161–170 of 683 posts
So the median accuracy went from ~58% (2018) to 84% (2020) in 2 years? Does 84% == solved? Also, any low hanging frut implications for longevity tech?
So who will have access to this? DeepMind never publishes their models.
Earlier quoted context omitted.
>Those need to be tackled too before I would consider protein folding 'solved' Semantics. From a systemtheoretical point of view, dynamic folding is an abstraction of static folding; solve (i.e. understand the underlying mechanisms) static folding and you can start progressing on dynamic folding, building up on your previously achieved solution. Wether it's solved or not depends on wether you mean `general folding` o…
Solve could mean understanding the underlying mechanism, but in this case, I don’t think that’s how they did it.
Earlier quoted context omitted.
So what? The DNA only codes for the RNA and amino acid sequence. Structure determination is yet another topic. When we determine the protein structure we already know the sequence. Neither DeepMind has to look at the DNA to train their DNN.
They are two topics which are both relevant to the discussion. Structure determination is what allows you to see the purpose/effect of the sequence that the DNA encoded.
Has anyone got any good other references for this? After some of the dodgy experiments related to alpha zero (comparing to purposefully degraded chess systems), I'd love to see some independent analysis.
CASP is that independent analysis...
This is a big step forward, but the outstanding question as far as to whether or not this is useful for evaluating novel proteins, is going to be how good is the confidence metric at telling the user to trust or not trust the results. You can see from their examples, that AlphaFold is very good but not perfect. I imagine for some proteins it will still give misleading or erroneous results and if you can’t tell when t…
Scientists can verify that an AlphaFold-predicted structure is correct, or at least useful, without being able to get the structure experimentally. For instance, we could use the AlphaFold-predicted structure to do protein-ligand binding calculations for a bunch of known molecules. If these calculations agree with experimental protein-ligand binding (which they generally do for proteins with known structures), then w…
Earlier quoted context omitted.
This is about proteins, not DNA.
The full chain is DNA -> mRNA -> Ribosome -> tRNA combinations -> amino acid chain -> protein. It's true that in nature there are many steps between DNA and proteins (this list doesn't even include the steps that mediate the translation, ie. start it, stop it, slow it down, ...), but the structure of a protein is fully determined by the DNA code. Protein folding is about you start from the DNA code that is fed into t…
But anyway your answer does not contradict my statement. What you say belongs to the basics of molecular biology, but does not justify that DNA should be considered when determining the structure of proteins. In practice, the amino acid sequence is always already present.
Earlier quoted context omitted.
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 predict…
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 wh…
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.
CASP (Critical Assessment of protein Structure Prediction) is calling it a solution. To quote from the article: "We have been stuck on this one problem – how do proteins fold up – for nearly 50 years. To see DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts, wondering if we’d ever get there, is a very special moment." --Professor John Moult C…
This is an issue of the more subtle aspects of English. "To see DeepMind produce a solution for this" does not imply something is solved. I can produce a bad solution. I can produce a really good solution. All without solving a problem.