Latent Sequence Generation of Steered Molecular Dynamics
Abstract
In this paper, we use a LSTM-VAE model framework in order to learn latent representations that are conditioned by potential energy through TorchMD, while being able to autoregressively generate sequences of a 10 deca-alanine system. While previous work have used generative deep learning methods for learning latent representations and predicting motion of molecules, this paper tackles with the latent representations for steered molecular dynamics (SMD).
Cite
Text
Cava et al. "Latent Sequence Generation of Steered Molecular Dynamics." ICLR 2023 Workshops: Physics4ML, 2023.Markdown
[Cava et al. "Latent Sequence Generation of Steered Molecular Dynamics." ICLR 2023 Workshops: Physics4ML, 2023.](https://mlanthology.org/iclrw/2023/cava2023iclrw-latent/)BibTeX
@inproceedings{cava2023iclrw-latent,
title = {{Latent Sequence Generation of Steered Molecular Dynamics}},
author = {Cava, John Kevin and Shukla, Ankita and Vant, John Wyatt and Karmaker, Shubhra Kanti and Turaga, Pavan K. and Maciejewski, Ross and Singharoy, Abhishek},
booktitle = {ICLR 2023 Workshops: Physics4ML},
year = {2023},
url = {https://mlanthology.org/iclrw/2023/cava2023iclrw-latent/}
}