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

341–350 of 683 posts

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

#341

Post by mjn »

dekhn wrote: post #335
mjn wrote: post #308

Earlier quoted context omitted.

Even if you try to account for the overall R&D cost, DeepMind isn't that large an organization by the standards of biomedical research. It's very big and well funded for a computer science research organization, yes, and most CS departments can't match its resources. But the NIH budget is $40 billion, and private pharmaceutical companies do another $80 billion in annual R&D. It's interesting that this kind of breakth…

DeepMind is taking advantage of NIH's funding. For example, Anfinsen who demonstrated that proteins fold spontaneously and reproducibly ( https://en.wikipedia.org/wiki/Anfinsen%27s_dogma ) ran a lab at NIH. Levinthal (who postulated an early and easily refutable model of protein folding) was funded by NIH for decades. Most of the competitors at CASP are supported by NIH and its investments have contributed to the mod…

That's a good point; this system certainly didn't come from nowhere! The protein datasets they used also mostly came out of various NIH-funded projects.

What I meant to focus on was that I think DeepMind has less of a pure money/scale advantage in this area than in some others. In something like Go or Atari game-playing, there are many academic groups researching similar things, but their resources are laughably small compared to what DeepMind threw at it. So you might argue that they got good results there in part because they directed 1000x the personnel and compute at the problem compared to what any academic group could afford. In biomed though, their peers in academia and industry are also pretty well-funded.

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

#342

Post by sdenton4 »

elcritch wrote: post #263
kxs wrote: post #205

Earlier quoted context omitted.

How do you define enormous? "It uses approximately 128 TPUv3 cores (roughly equivalent to ~100-200 GPUs) run over a few weeks". Also last time it took about a year for good replications to pop up.

A couple of hundred GPU's is well within the reach of many even moderately well heeled research institutes. It'd seem that about 3 weeks of compute time with 128 TPU v3's would be about $170,311.68.

Also with keeping in mind that once a good open source model is available, researchers with less resources can still use it to fine tune and get new results for far cheaper than training a new model from scratch.

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

#343

Post by dekhn »

mjn wrote: post #341
dekhn wrote: post #335

Earlier quoted context omitted.

DeepMind is taking advantage of NIH's funding. For example, Anfinsen who demonstrated that proteins fold spontaneously and reproducibly ( https://en.wikipedia.org/wiki/Anfinsen%27s_dogma ) ran a lab at NIH. Levinthal (who postulated an early and easily refutable model of protein folding) was funded by NIH for decades. Most of the competitors at CASP are supported by NIH and its investments have contributed to the mod…

That's a good point; this system certainly didn't come from nowhere! The protein datasets they used also mostly came out of various NIH-funded projects. What I meant to focus on was that I think DeepMind has less of a pure money/scale advantage in this area than in some others. In something like Go or Atari game-playing, there are many academic groups researching similar things, but their resources are laughably smal…

Personally I think a major part of the secret sauce is Google's internal compute infrastructure. When I was an academic, 50% of my time went to building infra to do my science. At Google, petabytes of storage, millions of cores, algorithms, and brains were all easily tappable within a common software repo and cluster infrastructure. That immediately translates to higher scientific productivity.

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

#344

Post by uoaei »

intpx wrote: post #310
colonelcanoe wrote: post #286

Earlier quoted context omitted.

It might be the case that the relevant, practical threshold now tightens. For example, perhaps it is easier to experimentally verify a protein shape predicted by an algorithm than it is to experimentally determine the protein shape?

exactly. Even an incomplete map with somewhat limited resolution makes navigation a hell of a lot easier than flying blind. This effectively is a data reduction solution-- if you have a fuzzy shape of the thing you are trying to model, and you learn the mechanics better with each thing you model, your ability to quickly and accurately reach a goal improves

That's true and also is not what is being challenged by my comment.

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

#345

Post by jey »

timr wrote: post #336
treis wrote: post #143

Earlier quoted context omitted.

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.

"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." While this is an accomplishment, nobody is going to be confusing these models for structures produced experimentally. The CASP metric is for backbone atoms. To have a useful model of protein structure, you really need to have the positions of the…

So it's a really good start, but nobody is going to be throwing these structures into molecular docking simulations for drug discovery or etc just yet. But hopefully those details can be worked out soon enough.

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

#346

Post by xphos »

Like this is awesome and a huge advancement but one thing that worries me with an AI solution is that it doesn't really draw us any closer to the why. Why do proteins fold the way they do? We can predict the resulting structure which is extremely significant, we have no clue why. While we get the insight of being able to predict some structures we don't get the insight of why things are happening the way they are. In some cases like this it might not matter but in other cases that insight might actually be way more significant than answer the problem to begin with. Of course we can review over the problem with the additional predictions that AI gives us but this can be haphazardous because what if there is specific sequence spins in some certain way that we and thus the AI has never seen and it goes missed. I'm not a biologist to say this is possible but I known this kind of edge case can come up and what rabbit holes will we go down because we only have the AI implied insight.

disclaimer I think the contributions are super useful for science but they do come with worries as does every path of discovery

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

#347

Post by robocat »

colonelcanoe wrote: post #286
astroalex wrote: post #272

Earlier quoted context omitted.

The distinction you're making between "solved" and "closely approximated" makes logical sense to me. However, if I'm interpreting the AlphaFold results correctly, this distinction isn't practically significant, right? If you can approximate an algorithm with error that is "below the threshold that is considered acceptable in experimental measurements" (to quote another HN comment), then you have something as good as…

It might be the case that the relevant, practical threshold now tightens. For example, perhaps it is easier to experimentally verify a protein shape predicted by an algorithm than it is to experimentally determine the protein shape?

From: https://www.sciencemag.org/news/2020/11/game-has-changed-ai-...

“The organizers even worried DeepMind may have been cheating somehow. So Lupas set a special challenge: a membrane protein from a species of archaea, an ancient group of microbes. For 10 years, his research team tried every trick in the book to get an x-ray crystal structure of the protein. ‘We couldn’t solve it.’”

“But AlphaFold had no trouble. It returned a detailed image of a three-part protein with two long helical arms in the middle. The model enabled Lupas and his colleagues to make sense of their x-ray data; within half an hour, they had fit their experimental results to AlphaFold’s predicted structure. ‘It is almost perfect,’ Lupas says.”

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

#349

Post by whimsicalism »

klmr wrote: post #337
whimsicalism wrote: post #299

Earlier quoted context omitted.

What do you mean? Genetics is amenable because the genome is a sequence that can be language modeled/auto-regressed for depth of understanding by the network. There are plenty of inferences that you would want to do on genetic sequences that we can't model exactly and there is some past work on doing stuff like this, although biology is usually a few years behind. https://www.nature.com/articles/s41592-018-0138-4 e:…

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 you would think that is the case, but if you've been following deep sequence research recently then you would know there are actually immense benefits to doing so because the embeddings learned can then be portably used on downstream tasks.

> it’s purely limited by data availability.

Yes, and transfer learning on models pre-trained on unsupervised sequence tasks provides a (so-far under-explored) path around labeled data availability problems.

I already linked to a paper showing a task that these sorts of approaches outperform, and that is without using the most recent techniques in sequence modeling.

Maybe read the paper in Nature that uses this exact LM technique to predict the effect of mutations before assuming that it doesn't work: https://sci-hub.do/10.1038/s41592-018-0138-4

I am not directly in the field, you are right - but I think you are also being overconfident if you think that these approaches are exactly the same as the HMM/markov chain approaches that came before.

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

#350

Post by whimsicalism »

garmaine wrote: post #334
whimsicalism wrote: post #299

Earlier quoted context omitted.

What do you mean? Genetics is amenable because the genome is a sequence that can be language modeled/auto-regressed for depth of understanding by the network. There are plenty of inferences that you would want to do on genetic sequences that we can't model exactly and there is some past work on doing stuff like this, although biology is usually a few years behind. https://www.nature.com/articles/s41592-018-0138-4 e:…

This is word salad.

Rude. I would appreciate substantive criticism, especially when I'm linking papers in Nature starting to do exactly what I'm talking about.
Post reply on HN