xtaldave, to strucbio
@xtaldave@xtaldave.net avatar

Open letter to Nature editors complaining about the lack of code availability for AF3 (Publishing code is normally a prerequisite for publishing in Nature)

(Yes, I am fully aware of the irony of using a Google form to do this - not my idea, just sharing.)

@strucbio

https://docs.google.com/forms/d/e/1FAIpQLSf6ioZPbxiDZy5h4qxo-bHa0XOTOxEYHObht0SX8EgwfPHY_g/viewform

flaccide, to ArtificialIntelligence French

L' à bon escient

En 2018, , l’IA créée par , faisait une percée spectaculaire. [...] Une IA capable de prédire à quoi ressemblera une à partir de sa seule séquence. Sur les 200 millions de protéines connues, nous ne connaissons la structure 3D que de 20 % d'entre elles. Le fait donc cette promesse : combler ces lacunes pour de grandes avancées médicales et la création de nouveaux

radiofrance.fr/franceculture/p…

ngmi, to ai
@ngmi@mastodon.online avatar
xtaldave, to strucbio
@xtaldave@xtaldave.net avatar

Space exploration: finding new protein conformations using AlphaFold2 | Nature Structural & Molecular Biology

https://www.nature.com/articles/s41594-023-01186-2#ref-CR1

@strucbio

terwilltom, to random

A commentary by Derek Lowe explaining the significance of our article,

"AlphaFold predictions are valuable hypotheses and accelerate but do not replace experimental structure determination." Nature Methods (2023) (https://www.nature.com/articles/s41592-023-02087-4)

https://www.science.org/content/blog-post/alphafold-s-place-world

@strucbio

xtaldave, to strucbio
@xtaldave@xtaldave.net avatar
martenson, to random

Need to fold some proteins?

Private
p2phuture,

Thank you @xtaldave ! @JPricePhysics @nmrchat @p_vanderwel
Incidentally anyone have any thoughts on efficacy of for protein-ligand interactions?

danmcquillan, to ai
@danmcquillan@kolektiva.social avatar

😂😂😂 there was more scientific rationale in renaissance alchemy than there is in deep learning's brute-forced correlationism

xtaldave, to strucbio
@xtaldave@xtaldave.net avatar

How accurately can one predict drug binding modes using AlphaFold models?

"the accuracy of ligand binding poses predicted by computational docking to AF2 models is not significantly higher than when docking to traditional homology models and is much lower than when docking to structures determined experimentally without these ligands bound."

@strucbio

http://biorxiv.org/cgi/content/short/2023.05.18.541346v1?rss=1

julien_denis, to cscareerquestions French
  • All
  • Subscribed
  • Moderated
  • Favorites
  • JUstTest
  • kavyap
  • DreamBathrooms
  • khanakhh
  • magazineikmin
  • InstantRegret
  • tacticalgear
  • thenastyranch
  • Youngstown
  • rosin
  • slotface
  • modclub
  • everett
  • ngwrru68w68
  • anitta
  • Durango
  • osvaldo12
  • normalnudes
  • cubers
  • ethstaker
  • mdbf
  • tester
  • GTA5RPClips
  • cisconetworking
  • Leos
  • megavids
  • provamag3
  • lostlight
  • All magazines