Nazim Bouatta | Machine learning for protein structure prediction, Part 2: AlphaFold2 architecture

Special Lectures on Machine Learning and Protein Folding 2/16/23 Lecture 2
Speaker: Nazim Bouatta, Harvard Medical School
Abstract: AlphaFold2, a neural network-based model which predicts protein structures from amino acid sequences, is revolutionizing the field of structural biology. This lecture series, given by a leader of the OpenFold project which created an open-source version of AlphaFold2, will explain the protein structure problem and the detailed workings of these models, along with many new results and directions for future research.
Lecture 2: Machine learning for protein structure prediction, Part 2: AlphaFold2 architecture
Abstract: Turning the co-evolutionary principle into an algorithm: EvoFormer. Structure module and symmetry principles (equivariance and invariance). OpenFold: retraining AlphaFold2 and insights into its learning mechanisms and capacity for generalization. Applications of variants of AlphaFold2 beyond protein structure prediction: AlphaFold Multimer for protein complexes, RNA structure prediction.

[@maxbailey9164]

Best lecture on alpha fold 2’s architecture I’ve seen so glad it’s publicly available, currently doing biochem and Pharma at Cambridge and the closest I’ve come to anything like this is small talk in supervisions

[@JAM-ub3qy]

Good lecture, especially on clarifying pairing, pair alignment, and pair representation.

[@Jaeoh.woof765]

20:00 Evoformer

[@user-rk3mb7gq9p]

want the slides

[@maxbailey9164]

Bro giving the intro really said mmhmmgmdmgmffffmgntfh