News for hackers. Stuff that matters.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by derefr on Monday November 30, 2020 @11:20AM (#25255384)
We can already determine how a few proteins (170k — which sounds like a lot, but which is only 0.09% of all currently-catalogued protein sequences) fold by experimental work.

What an accurate model of protein folding allows us to do, is to take our big database of DNA, predict protein foldings for all of it, and then stand up a search index for this database, keying each amino-acid "row" by the "words" of its predicted protein's structural features.

We could then, with a simple search query that executes in O(log n) time, find DNA targets that produce molecules with interesting structures that might be worthy of study.

This would, for example, be a game-changer in how biopharmaceutical macromolecule-therapy R&D is conducted. Right now we have to notice that some bacterium or another produces some interesting protein, and then engineer a bioreactor to get more of that protein. With this tech, we can work backward from an entirely hyothetical, under-specified "interesting protein", to figure out what catalogued-but-unstudied DNA sequences produce never-before-catalogued proteins that fit that particular functional "shape", and therefore might do the interesting thing. Then we can either directly synthesize that same DNA, or find the organism we originally sampled it from and study it more.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by fabian2k on Monday November 30, 2020 @11:27AM (#25255473)
"A few" does appear quite dismissive of the enormous amounts of effort in structural biology so far. There are more than 170,000 structures in the PDB right now.

To determine potential targets for drugs we have to understand what the proteins do. Having the structure is not really enough for that, it doesn't tell you the purpose of the protein (though it certainly can give you some hints).

In most cases the proteins were determined to be interesting by other experiments, and then people decided to try and solve their structure. So the structures we already solved are also biased towards the more biologically relevant proteins.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by derefr on Monday November 30, 2020 @11:36AM (#25255601)
170k is "a few" compared to 180 million (i.e. the size of the PDB as soon as someone runs AlphaFold over everything in the UniProt.)

> In most cases the proteins were determined to be interesting by other experiments, and then people decided to try and solve their structure.

Yes, that's what we're doing right now, because structure is not a useful predictor, because we don't have structure available in advance of studies on the protein itself. There was no point to a "functional taxonomy" of proteins, because we were never trying to predict with protein-structure as the only data available.

In a world where protein structure is "on tap" in a data warehouse, part of the game of bioinformatics will become "structural analysis" of classes of known-function proteins, to find functional sub-units that do similar things among all studied proteins, allowing searches to be conducted for other proteins that express similar functional sub-units.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by fabian2k on Monday November 30, 2020 @11:43AM (#25255717)
Determining what a protein structure does might be even harder than folding. Right now we can't really do that ab initio, you have determine the activity in the lab and then look at the structure. And that allows you to potentially identify this motif in other proteins.

If someone produces an AI that you give a sequence and it tells you what the protein does exactly, I'd be extremely impressed. I don't see that happening soon.

The specifics matter a lot here. We can often determine rough functions for subdomains by homology alone. But that really doesn't tell you the full story, it only gives you some hints on what that protein actually does.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by jeffxtreme on Monday November 30, 2020 @03:28PM (#25258538)
Five years ago, I would have said the following:

"If someone produces an AI that you give a sequence and it tells you the protein conformation, I'd be extremely impressed".

Sure there are many more things to solve in this space; but that doesn't take away that this is an impressive achievement and does unlock quite a few things (including making more tractable the problem you just brought up). I'm excited to see what DeepMind works on now and what the new state of the world will be just five years from now.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by fabian2k on Monday November 30, 2020 @03:58PM (#25258881)
I think I have to clarify that my response was to a large part to the "this will change all our lives" part, and might look too negative on its own. I'm very, very impressed by these results, but that still doesn't mean that we just solved biology. If this works that well on folding, this could mean that a lot of other stuff that simply didn't work well in silico might come into reach.

I'm maybe overcompensating for the tech-centric population here, with some comments speculating for very near and drastic impacts from discoveries like this. Biology and life sciences are much slower, and there's always more complexity below every breakthrough. That does tend to push me towards commenting with the more skeptical and sober view here.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by whatshisface on Monday November 30, 2020 @11:59AM (#25255933)
My understanding of this is not perfect, but wouldn't answering the "actually does" question require a full biomolecular model of the cell, or even the whole organism? If so I see what you mean. I suppose that it might be possible to get around this by improving the theory of catalysts so that you could look at a site and say, "oh, this will act in such a way..." Dynamic quantum simulation of a few atoms at the active site is hardly easy but a far sight easier than the other.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by Rochus on Monday November 30, 2020 @11:42AM (#25255695)
It's a step forward for sure, but structures change over time to perform their function. The method described here only returns a static structure. Much more research and development is needed to be able to predict the dynamic behavior and interplay with other proteins or RNA.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by AlexCoventry on Monday November 30, 2020 @04:11PM (#25259035)
> as soon as someone runs AlphaFold over everything in the UniProt

It'll take a while before those results can be trusted, though, right? There's probably a selection bias in the training data for proteins which are easy to crystallize, so many proteins probably aren't well represented by the training examples.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by entropicdrifter on Monday November 30, 2020 @11:34AM (#25255566)
170,000 is three orders of magnitude less than the number of recorded protein sequences. I don't think it's dismissive to describe that as comparatively few.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by flobosg on Monday November 30, 2020 @12:02PM (#25255963)
Structure is much, much more conserved than sequence. In other words, protein sequences with low sequence identity can fold similarly due to the physical constraints that guide protein folding.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by ClumsyPilot on Monday November 30, 2020 @11:40AM (#25255675)
I don't know the field, and I understood 'a few' as like a dozen, certainly not in the thousands.

Anyone uninitiated with think the same, and thise already informed. Well, they are already informed.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by ALittleLight on Monday November 30, 2020 @01:29PM (#25257134)
I also don't know the field and the opposite concern is that 170,000 sounds like a lot, but, apparently, it's a relatively small amount compared to the number of proteins there are. It makes sense to me to refer to it as a small number - e.g. "That hard drive is tiny." "No, it stores several million bytes..."
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by btilly on Monday November 30, 2020 @12:57PM (#25256709)
We can already determine how a few proteins fold by experimental work.

Where "a few" is around 0.1% of the known 180 million proteins. So a relative few and a whole lot.

But the catch is which proteins could we figure out by experiment, and which not. In particular membrane proteins are hard to experimentally determine. But knowing how they fold is very important for figuring out how to get things to react with or get through membranes such as cell walls. Which is an important problem for everything from understanding how viruses work to targeted delivery of drugs. We now have a way to find those structures.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by FredFS456 on Monday November 30, 2020 @05:39PM (#25259964)
There are post-translational modifications to proteins. This means that for many (most?) proteins, the amino acid chain sequence is different from what you would predict from the DNA. These modifications are dependent on the state of the cell at the time of translation, and so cannot be predicted from the DNA alone. Even with a 100% accurate folding model, we cannot simply know the shapes of all the proteins inside the human body based on the genome.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by carlob on Monday November 30, 2020 @11:40AM (#25255673)
Here is another interesting approach in synthetic protein building:

https://science.sciencemag.org/content/369/6502/440.abstract

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by ghostpepper on Monday November 30, 2020 @11:27AM (#25255476)
This does indeed sound like a game changer then, if true
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by IgniteTheSun on Monday November 30, 2020 @11:30AM (#25255518)
Considering that this system "uses approximately 128 TPUv3 cores (roughly equivalent to ~100-200 GPUs) run over a few weeks" to determine a single protein structure, making predictions for all proteins encoded in a human genome seems impractical at this stage. With luck, this advance will help lead to discovery and definition of new folding rules and optimizations that will make protein folding predictions for the whole human genome more tractable.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by mrDmrTmrJ on Monday November 30, 2020 @12:06PM (#25256031)
I think it is possible to make predictions for all proteins encoded in the human genome. Perhaps you misread a very long and confusing sentence?

Background, Neural networks have two modes 1) training - where you learn all the model weights and 2) inference - where you run the model once on new data. Training takes takes a long time, because you're computing derivatives to implement updates rules on millions or billions of parameters based on iteratively examining massive datasets. Inference is extremely fast because you're just running matrix multiplies of those parameters on new data. And TPUs/GPUs are specially designed to compute matrix multiplies.

The article said: "We trained this system [...] over a few weeks." I searched for, but did not see them identify the inference time. I do expect inference time to be well under one second, though I'm not personally experienced with running inference on this type of network architecture.

For comparison, GPT-3 and AlphaStar have month long training times and real-time (sub-second) inference times.

Re:AlphaFold: a solution to a 50-year-old grand challenge in... by sanxiyn on Monday November 30, 2020 @11:36AM (#25255603)
That's training time, not inference time.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by foota on Monday November 30, 2020 @11:38AM (#25255635)
My reading based on context was that this was time to train, not time to predict.
Re:AlphaFold: a solution to a 50-year-old grand challenge in... by Rochus on Monday November 30, 2020 @12:09PM (#25256077)
Still much faster than synthesizing the protein and then doing NMR or cristallography to solve the structure puzzle what easily takes half a year or more (and very expensive equipment).