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

#191

Post by natechols » Wed, May 08, 2024, 6:03 PM UTC

dekhn wrote: post #182

natechols wrote: post #125

Earlier quoted context omitted.

The DeepMind team was essentially forced to publish and release an earlier iteration of AlphaFold after the Rosetta team effectively duplicated their work and published a paper about it in Science. Meanwhile, the Rosetta team just published a similar work about co-folding ligands and proteins in Science a few weeks ago. These are hardly the only teams working in this space - I would expect progress to be very fast in…

How much has changed- I talked with David Baker at CASP around 2003 and he said at the time, while Rosetta was the best modeller, every time they updated its models with newly determined structures, its predictions got worse :)

It's kind of amazing in retrospect that it was possible to (occasionally) produce very good predictions 20 years ago with at least an order of magnitude smaller training set. I'm very curious whether DeepMind has tried trimming the inputs back to an earlier cutoff point and re-training their models - assuming the same computing technologies were available, how well would their methods have worked a decade or two ago? Was there an inflection point somewhere?

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

#192

Post by coffeemug » Wed, May 08, 2024, 6:04 PM UTC

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…

> 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

This seems to me an empirical question about the world. It’s clear our minds are limited, and we understand complex phenomena through abstraction. So either we discover we can continue converting advanced models to simpler abstractions we can understand, or that’s impossible. Either way, it’s something we’ll find out and will have to live with in the coming decades. If it turns out further abstractions aren’t possible, well, enlightenment thought had lasted long enough. It’s exciting to live at a time in humanity’s history when we enter a totally uncharted new paradigm.

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

#193

Post by ChuckMcM » Wed, May 08, 2024, 6:05 PM 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…

Interesting times indeed. I think the early history of medicines takes away from your observation though. In the 19th and early 20th century people didn't know why medicines worked, they just did. The whole "try a bunch of things on mice, pick the best ones and try them on pigs, and then the best of those and try a few on people" kind of thing. In many ways the mice were a stand in for these models, at the time scientists didn't understand nearly as much about how mice worked (early mice models were pretty crude by today's standards) but they knew they were a close enough analog to the "real thing" that the information provided by mouse studies was usefully translated into things that might help/harm humans.

So when you're tools can produce outputs that you find useful, you can then use those tools to develop your understanding and insights. As a tool, this is quite good.

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

#194

Post by jprete » Wed, May 08, 2024, 6:06 PM UTC

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…

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, but if they aren't trying to explain anything, what are they even doing?

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

#195

Post by nybsjytm » Wed, May 08, 2024, 6:07 PM UTC

bluerooibos wrote: post #180

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...

That's pretty good. Based on the previous performance improvements of Alpha-- models, it'll be nearing 100% in the next couple of years.

Just "Alpha-- models" in general?? That's not a remotely reasonable way to reason about it. Even if it were, why should it stop DeepMind from clearly communicating accuracy?

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

#196

Post by aaroninsf » Wed, May 08, 2024, 6:08 PM 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…

The top HN response to this should be,

what happens is an opportunity has entered the chat.

There is a wave coming—I won't try to predict if it's the next one—where the hot thing in AI/ML is going to be profoundly powerful tools for analyze other such tools and render them intelligible to us,

which will I imagine mean providing something like a zoomable explainer. At every level there are footnotes; if you want to understand why the simplified model is a simplification, you look at the fine print. Which has fine print. Which has...

Which doesn't mean there is not a stable level at which some formal notion of "accurate" cannot be said to exist, which is the minimum viable level of simplification.

Etc.

This sort of thing will of course will the input to many other things.

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

#197

Post by fire_lake » Wed, May 08, 2024, 6:11 PM UTC

jprete wrote: post #194

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…

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…

What if the underlying principles of the universe are too complex for human understanding but we can train a model that very closely follows them?

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

#198

Post by sangnoir » Wed, May 08, 2024, 6:11 PM UTC

nojvek wrote: post #189

So much hyperbole from recent Google releases. I wish they didn't hype AI so much, but I guess that's what people want to hear, so they say that.

I don't blame them for hyping their products - if only to fight the sentiment that Google is far behind OpenAI because they were not first to release a LLM.

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

#199

Post by variadix » Wed, May 08, 2024, 6:11 PM UTC

interroboink wrote: post #167

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…

> ... and strongly believe that science's goal is to produce falsifiable hypotheses, these new approaches will be extremely depressing I don't quite understand this point — could you elaborate? My understanding is that the ML model produces a hypothesis, which can then be tested via normal scientific method (perform experiment, observe results). If we have a magic oracle that says "try this, it will work", and then w…

There is an issue scientifically. I think this point was expressed by Feynman: the goal of scientific theories isn’t just to make better predictions, it’s to inform us about how and why the world works. Many ancient civilizations could accurately predict the position of celestial bodies with calendars derived from observations of their period, but it wasn’t until Copernicus proposed the heliocentric model and Galileo provided supporting observations that we understood the why and how, and that really matters for future progress and understanding.

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

#200

Post by dekhn » Wed, May 08, 2024, 6:12 PM UTC

jprete wrote: post #194

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…

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…

That's the aspirational goal. And I would say that it's a bit of an inflexible one- for example, if we had an ML that could generate molecules that cure diseases that would pass FDA approval, I wouldn't really care if scientists couldn't explain the underlying principles. But I'm an ex-scientist who is now an engineer, because I care more about tools that produce useful predictions than understanding underlying principles. I used to think that in principle we could identify all the laws of the universe, and in theory, simulate that would enough accuracy, and inspect the results, and gain enlightenment, but over time, I've concluded that's a really bad way to waste lots of time, money, and resources.