[HN Gopher] Foldit
___________________________________________________________________
Foldit
Author : tosh
Score : 44 points
Date : 2024-02-18 16:55 UTC (6 hours ago)
(HTM) web link (en.wikipedia.org)
(TXT) w3m dump (en.wikipedia.org)
| Havoc wrote:
| I used to participate in the folding at home project. Not sure it
| makes sense post alphaFold. Is this not a solved problem now?
|
| Or does additional compute still matter?
| humnre wrote:
| > Is this not a solved problem now?
|
| This is an interesting question.
|
| Can any contemporary "ai" solution be considered a solved
| problem?
|
| A lot of these neural net architecture are designed first and
| foremost as approximation engines without any guarantees the
| provided approximation is even any good.
|
| This can be useful, but especially in a medical sense, also
| insufficient or even dangerous.
|
| > AlphaFold's protein structure prediction results at CASP were
| described as "transformational" and "astounding".[93][94] Some
| researchers noted that the accuracy is not high enough for a
| third of its predictions, and that it does not reveal the
| mechanism or rules of protein folding for the protein folding
| problem to be considered solved.[95] Nevertheless, it is
| considered a significant achievement in computational
| biology[92] and great progress towards a decades-old grand
| challenge of biology.[93]
|
| https://en.m.wikipedia.org/wiki/Protein_folding
|
| Protein folding is still very much an unsolved problem.
| COGlory wrote:
| What AlphaFold is doing is essentially matching a sequence of
| amino acids to solved protein structures, albeit dynamically,
| and with some advanced constraints. In essence, it's not
| predicting how the protein will fold, but rather, how the
| protein will look once it's done folding. And in many many
| cases, there's no matching fold for a sequence.
|
| Also, proteins are dynamic. They interact with other proteins.
| They sample multiple conformations, they frequently rearrangle,
| or become disordered, and then re-ordered. AlphaFold is just a
| single snapshot.
|
| If we want to understand how proteins fold, we need more than
| just AlphaFold.
| samtho wrote:
| Link to project: https://fold.it/
|
| Biochemistry mystifies me in same way that most other sciences to
| do not. It's amazing to me that they can, in theory, derive
| useful insight or scientific leads from people playing.
|
| Does anyone have an ELI5 on why/if this is more efficient than
| just iterating through combination programmatically?
| synapsomorphy wrote:
| The goal of most/all machine learning is hunting down
| performance maxima in a super high dimensional space. In this
| case the space is the positions and angles etc of the atoms
| that comprise a protein and the "performance" is the stability
| of the protein.
|
| For the number of atoms that comprise most proteins, iterating
| through all the possible positions would take an unimaginable
| amount of time, so you have to have some kind of search method
| to identify good position-space-areas to investigate more
| closely.
|
| My guess as to where people help in is getting away from bad
| local maxima. In my experience playing foldit, sometimes you
| can see pretty clearly that the stability is not good and it's
| not going to get much better with small changes - the algorithm
| has found a bad local maxima of performance - so you can
| manually move big chunks of the protein around to explore a new
| part of the position-space. This kind of evaluation, knowing
| when to stop climbing a small hill and instead go looking for
| bigger hills, seems to be something that humans are pretty
| decent at. Of course there's also a million algorithms to do
| the same thing without humans.
| COGlory wrote:
| Just a nitpick, we typically call it a local minima, because
| we are trying to minimize energy. A stable protein will be at
| (or near) the minimal energy conformation.
|
| Otherwise, I think you are absolutely correct. It's a nearly
| infinite computational problem that has a tendency to
| overfit. There are all sorts of ways to try to solve this
| problem, but they don't always work as well in all cases.
| synapsomorphy wrote:
| Yeah, it's actually a loss function minima, just trying to
| ELI5ify it a bit.
| web007 wrote:
| The added benefit of FoldIt is to see _how_ humans find a
| better answer than naive "shake" and local minima/maxima.
| Those methods can then be integrated into automation to get
| better results. So it's not just "people are better at this,
| let them do the work" it's "let's get people to show their
| work" and then use that process to make better tools.
| el_benhameen wrote:
| If you misfold the proteins, does it spread to other users and
| crash the game?
| amarant wrote:
| Depends. If you manage to fold a prion it will spread to other
| users and corrupt their memory, introduce odd rendering
| artifacts and finally brick their computer.
|
| ;)
| harveywi wrote:
| They missed an opportunity to call it Texas Fold 'Em.
| recursive wrote:
| From Washington though.
| schappim wrote:
| This is like Ender's Game for protein folding.
___________________________________________________________________
(page generated 2024-02-18 23:01 UTC)