AlphaFold 3 predicts the structure and interactions of life's molecules • Hacker News Board

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

#381

Post by porphyra » Thu, May 09, 2024, 5:26 AM UTC

nybsjytm wrote: post #62

Important caveat: it's only about 70% accurate. Why doesn't the press release say this explicitly? It seems intentionally misleading to only report accuracy relative to existing methods, which apparently are just not so good (30%, 50% in various settings). https://www.fastcompany.com/91120456/deepmind-alphafold-3-dn...

They also had a headline for Alphazero that convinced everyone that they crushed Stockfish and that classical chess engines were stuff of the past, when in fact it was about 50 elo better than the Stockfish version they were testing against, or roughly the same as how much Stockfish improves each year.

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

#382

Post by kobenni » Thu, May 09, 2024, 5:28 AM UTC

stouset wrote: post #363

dekhn wrote: post #93

Earlier quoted context omitted.

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…

> If you're the sort of person who believes that human brains are capable of understanding the "why" of how things work in all its true detail, you'll find this an interesting challenge- can we actually interpret these models, or are human brains too feeble to understand complex systems without sophisticated models? I think chess engines, weirdly enough, have disabused me of this notion. There are lots of factors a h…

I don't understand why you would draw this conclusion. The deep search you describe is an algorithm that humans can understand perfectly fine. Humans just can't solve it in their heads and need to let a computer handle the number crunching. Just like a scientist may understand the differential equations to describe a system perfectly fine, but require a computer to approximate the solution for an initial value problem.

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

#383

Post by arjvik » Thu, May 09, 2024, 5:42 AM UTC

sangnoir wrote: post #220

LarsDu88 wrote: post #190

As a software engineer, I kind of feel uncomfortable about this new model. It outperforms Alphafold 2 at ligand binding, but Alphafold 2 also had some more hardcoded and interpretable structural reasoning baked into the model architecture. There's so many things you can incorporate into a protein folding model such as structural constraints, rotational equivariance, etc, etc This new model simple does away with some…

> Makes me feel a bit uncomfortable. Why? Do compilers which can't bootstrap themselves also make you uncomfortable due to dependencies on pre-built artifacts? I'm not saying you're unjustified to feel that way, but sometimes more abstracted systems are quicker to build and may have better performance than those built from the ground up. Selecting which one is better depends on your constraints and taste

Compilers are deterministic (for the most part, and it's incredibly rare to introduce a compiler bug that self-replicates in future compilers (unless you're Ken Thompson and are reflecting upon trust itself)).

Alternatively, AlphaFold 2's output is noisy, and using that to train AlphaFold 3, which presumably may be used to train what becomes AlphaFold 4, results in a cascade of errors.

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

#384

Post by tsimionescu » Thu, May 09, 2024, 5:43 AM UTC

fsloth wrote: post #379

jprete wrote: post #194

Earlier quoted context omitted.

The goal of science has always been to discover underlying principles and not merely to predict the outcome of experiments. I don't see any way to classify an opaque ML model as a scientific artifact since by definition it can't reveal the underlying principles. Maybe one could claim the ML model itself is the scientist and everyone else is just feeding it data. I doubt human scientists would be comfortable with that…

AFAIK in wet science you need (or needed) to do tons of experimentations with liquids with specific molar compositions and temperatures splurging in and out of test tubes - basically just physically navigating a search space. I would view an AI model with super powerful guestimation capability as a much faster way of A) cutting through search space B) providing accidental discoveries while at it Now, if we look at hi…

> singularity? That’s just a word for “we don’t know what’s gonna happen” - not a specific concrete forecasted scenario

It's more specific than you make it out. The singularity idea is that smart AIs working on improving AI will produce smarter AIs, leading to an ever increasing curve that at some point hits a mathematical singularity.

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

#385

Post by d0mine » Thu, May 09, 2024, 5:43 AM UTC

drdeca wrote: post #361

jvanderbot wrote: post #255

Earlier quoted context omitted.

"this tool works better than my intuition" absolutely is science. "be quiet and calculate" is a well worn mantra in physics is it not?

“calculate” in that phrase, refers to doing the math, and the understanding that that entails, not pressing the “=“ button on a calculator.

Why do you think systems of partial differential equations (common in physics) are somehow provide more understanding than the corresponding ML math (at the end of the day both can produce results using a lots of matrix multiplications).

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

#386

Post by kajic » Thu, May 09, 2024, 5:47 AM UTC

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…

It’s much easier to reverse engineer a solution that you don’t understand (and discover important underlying theories on that journey), than it is to arrive at that same solution and the underlying theories without knowing in advance where you are going.

For this reason, discoveries made by AI will be immensely useful for accelerating scientific progress, even if those discoveries are opaque at first.

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

#387

Post by yieldcrv » Thu, May 09, 2024, 5:47 AM UTC

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 it creates new studies, such as diagnosing these models behaviors without the doctor having an intricate understanding of all of the model's processes/states just like with natural organisms

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

#388

Post by strogonoff » Thu, May 09, 2024, 5:58 AM UTC

jltsiren wrote: post #294

strogonoff wrote: post #238

Earlier quoted context omitted.

Can underlying principles be discovered using the framework of scientific method? The primary goal of models and theories it develops is to support more experiments and eventually be disproven. If no model can be correct, complete and provable in finite time, then a theory about underlying principles that claims completeness would have to be unfalsifiable. This is reasonable in context of philosophy, but not in natur…

I don't find that argument convincing. People clearly have been able to discover many underlying principles using the scientific method. Then they have been able to explain and predict many complex phenomena using the discovered principles, and create even more complex phenomena based on that. Complex phenomena such as the technology we are using for this discussion. Words dont have any inherent meaning, just the mea…

> The kind of absolute truth you are talking about may make sense when discussing philosophy or religion.

Exactly—except you are talking about it, too. When you say “discovering underlying principles”, you are implying the idea of absolute truth where there is none—the principles are not discovered, they are modeled, and that model is our fallible human construct. It’s a similar mistake as where you wrote “explain”: every model (there should always be more than one) provides a metaphor that 1) first and foremost, jives with our preexisting understanding of the world, and 2) offers a lossy map of some part of [directly inaccessible] reality from a particular angle—but not any sort of explanation with absolute truth in mind. Unless you treat scientific method as something akin to religion, which is a common fallacy and philosophical laziness, it does not possess any explanatory powers—and that is very much by design.

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

#389

Post by whymauri » Thu, May 09, 2024, 6:01 AM UTC

moconnor wrote: post #94

nexuist wrote: post #48

Earlier quoted context omitted.

As a steelman, wouldn't the abundance of infinitely generate-able situations make it _easier_ for us to develop strong theories and models? The bottleneck has always been data. You have to do expensive work in the real world and accurately measure it before you can start fitting lines to it. If we were to birth an e.g. atomically accurate ML model of quantum physics, I bet it wouldn't take long until we have mathemat…

Maybe; AI chess engines have improved human understanding of the game very rapidly, even though humans cannot beat engines.

I've seen generative models for molecular structures produce results that looked non-sensical at first glance; however, when passed along to more experienced medicinal chemists they identified a bit 'creativity' that only a very advanced practitioner would understand or appreciate. Those hypotheses, which would not be produced by most experts, served as an anchor for further exploration of novel structures and ideas.

So in a way, what you say is already possible. Just how GMs in chess specialize in certain openings or play styles, master chemists have pre-existing biases that can affect their designs; algorithms can have different biases which push exploration to interesting places. Once you have a good latent representation of relevant chemical space, so you can optimize for this sort of creativity (a practical but boring example is to push generation outside of patent space).

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

#390

Post by pineaux » Thu, May 09, 2024, 6:12 AM UTC

dumpsterdiver wrote: post #299

chasd00 wrote: post #270

Earlier quoted context omitted.

If all you can do is predict an outcome without being able to explain how then what have you really discovered? Asking someone to just believe you can predict outcomes without any reasoning as to how, even if you're always right, sounds like the concept of faith in religion.

> what have you really discovered? You’ve discovered magic. When you read about a wizard using magic to lay waste to invading armies, how much value would you guess the armies place in whether or not the wizard truly understands the magic being used against them? Probably none. Because the fact that the wizard doesn’t fully understand why magic works does not prevent the wizard from using it to hand invaders their as…

Exactly! The magic to lay waste to invading armies is packaged into a large flask and magical metal birds are flown to above the army. There the flask is released from the birds bellies and gently glides down. When the flask is at optimum height it releases the power of the sun and all that are beneath it get vaporized. A newer version of this magic is attached to a gigantic fireworks rocket that can fly over whole mountain ranges and seas.