Scaling Biomolecular Simulations with Equivariant Models
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
Key pointsA framework for large-scale biomolecular simulation using equivariant deep learning.
01
Equivariant network scaling: Achieves high accuracy through equivariant deep learning that respects molecular symmetries.
02
44M atom HIV capsid: Simulated a complete, all-atom, explicitly solvated HIV capsid structure of 44 million atoms.
03
Nanosecond-scale stable dynamics: Performs nanoseconds-long stable simulations of protein dynamics - much longer than prior ML-MD simulations.
04
Perlmutter deployment: Scales to the Perlmutter supercomputer, demonstrating ML-accelerated molecular dynamics at HPC scale.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack