!

As someone in the drug discovery business I’m skeptical as I’ve seen many such “advances” flop.

I remember when computer aided drug design first came out (and several “quantum jumps” along the way). While useful they failed often at the most important cases.

New drugs tend to be developed in spaces we know very little about. Thus there is nothing useful for AI to be trained on.

Nothing quite like hearing from the computational scientist “if you make this one change it will improve binding by 1000x”. Then spending 3 weeks making it to find out it actually binds worse.

Post reply on HN