Mathematical and Machine Learning Approaches for Classification of Protein Secondary Structure Elements from Cα Coordinates

Creative Commons License

Sekmen A., Al Nasr K., Bilgin B., KOKU A. B., Jones C.

Biomolecules, vol.13, no.6, 2023 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 13 Issue: 6
  • Publication Date: 2023
  • Doi Number: 10.3390/biom13060923
  • Journal Name: Biomolecules
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, BIOSIS, CAB Abstracts, Chemical Abstracts Core, EMBASE, Food Science & Technology Abstracts, MEDLINE, Veterinary Science Database, Directory of Open Access Journals
  • Keywords: machine learning, mathematical modeling, protein secondary structure, protein structure modeling, protein trace, secondary structure identification
  • Middle East Technical University Affiliated: Yes

Abstract

Determining Secondary Structure Elements (SSEs) for any protein is crucial as an intermediate step for experimental tertiary structure determination. SSEs are identified using popular tools such as DSSP and STRIDE. These tools use atomic information to locate hydrogen bonds to identify SSEs. When some spatial atomic details are missing, locating SSEs becomes a hinder. To address the problem, when some atomic information is missing, three approaches for classifying SSE types using Cα atoms in protein chains were developed: (1) a mathematical approach, (2) a deep learning approach, and (3) an ensemble of five machine learning models. The proposed methods were compared against each other and with a state-of-the-art approach, PCASSO.