Rxivist logo

MP-NeRF: A Massively Parallel Method for Accelerating Protein Structure Reconstruction from Internal Coordinates

By Eric Alcaide, Stella Biderman, Amalio Telenti, M. Cyrus Maher

Posted 09 Jun 2021
bioRxiv DOI: 10.1101/2021.06.08.446214

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 400-1000x over the previous state-of-the-art NeRF implementation. It accomplishes this by dividing the conversion into three main phases: a parallel composition of the monomer backbone, the assembly of backbone subunits, and the parallel elongation of sidechains; and by batching computations into a minimal number of efficient matrix operations. Special emphasis is placed on reusability and ease of use within diverse pipelines. We open source the code (available at https://github.com/EleutherAI/mp_nerf) and provide a corresponding python package.

Download data

  • Downloaded 500 times
  • Download rankings, all-time:
    • Site-wide: 76,080
    • In molecular biology: 2,194
  • Year to date:
    • Site-wide: 12,615
  • Since beginning of last month:
    • Site-wide: 18,720

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide