Learning Correlations between Internal Coordinates to improve 3D Cartesian Coordinates for Proteins

We consider a generic representation problem of internal coordinates (bond lengths, valence angles, and dihedral angles) and their transformation to 3-dimensional Cartesian coordinates of a biomolecule. We show that the internal-to-Cartesian process relies on correctly predicting chemically subtle c...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Li, Jie, Zhang, Oufan, Lee, Seokyoung, Namini, Ashley, Zi Hao Liu, João Miguel Correia Teixeira, man-Kay, Julie D, Head-Gordon, Teresa
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.05.2022
Subjects
Accuracy
Algorithms
Backbone
Biomolecules
Cartesian coordinates
Correlation
Lipids
Machine learning
Proteins
Representations
Residues
Online AccessGet full text

Cover

More Information
Summary:We consider a generic representation problem of internal coordinates (bond lengths, valence angles, and dihedral angles) and their transformation to 3-dimensional Cartesian coordinates of a biomolecule. We show that the internal-to-Cartesian process relies on correctly predicting chemically subtle correlations among the internal coordinates themselves, and learning these correlations increases the fidelity of the Cartesian representation. This general problem has been solved with machine learning for proteins, but with appropriately formulated data is extensible to any type of chain biomolecule including RNA, DNA, and lipids. We show that the internal-to-Cartesian process relies on correctly predicting chemically subtle correlations among the internal coordinates themselves, and learning these correlations increases the fidelity of the Cartesian representation. We developed a machine learning algorithm, Int2Cart, to predict bond lengths and bond angles from backbone torsion angles and residue types of a protein, and allows reconstruction of protein structures better than using fixed bond lengths and bond angles, or a static library method that relies on backbone torsion angles and residue types on a single residue. The Int2Cart algorithm has been implemented as an individual python package at https://github.com/THGLab/int2cart.
ISSN:2331-8422