Back to search

Virginia Tech

Machine Learning Methods for Protein Model Quality Estimation

Abstract

dc:description.abstract

Protein model quality estimation helps at various stages of the computational prediction of protein three-dimensional (3D) structures, which are essential for numerous biological processes. Existing quality estimation methods for monomeric and multimeric protein models fall short of leveraging the latest technological breakthrough in deep learning that has recently revolutionized protein structure prediction, particularly in harnessing the power of a symmetry-aware network informed by the Protein Language Model (pLM) and the integration of important evolutionary and structural information, limiting their ability to improve quality estimation performance. Moreover, despite the significant progress made by AlphaFold2 in predicting highly accurate protein models, existing methods fall short of the estimation of high-resolution protein model quality and its application in improving the accuracy of predicted protein models. Therefore, the objectives of my research include 1) the development of quality estimation methods for monomeric protein models by learning efficient structural representation with the application of the latest deep learning architectures; 2) the application of our quality estimation methods to improve the structural accuracy of computationally generated protein models; and 3) the development of multimeric protein model quality estimation methods with deep graph learning of protein-protein interface. The benefits of achieving these objectives are two-fold for the broader scientific community. Firstly, it will enable the evaluation of protein models without the presence of experimentally determined protein structures. Secondly, our protein model quality estimation methods can potentially guide the overall structure prediction process and improve the structural accuracy of predicted models.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Computer Science and Applications
Department dc:contributor.department
Computer Science and Applications
Grantor dc:publisher
Virginia Tech
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Shuvo, Md Hossain
Chair dc:contributor.committeechair
  • Bhattacharya, Debswapna
Committee members dc:contributor.committeemember
  • Zhang, Liqing
  • Heath, Lenwood S.
  • Onufriev, Alexey
  • Emrich, Scott

Subjects

dc:subject × 4

Rights

dc:rights
Statement dc:rights
  • In Copyright
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
vt_gsexam:39314

Chain of custody

source
Harvested from
Virginia Tech
Base URL
vtechworks.lib.vt.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Shuvo, Md Hossain. Machine Learning Methods for Protein Model Quality Estimation. doctoral thesis, Virginia Tech, 2023. https://hdl.handle.net/10919/117278