LGBMNov 23, 2018

TorchProteinLibrary: A computationally efficient, differentiable representation of protein structure

arXiv:1812.01108v11 citationsHas Code
Originality Synthesis-oriented
AI Analysis

This work provides a tool for researchers in computational biology to accelerate the development of end-to-end protein structure and dynamics models, though it is incremental as it builds on existing representations.

The authors tackled the need for efficient computational primitives in new protein structure prediction methods by developing TorchProteinLibrary, a differentiable library that maps dihedral-angle representations to atomic Cartesian coordinates, achieving computational efficiency for large-scale investigations.

Predicting the structure of a protein from its sequence is a cornerstone task of molecular biology. Established methods in the field, such as homology modeling and fragment assembly, appeared to have reached their limit. However, this year saw the emergence of promising new approaches: end-to-end protein structure and dynamics models, as well as reinforcement learning applied to protein folding. For these approaches to be investigated on a larger scale, an efficient implementation of their key computational primitives is required. In this paper we present a library of differentiable mappings from two standard dihedral-angle representations of protein structure (full-atom representation "$φ,ψ,ω,χ$" and backbone-only representation "$φ,ψ,ω$") to atomic Cartesian coordinates. The source code and documentation can be found at https://github.com/lupoglaz/TorchProteinLibrary.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes