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

51–60 of 504 posts

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

#51

Post by jncfhnb »

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…

These processes are both beyond human comprehension because they contain vast layers of tiny interactions and also not practical to simulate. This tech will allow for exploration for accurate simulations to better understand new ideas if needed.

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

#52

Post by tomrod »

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…

A few things:

1. Research can then focus on where things go wrong

2. ML models, despite being "black boxes," can still have brute-force assessment performed of the parameter space over covered and uncovered areas by input information

3. We tend to assume parsimony (i.e Occam's razor) to give preference to simpler models when all else is equal. More complex black-box models exceeding in prediction let us know the actual causal pathway may be more complex than simple models allow. This is okay too. We'll get it figured out. Not everything is closed-form, especially considering quantum effects may cause statistical/expected outcomes instead of deterministic outcomes.

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

#53

Post by dekhn »

fabian2k wrote: post #35
dekhn wrote: post #23

Earlier quoted context omitted.

AlphaFold very explicitly (unless something has changed) removes NMR structures as references because they are not accurate enough. I have a PhD in NMR biomolecular structure and I wouldn't trust. the structures for anything.

Looking at the supplementary material (section 2.5.4) for the AlphaFold 3 paper it reads to me like they still use NMR structures for training, but not for evaluating performance of the model.

I think it's implicit in their description of filtering the training set, where they say they only include structures with resolution of 9A or less. NMR structures don't really have a resolution, that's more specific to crystallography. However, I can't actually verify that no NMR structures were included without directly inspecting their list of selected structures.

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

#54

Post by gameman144 »

Jerrrry wrote: post #12
Metacelsus wrote: post #4

From: https://www.nature.com/articles/d41586-024-01383-z >Unlike RoseTTAFold and AlphaFold2, scientists will not be able to run their own version of AlphaFold3, nor will the code underlying AlphaFold3 or other information obtained after training the model be made public. Instead, researchers will have access to an ‘AlphaFold3 server’, on which they can input their protein sequence of choice, alongside a selection of…

The second amendment prevents the government's overreaching perversion to restrict me from having the ability to print biological weapons from the comfort of my couch. Google has no such restriction.

I know this is tongue in cheek, but you absolutely can be restricted from having a biological weapons factory in your basement (similar to not being able to pick "nuclear bombs" as your arms to bear).

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

#55

Post by photochemsyn »

Metacelsus wrote: post #4

From: https://www.nature.com/articles/d41586-024-01383-z >Unlike RoseTTAFold and AlphaFold2, scientists will not be able to run their own version of AlphaFold3, nor will the code underlying AlphaFold3 or other information obtained after training the model be made public. Instead, researchers will have access to an ‘AlphaFold3 server’, on which they can input their protein sequence of choice, alongside a selection of…

Well, it's because you can design deadly viruses using this technology. Viruses gain entry to living cells via cell-surface receptor proteins whose normal job is to bind signalling molecules, alter their conformation and translate that external signal into the cellular interior where it triggers various responses from genomic transcription to release of other signal molecules. Viruses hijack such mechanisms to gain entry to cells.

Thus if you can design a viral coat protein to bind to a human cell-surface receptor, such that it gets translocated into the cell, then it doesn't matter so much where that virus came from. The cell's firewall against viruses is the cell membrane, and once inside, the biomolecular replication machinery is very similar from species to species, particularly within restricted domains, such as all mammals.

Thus viruses from rats, mice, bats... aren't going to have major problems replicating in their new host - a host they only gained access to because some nation-state actors working in collaboration on such gain-of-function research in at least two labs on opposite sides of the world with funds and material provided by the two largest economic powers for reasons that are still rather opaque, though suspiciously banal...

Now while you don't need something like AlphaFold3 to do recklessly stupid things (you could use directed evolution, making millions of mutatad proteins, throwing them at a wall of human cell receptors and collecting what stuck), it makes it far easier. Thus Google doesn't want to be seen as enabling, though given their prediliction for classified military-industrial contracting to a variety of nation-states, particularly with AI, with revenue now far more important than silly "don't be evil" statements, they might bear watching.

On the positive side, AlphaFold3 will be great for fields like small molecular biocatalysis, i.e. industrial applications in which protein enzymes (or more robust heterogenous catalysts designed based on protein structures) convert N2 to ammonia, methane to methanol, or selectively bind CO2 for carbon capture, modification of simple sugars and amino acids, etc.

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

#56

Post by fabian2k »

dekhn wrote: post #53
fabian2k wrote: post #35

Earlier quoted context omitted.

Looking at the supplementary material (section 2.5.4) for the AlphaFold 3 paper it reads to me like they still use NMR structures for training, but not for evaluating performance of the model.

I think it's implicit in their description of filtering the training set, where they say they only include structures with resolution of 9A or less. NMR structures don't really have a resolution, that's more specific to crystallography. However, I can't actually verify that no NMR structures were included without directly inspecting their list of selected structures.

I think it is very plausible that they don't use NMR structures here, but I was looking for a specific statement on it in the paper. I think your guess is plausible, but I don't think the paper is clear enough here to be sure about this interpretation.

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

#57

Post by kylebenzle »

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…

That is not a real concern, just a confusion on how statistics works :(

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

#58

Post by timschmidt »

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…

There will be an iterative process built around curated training datasets - continually improved, top tier models, teams reverse engineering the model's understanding and reasoning, and applying that to improve datasets and training.

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

#59

Post by dekhn »

fabian2k wrote: post #56
dekhn wrote: post #53

Earlier quoted context omitted.

I think it's implicit in their description of filtering the training set, where they say they only include structures with resolution of 9A or less. NMR structures don't really have a resolution, that's more specific to crystallography. However, I can't actually verify that no NMR structures were included without directly inspecting their list of selected structures.

I think it is very plausible that they don't use NMR structures here, but I was looking for a specific statement on it in the paper. I think your guess is plausible, but I don't think the paper is clear enough here to be sure about this interpretation.

Yes, thanks for calling that out. In verifying my statement I actually was confused because you can see they filter NMR out of the eval set (saying so explicitly) but don't say that in the test set section (IMHO they should be required to publish the actual selection script so we can inspect the results).

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

#60

Post by niemandhier »

Metacelsus wrote: post #4

From: https://www.nature.com/articles/d41586-024-01383-z >Unlike RoseTTAFold and AlphaFold2, scientists will not be able to run their own version of AlphaFold3, nor will the code underlying AlphaFold3 or other information obtained after training the model be made public. Instead, researchers will have access to an ‘AlphaFold3 server’, on which they can input their protein sequence of choice, alongside a selection of…

The logical consequence is to put all scientific publications under a license that restricts the right to train commercial ai models on them.

Science advances because of an open exchange of ideas, the original idea of patents was to grant the inventor exclusive use in exchange for disclosure of knowledge.

Those who did not patent, had to accept that their inventions would be studied and reverse engineered.

The „as a service“ model, breaks that approach.

Post reply on HN