"How AI Cracked the Protein Folding Code and Won a Nobel Prize" video mentions Foldit

Started by beta_helix

beta_helix Staff Lv 1

Foldit mention at the 12-minute mark: https://www.youtube.com/watch?v=cx7l9ZGFZkw&t=722s

More Foldit mentions in the accompanying article: https://www.quantamagazine.org/how-ai-revolutionized-protein-science-but-didnt-end-it-20240626/

"In March 2016, when DeepMind co-founder Demis Hassabis was in Seoul watching his AI system AlphaGo beat a human world champion in the ancient game of Go, he flashed back to playing Foldit as an undergraduate. He wondered: If DeepMind researchers could write an algorithm to mimic the intuition of Go masters, couldn’t they write one to mimic the intuition of Foldit gamers, who knew nothing about biology but could fold proteins?"

BootsMcGraw Lv 1

Speak for yourself, Demis. I have a degree in biology and was studying protein structure over twenty years before Foldit became a thing… and probably before you were born.

jeff101 Lv 1

I agree with Boots. I don't think most Foldit players are stereotypical gamers. In the 12+ years I've been playing Foldit, there have been multiple surveys about our backgrounds. If you examined those, you might be surprised. I think many of us want to make a contribution to science and take the game very seriously. Rather than calling us gamers, calling us citizen scientists would be more appropriate.

What's good about Foldit is that people from any background can play. No advanced degrees or NIH-funded grants are required. We don't have to live in Silicon Valley or attend a prestigious institution. We don't need to have a history of publications in high-impact journals. We can play when we want to, take breaks when we want to, work full-time jobs, be retired, be stay-at-home moms, be caretakers for aging parents, have disabilities, etc. We don't have to pass drug tests or background checks, answer interview questions, or ask for reference letters. We don't have to show up for group meetings. We can stay in our home countries.

I'd like to think that good ideas can come from anywhere. Who knows what ideas get lost because the people bearing them aren't connected to the science apparatus of the world?

jeff101 Lv 1

One thing I hope is that this Nobel Prize will encourage more investment in games like Foldit. There are many things that could be improved about the game that would help capture more of our players' creativity and intuition. Things like adding LUA handles for the latest Foldit tools would help players write more powerful Foldit recipes to automate some of the repetitive tasks involved in playing the game, making it easier for us to design things closer to what we envision. Who knows what doors would open if Foldit players were given access to atomic coordinates or dihedral angles within the game, information I'd imagine is taken for granted by developers of tools outside of Foldit? How effective would external AI tools be if they didn't have access to atomic coordinates or dihedral angles? Whatever Foldit players have been able to accomplish so far has been done without access to this information. Maybe AI developers could learn something from how Foldit players have worked around this obstacle.

It would also be nice to have new protein design puzzles within Foldit, perhaps incorporating some of the latest AI tools. I for one would very much like this, because after many puzzles trying to create certain protein structures, things were finally starting to work for me. Then suddenly it was our last protein design puzzle. I often wonder what interesting designs are already lurking on Foldit's servers awaiting further exploration. Would the latest AI predict them to fold as players designed them? Could our designed structures be mutated to make them more likely to fold? Would any of the designed structures fold in the lab as predicted?

Asclepios Lv 1

Hello, i have a question, i am a new player on foldit (2024) and i want to know how use some tools, how transforme hydrophile into hydrophobe. I want to know how my participation can help scientists. I hope someone can see that and anwser me.
Have a nice day :)