AlphaFold: a solution to a 50-year-old grand challenge in biology • Hacker News Board

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

#451

Post by 6gvONxR4sf7o » Mon, Nov 30, 2020, 9:17 PM UTC

vadansky wrote: post #351

vadansky wrote: post #128

Just to add to this whole "It's not solved! Yes it is!" discussion. Note that >According to Professor Moult, a score of around 90 GDT is informally considered to be competitive with results obtained from experimental methods. So if we go by >= 90 as solved: >In the results from the 14th CASP assessment, released today, our latest AlphaFold system achieves a median score of 92.4 GDT overall across all targets. they so…

Just to add to my own comment. Why does HN like being so pedantic about the definitions of words? This is an interesting post regarding AI and cellular biochemistry. Do we really need to add a philosophical debate about the meaning of "solution"? Personally I think anyone who can't add to the discussion about AI and protein folding should just not comment, instead of settled on adding to the what does solution mean "…

HN pushes back on hype and because there's generally too much hype in announcements.

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

#452

Post by generalizations » Mon, Nov 30, 2020, 9:19 PM UTC

e_y_ wrote: post #440

elcritch wrote: post #270

Earlier quoted context omitted.

It also makes one reconsider the notion that monopolies are entirely bad. This essentially appears to be a vanity project for Google. Though of course they'll benefit from it in many ways, but it's not like they're doing this as the core product of their service. It's a pretty awesome achievement.

I think there's some merit to the idea that huge corporate monopolies have the resources to accomplish undertakings that smaller companies cannot. But it's often a what-if, because we don't know what the alternative might have been. Big companies can suck up all the air in the room by monopolizing talent and making it harder for startups to pay the kinds of salaries needed for top tier AI research. Xerox PARC came up…

Note that Bell Labs is another example of the corporate monopoly research lab producing things that others couldn't / didn't.

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

#453

Post by flobosg » Mon, Nov 30, 2020, 9:20 PM UTC

heycosmo wrote: post #446

flobosg wrote: post #428

Earlier quoted context omitted.

> do MSA-based approaches also help understand "first-principles" folding physics any better? Not really. MSA-based approaches, as most structure prediction methods, have as a goal to find the lowest energy conformation of the protein chain, disregarding folding kinetics and basically all dynamic aspects of protein structure. > If I write a random genetic sequence (think drug discovery) that has many aligned sequence…

> I don't think I fully understood this, but I'll give it a shot anyway. If your artificial sequence aligns with others, there's a chance that it will fold like them, depending on the quality and accuracy of the multiple sequence alignment. Since multiple sequence alignments are built under the assumption of homology (all sequences have a common ancestor), it's a matter of how far from the "sequence sampling space" y…

Oh, I see! Yes, an intrachain alignment of an artificial sequence does not by itself give any information about co-evolution, especially since you don't know whether your protein is actually folding. To assess co-evolution you need a multiple sequence alignment between protein homologs containing correlated mutations.

> I understand that similar sequences may fold similarly (although as length increases, I highly doubt it, but IDK).

As long as the sequence similarity is kept between those sequences, length is not an issue.

> Co-evolution suggests that aligned sub-sequences are also proximal

What do you mean by "proximal"? Close in space, or similar in structure?

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

#454

Post by jfarlow » Mon, Nov 30, 2020, 9:21 PM UTC

0xBA5ED wrote: post #190

Does this give the ability to engineer cures for currently incurable diseases?

In short - certain ones, yes. This should be one step (that was a bottleneck) in helping a company with a fixed budget do an order or magnitude more 'experiments' with the same amount of resources. Lab resources are expensive and fixed, so if you can pre-compute what you need, you can get right to the more powerful results.

We design proteins for immunotherapies - this kind of thing would help us more rapidly design our proteins (and more efficiently use our wet-lab resources to speed existing projects). For others, some drugs are hard build without knowing how they will interact - this could both provide new 'targets' to go after, but also might help prevent projects that would otherwise accidentally target an important protein.

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

#455

Post by jeffxtreme » Mon, Nov 30, 2020, 9:22 PM UTC

deeviant wrote: post #444

jeffxtreme wrote: post #423

GDT_TS for AlphaFold is now comparable is at experimental levels; but that's based on the class of proteins for which we've been able to determine the 3D structure of the protein, for which there might be selection bias. I wonder if we can determine if this extends to proteins that aren't as keen to determining their 3D structure? For example, certain proteins are more crystallizable than others.. For these non-cryst…

> I wonder if we can determine if this extends to proteins that aren't as keen to determining their 3D structure? This is already happened. "An AlphaFold prediction helped to determine the structure of a bacterial protein that Lupas’s lab has been trying to crack for years. Lupas’s team had previously collected raw X-ray diffraction data, but transforming these Rorschach-like patterns into a structure requires some i…

Agree this is great to hear, but the fact that they had X-ray diffraction data indicates this protein was indeed crystallizable no?

Though the next paragraph in the article shows that DeepMind is indeed working on mapping out reliability:

"Demis Hassabis, DeepMind’s co-founder and chief executive, says that the company plans to make AlphaFold useful so other scientists can employ it. (It previously published enough details about the first version of AlphaFold for other scientists to replicate the approach.) It can take AlphaFold days to come up with a predicted structure, which includes estimates on the reliability of different regions of the protein. “We’re just starting to understand what biologists would want,” adds Hassabis, who sees drug discovery and protein design as potential applications."

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

#456

Post by naringas » Mon, Nov 30, 2020, 9:23 PM UTC

deeviant wrote: post #450

xphos wrote: post #346

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…

> 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. This isn't something specific to AI, but science itself. We know the value of C, but now why the value is C, sure we can point to something like the Lorentz transformation, but we can't and probably won't even be able to explain why it has these particular constants, we just know…

> Science isn't in the business of answering why.

I agree as long as science is a business. But why is science a business?

If science is not meant to answer why, does this mean we cannot know why?

should we just give up on having story-like (narrative) explanations for why and how things work? it seems like we are headed to a world where the computer just tells us what to do and where to go. a world in which we are free from having to think about why we are being told to do whatever it is we're doing. click (or tap) buttons, get tokens to buy food and pay rent.

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

#457

Post by dekhn » Mon, Nov 30, 2020, 9:24 PM UTC

MaxBarraclough wrote: post #409

dekhn wrote: post #343

Earlier quoted context omitted.

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.

Has cloud computing changed this?

Mostly? I left google to work at a biotech startup working in a related area and found that the big three cloud providers have built systems that greatly improve computational science. That said, it's still a lot of work to get productive, many in the field are really resistant to changes like version control, continuous integration, testing, and architecting distributed systems for handling complex lab production environments.

Here's an exemplar of how I think it evolved well in a cloud world: https://gnomad.broadinstitute.org/

that project adopts many concepts from google and others and greatly improved our analytic capabilities for large-scale genomics.

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

#458

Post by dekhn » Mon, Nov 30, 2020, 9:26 PM UTC

t_serpico wrote: post #437

dekhn wrote: post #52

Earlier quoted context omitted.

I ran Folding@Home at Google on hundreds of thousands of fast Xeon cores for over a year. I concluded at the end that unbiased MD simulations are not an effective use of computer time.

Out of curiosity, why not?

for the dollars invested, the amount of basic and applied results out weren't worth it.

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

#459

Post by timr » Mon, Nov 30, 2020, 9:29 PM UTC

ramraj07 wrote: post #438

timr wrote: post #405

Earlier quoted context omitted.

"It looks like DeepMind invented a completely new method for this round that's not just an extension of their previous work, showing how much you can gain if you don't shoebox yourself into just trying to improve existing methods. That all the scientists were highly skeptical about the scope of ML (and these are computer scientists to begin with mind you) just shows how little they knew of what they did know of what…

We don't know too much about the exact model they made but it looks sufficiently generalizable to be able to give a candidate protein structure for any given sequence. It doesn't automatically cure cancer and inject the drug but that by itself is an amazing tool that if available to everyone will revolutionize biology experimentation. I will definitely blame the protein structure field in multiple levels though. It w…

"We don't know too much about the exact model they made but it looks sufficiently generalizable to be able to give a candidate protein structure for any given sequence. It doesn't automatically cure cancer and inject the drug but that by itself is an amazing tool that if available to everyone will revolutionize biology experimentation."

They say on their own press-release page that side-chains are a future research problem, and nothing about their method description makes me believe they've innovated on all-atom modeling. This software seems able to generate good models of protein backbones; these kinds of models certainly have uses, but a backbone model is not enough for drug design.

This is certainly an advancement, but you're exaggerating the scope of the accomplishment.

" I only feel pity for the graduate students still trying to crystallize proteins in this day and age."

Nothing about this changes the fact that protein crystallography is a gold-standard method for determining a protein structure. CryoEM has made it possible to obtain good structures for classes of proteins we could never achieve before, and it's certainly interesting if we can run a computer for a few days to get a 1Å ab initio model for a protein sequence, but we could already do that for a large class of proteins with homology modeling. These predicted structures still aren't generally that useful for drug design, where tiny details of molecular interactions matter.

To put it in perspective: protein energetics are measured on the scale of tens of kcal / mol. Protein-drug interactions are measured in fractions of a kcal. A single hydrogen bond or cation-pi interaction or displaced water molecule can make the difference between a drug candidate and an abandoned lead. Tiny changes in backbone position make the difference between a good structure and a bad one. Alphafold isn't doing that kind of modeling.

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

#460

Post by flobosg » Mon, Nov 30, 2020, 9:29 PM UTC

jeffxtreme wrote: post #455

deeviant wrote: post #444

Earlier quoted context omitted.

> I wonder if we can determine if this extends to proteins that aren't as keen to determining their 3D structure? This is already happened. "An AlphaFold prediction helped to determine the structure of a bacterial protein that Lupas’s lab has been trying to crack for years. Lupas’s team had previously collected raw X-ray diffraction data, but transforming these Rorschach-like patterns into a structure requires some i…

Agree this is great to hear, but the fact that they had X-ray diffraction data indicates this protein was indeed crystallizable no? Though the next paragraph in the article shows that DeepMind is indeed working on mapping out reliability: "Demis Hassabis, DeepMind’s co-founder and chief executive, says that the company plans to make AlphaFold useful so other scientists can employ it. (It previously published enough d…

> Agree this is great to hear, but the fact that they had X-ray diffraction data indicates this protein was indeed crystallizable no?

Yes. CASP uses as targets proteins with no known published structure but a solved or soon-to-be-solved one. They are then kept on hold until the end of the competition.