Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Alphafold

github.com

Post reply on HN
Print view View original

161–170 of 170 posts

Re: Alphafold

#161

Post by varelse »

timr wrote: post #23
nextos wrote: post #16

Alphafold 2 is very very cool, but we need a little dose of reality. It's still a bit away from really solving protein folding as it was marketed. For example, multi-complex proteins are not well predicted yet and these are really important in many biological processes and drug design: https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-h... A disturbing thing is that the architecture is much less novel than I…

> A disturbing thing is that the architecture is much less novel than I originally thought it would be, so this shows perhaps one of the major difficulties was having the resources to try different things on a massive set of multiple alignments. This is something an industrial lab like DeepMind excels at. Whereas universities tend to suck at anything that requires a directed effort of more than a handful of people. Y…

Transformers seem to be the successor to conv nets. But in my direct experience advocating for them, it's amazing how reluctant industry peeps were to trying them because they associated all the limitations of LSTM networks with them for a long time. YMMV, but that's how it went with me.

I even predicted DeepMind's CASP 14 network would be transformer-based back in 2018, but I couldn't have told you the details of that transformer, just that it was a no-brainer to move from fixed width convolutions to arbitrary width attention sums because sequence motifs and long-range interactions are of arbitrary width in the sequence.

All that seems to have changed with AlphaFold 2 because unlike GPT-XXX, this isn't a parlor trick with memorized text. This is actually useful and the FOSSing of the network will spawn all sorts of new applications of the approach.

So now I wonder what will replace Transformers because nothing lasts forever and there are a lot of smart people trying all sorts of new ideas.

Re: Alphafold

#162

Post by CRConrad »

plankers wrote: post #153
pelorat wrote: post #144

Earlier quoted context omitted.

Teslas philosophy is that self driving is useless if it can't handle every road and route out there, while Waymo who already has a ride hailing service, relies on pre-mapped routes and databases. Both have their advantages and disadvantages. Waymo requires huge databases and a constant network connection. But it's good enough to be used in real-life without a backup driver, in certain select locations that is. If the…

Tesla's approach, however, kills people. Waymo's has not as of yet.

Wait, what about that woman on a bicycle in... Arizona, New Mexico, somewhere like that; about a year ago -- wasn't that Waymo?

Re: Alphafold

#163

Post by markus92 »

CRConrad wrote: post #162
plankers wrote: post #153

Earlier quoted context omitted.

Tesla's approach, however, kills people. Waymo's has not as of yet.

Wait, what about that woman on a bicycle in... Arizona, New Mexico, somewhere like that; about a year ago -- wasn't that Waymo?

That was Uber iirc

Re: Alphafold

#164

Post by Siira »

l33tman wrote: post #138
mikewarot wrote: post #98

Earlier quoted context omitted.

If you took their parameters, then trained it for while on a different set of data, it would vary from the original. I wonder how much compute would be required to make the offset far enough to hold up from scrutiny, and in court. Alternatively, you could manually change the network model, add a few hidden layers, etc... modifying the parameters in step, and result in a new model and new parameters. Some training to…

I would hazard a guess here that taking the parameters and continuing training constitutes "using" the parameters. Then when you get the subpoena you would have to explain the thousands of emails and slack messages discussing how you extend their parameters... :)

It's counterintuitive for me that this is a problem. One man should be able to do this in a month, no need for coordination that leaves behind evidence. Besides, how hard is it to communicate in secret?

Re: Alphafold

#165

Post by TaupeRanger »

sdenton4 wrote: post #136
TaupeRanger wrote: post #84

Earlier quoted context omitted.

That's the case with basically everything DeepMind does. They have a very good PR department which hypes up everything they do while conveniently ignoring that basically nothing of any practical consequence has come of their endeavors. But I do think it's important that these companies exist now so we can see what not to try going forward.

Well here's one example: Deepmind made Wavenet, which turned text-to-speech on it's head. Variants of Wavenet underlie most or all of the talking machines (Google assistant, Alexa, etc.).

That's pretty much it. A maybe-slightly-better computer voice.

Re: Alphafold

#166

Post by TaupeRanger »

Jyaif wrote: post #142
TaupeRanger wrote: post #84

Earlier quoted context omitted.

That's the case with basically everything DeepMind does. They have a very good PR department which hypes up everything they do while conveniently ignoring that basically nothing of any practical consequence has come of their endeavors. But I do think it's important that these companies exist now so we can see what not to try going forward.

Their PR strategy is to take problems people thought were impossible to solve in the next 10 years, and solve them (Go) or nearly solve them (StarCraft 2, protein solving)

No one thought that Go was impossible except people who weren't involved in engineering/software and shouldn't have been taken seriously in the first place.

Superhuman game AI has existed for decades. It's entirely unsurprising that one can play a strategy game, and no one thought it wasn't possible.

I'll send you $500 USD if AlphaFold derivatives lead to a single new therapy or drug that helps real patients in the next 5 years.

Re: Alphafold

#167

Post by timr »

dm319 wrote: post #158
feanaro wrote: post #128

Earlier quoted context omitted.

> And you can't solve the problem at all for non-trivial proteins using physics, so here we are. I'd appreciate if you could expand a bit on what you meant here, sounded interesting.

I guess poster is referring to purely using physics to work out the structure - i.e. no more knowledge than how atoms/molecules move and the sequence. At the moment knowledge is gleaned from evolution by virtue of evolutionary conservancy.

Essentially yes. In theory, you could start from quantum mechanics and get the structure of any chemical matter. In practice, that's intractable. So there has been decades of work to make ever-simpler, less expensive approximations, and use these models of forces/energies to predict the structures of complex biomolecules.For example, google "molecular mechanics" or "molecular dynamics", and you'll find discussion o f things like the van der waals model of an atom, models of chemical bonds that resemble springs from physics 101, coulomb's law, and so on.

People take these simple models, chain them together in different ways, adjust the free parameters (i.e. weights) by fitting to known data, and thus create "force fields" that can be used to estimate the energies and/or forces on a molecule, given only the coordinates of the atoms. These methods work OK for some limited problems, but tend to fly off the rails as simulation times get longer, or if atomic systems have more electrostatics, motion, "weird" atoms (like heavy metals), etc.

This (Alphafold) kind of work is completely different, in that it starts from data, and uses the physical models only to do final refinements (if at all).

Re: Alphafold

#168

Post by sdenton4 »

TaupeRanger wrote: post #165
sdenton4 wrote: post #136

Earlier quoted context omitted.

Well here's one example: Deepmind made Wavenet, which turned text-to-speech on it's head. Variants of Wavenet underlie most or all of the talking machines (Google assistant, Alexa, etc.).

That's pretty much it. A maybe-slightly-better computer voice.

Well, also Alpha-Fold, and let's not forget beating the world champions at Go, which was a really major unsolved problem. I'll also contend that WaveNet was not 'maybe-slightly-better,' but actually a massive leap forward.

The phrase 'who pissed in your cheerios' comes to mind... Here's hoping that if you ever build something worthwhile it is received with a bit more compassion.

Re: Alphafold

#169

Post by sdenton4 »

TaupeRanger wrote: post #166
Jyaif wrote: post #142

Earlier quoted context omitted.

Their PR strategy is to take problems people thought were impossible to solve in the next 10 years, and solve them (Go) or nearly solve them (StarCraft 2, protein solving)

No one thought that Go was impossible except people who weren't involved in engineering/software and shouldn't have been taken seriously in the first place. Superhuman game AI has existed for decades. It's entirely unsurprising that one can play a strategy game, and no one thought it wasn't possible. I'll send you $500 USD if AlphaFold derivatives lead to a single new therapy or drug that helps real patients in the n…

'In the next 10 years' is the key phrase here. Everyone watching Go (I looked at the problem 15-ish years ago) thought it required a massive advance to beat the best humans. DeepMind made that advance.

'bah, whatever, both Newton and Leibniz were hacks. Everyone knew calculus would have been invented anyway. It's basically a consequence of some stuff Archimedes did.'

Re: Alphafold

#170

Post by xor99 »

devindotcom wrote: post #76

Also announced today was RoseTTAFold from UW's Baker Lab, which claims nearly the same accuracy at much higher efficiencies. There's a public server and paper in Science. More info here and here: https://www.bakerlab.org/index.php/2021/07/15/accurate-prote... https://techcrunch.com/2021/07/15/researchers-match-deepmind...

> With RoseTTAFold, a protein structure can be computed in as little as ten minutes on a single gaming computer.

I guess its a little less accurate but the quick compute time makes as much difference too. E.g. research students can have multiple less costly mistakes before achieving what they want with the software.

Post reply on HN