logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

MP-NeRF: A massively parallel method for accelerating protein structure reconstruction from internal coordinates

delete2021-10-28
delete0
delete
OA
AI
E
Eric Alcaide
S
Stella Biderman
A
Amalio Telenti
M
M. Cyrus Maher *
DOI：10.1002/jcc.26768delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
The conversion of proteins between internal and cartesian coordinates is a limiting step in many pipelines, such as molecular dynamics simulations and machine learning models. This conversion is typically carried out by sequential or parallel applications of the Natural extension of Reference Frame (NeRF) algorithm. This work proposes a massively parallel NeRF implementation which, depending on the polymer length, achieves speedups between 400 and 1200x over the previous state-of-the-art. It accomplishes this by dividing the conversion into three main phases: parallel composition of the monomer backbone, assembly of backbone subunits, and parallel elongation of sidechains; and by batching these computations into a minimal number of efficient matrix operations. Special emphasis is placed on reusability and ease of use. We open source the code (available at ) and provide a corresponding python package.
Keywords:
algorithms
neural networks
polymer structure
protein science

Journal

Journal of Computational Chemistry cover
Journal of Computational Chemistry
IF:
4.8
Papers:
7.1K
Citations:
6.1W

Organization

No organization information available