Atom-level Protein Representation Learning Improves Protein Structure Prediction 事件

Atom-level Protein Representation Learning Improves Protein Structure Prediction arXiv:2605.22133v3 Announce Type: replace-cross Abstract: Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targets. Motivated by this, we study protein representations for predicting structures beyond conventional function annotation. We propose TriProRep, a structure-aware pretraining method that jointly models three aligned re