This is copy from openfold, commit id: bb3f51
Openfold is a great work. We try to reuse it when building models. However, A few modifications has been made for our protenix project.
- In protenix/openfold_local/model/primitives.py, we add a custom
Layernormimplementation, it accelerate protenix about 30%-50% during different training stages
If you use our work, please also cite Openfold:
@article {Ahdritz2022.11.20.517210,
author = {Ahdritz, Gustaf and Bouatta, Nazim and Floristean, Christina and Kadyan, Sachin and Xia, Qinghui and Gerecke, William and O{\textquoteright}Donnell, Timothy J and Berenberg, Daniel and Fisk, Ian and Zanichelli, Niccolò and Zhang, Bo and Nowaczynski, Arkadiusz and Wang, Bei and Stepniewska-Dziubinska, Marta M and Zhang, Shang and Ojewole, Adegoke and Guney, Murat Efe and Biderman, Stella and Watkins, Andrew M and Ra, Stephen and Lorenzo, Pablo Ribalta and Nivon, Lucas and Weitzner, Brian and Ban, Yih-En Andrew and Sorger, Peter K and Mostaque, Emad and Zhang, Zhao and Bonneau, Richard and AlQuraishi, Mohammed},
title = {{O}pen{F}old: {R}etraining {A}lpha{F}old2 yields new insights into its learning mechanisms and capacity for generalization},
elocation-id = {2022.11.20.517210},
year = {2022},
doi = {10.1101/2022.11.20.517210},
publisher = {Cold Spring Harbor Laboratory},
URL = {https://www.biorxiv.org/content/10.1101/2022.11.20.517210},
eprint = {https://www.biorxiv.org/content/early/2022/11/22/2022.11.20.517210.full.pdf},
journal = {bioRxiv}
}