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

AlphaFold 3 predicts the structure and interactions of life's molecules

blog.google

Post reply on HN
Print view View original

131–140 of 504 posts

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#131

Post by goggy_googy »

moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

I think at some point, we will be able to produce models that are able to pass data into a target model and observe its activations and outputs and put together some interpretable pattern or loose set of rules that govern the input-output relationship in the target model. Using this on a model like AlphaFold might enable us to translate inferred chemical laws into natural language.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#132

Post by pen2l »

moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

The most moneyed and well-coordinated organizations have honed a large hammer, and they are going to use it for everything, and so almost certainly future big findings in the areas you mention, probabilistically inclined models coming from ML will be the new gold standard.

But yet the only thing that can save us from ML will be ML itself because it is ML that has the best chance to be able to extrapolate patterns from these blackbox models to develop human interpretable models. I hope we do dedicate explicit effort to this endeavor, and so continue the human advances and expanse of human knowledge in tandem with human ingenuity with computers at our assistance.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#133

Post by moralestapia »

dekhn wrote: post #121
moralestapia wrote: post #85

Earlier quoted context omitted.

How easy/hard would be for the scientific community to come up with an "OpenFold" model which is pretty much AF3 but fully open source and without restrictions in it? I can image training will be expensive, but I don't think it will be at a GPT-4 level of expensive.

already did it, https://openfold.io/ https://github.com/aqlaboratory/openfold https://www.biorxiv.org/content/10.1101/2022.11.20.517210v1 https://lupoglaz.github.io/OpenFold2/ https://www.biospace.com/article/releases/openfold-biotech-a... I really have to emphasize that transformers have literally transformed science in only a few years. Truly extraordinary.

Oh, nice! Thanks for sharing.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#134

Post by natechols »

dekhn wrote: post #83
nybsjytm wrote: post #76

Earlier quoted context omitted.

>The alphafold work has been used across the industry (successfully, in the sense of blind prediction), and has been replicated independently. This is clearly an overstatement, or at least very incomplete. See for instance https://www.nature.com/articles/s41592-023-02087-4 : "In many cases, AlphaFold predictions matched experimental maps remarkably closely. In other cases, even very high-confidence predictions differ…

Yep, I know Paul Adams (used to work with him at Berkeley Lab) and that's exactly the paper he'd publish. If you read that paper carefully (as we all have, since it's the strongest we've seen from the crystallography community so far) they're basically saying the results from AF are absolutely excellent, and fit for purpose. (put another way: if Paul publishes a paper saying your structure predictions have issues, an…

I also worked with the same people (and share most of the same biases) and that paper is about as close to a ringing endorsement of AlphaFold as you'll get.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#135

Post by j7ake »

boxed wrote: post #91
j7ake wrote: post #80

So it’s okay now to publish a computational paper with no code? I guess Nature’s reporting standards don’t apply to everyone. > A condition of publication in a Nature Portfolio journal is that authors are required to make materials, data, code, and associated protocols promptly available to readers without undue qualifications. > Authors must make available upon request, to editors and reviewers, any previously unrep…

Are you an editor or reviewer?

If you read the standards it applies broadly beyond reviewers or editors.

> A condition of publication in a Nature Portfolio journal is that authors are required to make materials, data, code, and associated protocols promptly available to readers without undue qualifications.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#136

Post by lupire »

tnias23 wrote: post #126
moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

I wonder if ML can someday be employed in deciphering such black box problems; a second model that can look under the hood at all the number crunching performed by the predictive model, identify the pattern that resulted in a prediction, and present it in a way we can understand. That said, I don’t even know if ML is good at finding patterns in data.

> That said, I don’t even know if ML is good at finding patterns in data.

That's the only thing ML does.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#137

Post by Kalium »

HanClinto wrote: post #101
boxed wrote: post #91

Earlier quoted context omitted.

Are you an editor or reviewer?

Good question. Also makes me wonder -- where's the line? Is it reasonable to have "layperson" reviewers? Is it reasonable to think that regular citizens could review such content?

I think you will find that for the vast, vast majority of scientific papers there is significant negative expected value to even attempting to have layperson reviewers. Bear in mind that we're talking about papers written by experts in a specific field aimed at highly technical communication with other people who are experts in the same field. As a result, the only people who can usefully review the materials are drawn from those who are also experts in the same field.

For an instructive example, look up the seminal paper on the structure of DNA: https://www.mskcc.org/teaser/1953-nature-papers-watson-crick... Ask yourself how useful comments from someone who did not know what an X-ray is, never mind anything about organic chemistry, would be in improving the quality of research or quality of communication between experts in both fields.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#138

Post by thegrim33 »

moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

Reminds me of the novel Blindsight - in it there's special individuals who work as synthesists, whos job it is to observe and understand and then somehow translate back to "lay person" the seemingly undecipherable actions/decisions of advanced computers and augmented humans.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#139

Post by optimalsolver »

pen2l wrote: post #132
moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

The most moneyed and well-coordinated organizations have honed a large hammer, and they are going to use it for everything, and so almost certainly future big findings in the areas you mention, probabilistically inclined models coming from ML will be the new gold standard. But yet the only thing that can save us from ML will be ML itself because it is ML that has the best chance to be able to extrapolate patterns fro…

Spoiler: "Interpretable ML" will optimize for output that either looks plausible to humans, reinforces our preconceptions, or appeals to our aesthetic instincts. It will not converge with reality.

Re: AlphaFold 3 predicts the structure and interactions of life's molecules

#140

Post by narrator »

dekhn wrote: post #93
moconnor wrote: post #32

Stepping back, the high-order bit here is an ML method is beating physically-based methods for accurately predicting the world. What happens when the best methods for computational fluid dynamics, molecular dynamics, nuclear physics are all uninterpretable ML models? Does this decouple progress from our current understanding of the scientific process - moving to better and better models of the world without human-int…

If you're a scientist who works in protein folding (or one of those other areas) and strongly believe that science's goal is to produce falsifiable hypotheses, these new approaches will be extremely depressing, especially if you aren't proficient enough with ML to reproduce this work in your own hands. If you're a scientist who accepts that probabilist models beat interpretable ones (articulated well here: https://no…

What if our understanding of the laws of the natural sciences are subtly flawed and AI just corrects perfectly for our flawed understanding without telling us what the error in our theory was?

Forget trying to understand dark matter. Just use this model to correct for how the universe works. What is actually wrong with our current model and if dark matter exists or not or something else is causing things doesn't matter. "Shut up and calculate" becomes "Shut up and do inference."

Post reply on HN