Machine Learning Shows Torsion Angle Preferences In Left-Handed And Right-Handed Quadruplex DNAs
Document Type
Article
Publication Date
12-20-2022
Published In
Biophysical Journal
Abstract
Left-handed G quadruplexes (LHG4) have been recently discovered as a new class of G quadruplexes. The biological functions of LHG4s are still unknown, but they share a striking resemblance to Z-DNA in their helicity and jagged phosphate backbone. To further understand structural features of the LHG4s that define their left handedness, we have employed human-interpretable machine-learning methods to classify right- and left-handed G4s purely based on torsional angle analysis. Our results reveal the importance of the α, β, δ, and χ angles in left-handed structuring across both Z-DNAs and LHG4s. Our analysis may serve as the first step to understanding the conditions of formation for LHG4s and their potential biological relevance.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Kevin S. Li , '22; Liliya A. Yatsunyk; and S. Neidle.
(2022).
"Machine Learning Shows Torsion Angle Preferences In Left-Handed And Right-Handed Quadruplex DNAs".
Biophysical Journal.
Volume 121,
Issue 24.
4874-4881.
DOI: 10.1016/j.bpj.2022.08.021
https://works.swarthmore.edu/fac-chemistry/291