AI-Powered AlphaFold 2: Revolutionizing Protein Folding

Click For Summary

Discussion Overview

The discussion revolves around the implications of AI, particularly AlphaFold 2, in the field of protein folding. Participants explore the relationship between human intelligence and AI capabilities, the understanding of algorithms, and the nature of artificial intelligence in scientific applications.

Discussion Character

  • Exploratory
  • Debate/contested
  • Conceptual clarification

Main Points Raised

  • Some participants express enthusiasm for AI's role in biology, suggesting that it surpasses human capabilities in predicting protein folding.
  • Others argue that comparing human intelligence to AI capabilities is misleading, using analogies such as flying and calculating pi.
  • There is a discussion about the lack of understanding of how AI algorithms, like those used in AlphaFold, arrive at their predictions, contrasting this with human understanding of other technologies.
  • Participants note that while AlphaFold's predictions may be comparable to experimental results, discrepancies can arise from either prediction errors or experimental artefacts.
  • Concerns are raised about the implications of labeling algorithms as "Artificial Intelligence," suggesting it may mislead people into thinking they possess human-like intelligence.
  • Some participants highlight the difference between coding AI algorithms and traditional programming, emphasizing the reliance on statistical methods in AI.
  • There is a mention of the complexity of protein folding as a combinatorial problem, which may involve unknown rules compared to games like Go or Chess.

Areas of Agreement / Disagreement

Participants express a mix of agreement and disagreement regarding the capabilities of AI versus human intelligence, the understanding of algorithms, and the implications of AI in scientific contexts. No consensus is reached on these points.

Contextual Notes

Participants acknowledge limitations in understanding AI algorithms and the potential for discrepancies in experimental results versus predictions. The discussion reflects ongoing uncertainties in the field of AI and protein folding.

Biology news on Phys.org
Saying that humans aren't smart enough to predict the folding of a protein molecule is like saying that we don't have the arm strength to fly.

We concoct planes to fly and AI to solve the folding problem.
 
  • Like
Likes   Reactions: Ygggdrasil and BillTre
.Scott said:
Saying that humans aren't smart enough to predict the folding of a protein molecule is like saying that we don't have the arm strength to fly.

We concoct planes to fly and AI to solve the folding problem.
Sure, but the difference is we understand how planes fly, but can't fully grasp the details on how & why these algorithms work for protein folding, Go, chess or whatever. You get a statistical certainty, but no absolute proof.
 
BWV said:
Sure, but the difference is we understand how planes fly, but can't fully grasp the details on how & why these algorithms work for protein folding...
Maybe we will understand when we fold proteins for as long as we've been flying airplanes.

On the other hand, we may bump into the conundrum of whether anything can totally understand itself, whether machine or animal.

Anyhow, food for endless thought, ...or nightmares!
 
If I use a computer to calculate pi to 1000 digits, is it because I am not smart enough to calculate it myself?
 
.Scott said:
If I use a computer to calculate pi to 1000 digits, is it because I am not smart enough to calculate it myself?
Not the same, as you know how to do the calculation and explicitly provide these instructions to the computer.

We don't really know how complex ANNs arrive at their answers - can certainly study and learn from them, but if we really understood AlphaZero, for example, then we could presumably create Stockfish or Deepblue type programs to beat it. protein folding is a larger combinatorial space than Go or Chess and unlike the games, there may be ‘rules‘. we are not aware of
 
More from Nature, this may be the biggest science story of the year
https://www.nature.com/articles/d41586-020-03348-4
This is a big deal,” says John Moult, a computational biologist at the University of Maryland in College Park, who co-founded CASP in 1994 to improve computational methods for accurately predicting protein structures. “In some sense the problem is solved.”
...

nearly two-thirds were comparable in quality to experimental structures. In some cases, says Moult, it was not clear whether the discrepancy between AlphaFold’s predictions and the experimental result was a prediction error or an artefact of the experiment.

1620846240680.jpeg
 
BWV said:
Not the same, as you know how to do the calculation and explicitly provide these instructions to the computer.
If I know the AI algorithm - and code it myself, then is it like long division?

Calling an algorithm "Artificial Intelligence" is like calling a driver-assist tool "Autopilot". The name alone tempts you to think of the application as independently smart and "person-like".
 
.Scott said:
Calling an algorithm "Artificial Intelligence" ...tempts you to think of the application as independently smart and "person-like".
I did not make up the term and am not tempted to think about ANNs as either ’smart’ or ‘person-like’
 
  • #10
BWV said:
I did not make up the term and am not tempted to think about ANNs as either ’smart’ or ‘person-like’
But coding up something that uses AI techniques is different than coding up something that doesn't rely on statistics or pattern discovery?
 
  • #11
.Scott said:
But coding up something that uses AI techniques is different than coding up something that doesn't rely on statistics or pattern discovery?
it is if you don't understand exactly the algorithm is doing. We don't understand exactly how or why AlphaZero is better at chess than Stockfish. One could imagine, as an analogy, some dumbass feeding a bunch of data into a NN of measurements of force, acceleration and mass then relying on the algorithm without understanding F=MA
 
Last edited:

Similar threads

  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 5 ·
Replies
5
Views
3K
  • · Replies 2 ·
Replies
2
Views
931
  • · Replies 20 ·
Replies
20
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
Replies
10
Views
5K
  • · Replies 5 ·
Replies
5
Views
1K
  • · Replies 13 ·
Replies
13
Views
4K
  • · Replies 3 ·
Replies
3
Views
5K