[IgniteTheSun]

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.

[mrDmrTmrJ]

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.

[sanxiyn]

That's training time, not inference time.

[foota]

My reading based on context was that this was time to train, not time to predict.

[Rochus]

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).