EUVIMEDOpdag EUVIMED
Open access

Protein structure accuracy estimation using geometry‐complete perceptron networks

Alex Morehead iD, Jian Liu iD, Jianlin Cheng iD

Protein Science · 2024

DOI: 10.1002/pro.4932 ↗

At a glance

Journal article in Protein Science, 2024. Written by Alex Morehead and 2 co-authors. Institution: Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri, USA. Major MEDLINE topics: Neural Networks, Computer, Proteins. Cited 10 times so far (Crossref); 37 references. The full text is freely available in PubMed Central. Funded by: NIGMS NIH HHS, NIH HHS, National Science Foundation.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Estimating the accuracy of protein structural models is a critical task in protein bioinformatics. The need for robust methods in the estimation of protein model accuracy (EMA) is prevalent in the field of protein structure prediction, where computationally‐predicted structures need to be screened rapidly for the reliability of the positions predicted for each of their amino acid residues and their overall quality. Current methods proposed for EMA are either coupled tightly to existing protein structure prediction methods or evaluate protein structures without sufficiently leveraging the rich, geometric information available in such structures to guide accuracy estimation. In this work, we propose a geometric message passing neural network referred to as the geometry‐complete perceptron network for protein structure EMA (GCPNet‐EMA), where we demonstrate through rigorous computational benchmarks that GCPNet‐EMA's accuracy estimations are 47% faster and more than 10% (6%) more correlated with ground‐truth measures of per‐residue (per‐target) structural accuracy compared to baseline state‐of‐the‐art methods for tertiary (multimer) structure EMA including AlphaFold 2. The source code and data for GCPNet‐EMA are available on GitHub, and a public web server implementation is freely available.

Subjects

MeSH terms (MEDLINE)

Neural Networks, ComputerProteinsReproducibility of ResultsSoftwareAmino AcidsComputational Biology

Author keywords

3D graphsaccuracy estimationdeep learningprotein structure

Substances

ProteinsAmino Acids

Authors and institutions

  • Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri, USA.

ORCID profiles: Alex Morehead, Jian Liu, Jianlin Cheng

Funding

  • NIGMS NIH HHS
  • NIH HHS
  • National Science Foundation
  • National Institutes of Health
  • U.S. Department of Energy

Cite

APA

Morehead, A., Liu, J., & Cheng, J. (2024). Protein structure accuracy estimation using geometry‐complete perceptron networks. Protein Science. https://doi.org/10.1002/pro.4932

Vancouver

Morehead A, Liu J, Cheng J. Protein structure accuracy estimation using geometry‐complete perceptron networks. Protein Science. 2024. doi:10.1002/pro.4932

BibTeX
@article{Morehead2024,
  author = {Morehead, Alex and Liu, Jian and Cheng, Jianlin},
  title = {Protein structure accuracy estimation using geometry‐complete perceptron networks},
  journal = {Protein Science},
  year = {2024},
  doi = {10.1002/pro.4932}
}
Start for free →