EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Amino acid sequence assignment from single molecule peptide sequencing data using a two-stage classifier

Matthew Beauregard Smith iD, Zack Booth Simpson, Edward M Marcotte iD

PLOS Computational Biology · 2023

DOI: 10.1371/journal.pcbi.1011157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2023. Verfasst von Matthew Beauregard Smith und 2 weiteren Autor:innen. Beteiligte Einrichtung: Oden Institute, The University of Texas at Austin, Austin, Texas, United States of America. Hauptthemen laut MEDLINE: Algorithms, Peptides. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NICHD NIH HHS, Computational Sciences, Engineering, and Mathematics graduate program fellowship from the Oden Institute at the University of Texas at Austin.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a machine learning-based interpretive framework ( whatprot ) for analyzing single molecule protein sequencing data produced by fluorosequencing, a recently developed proteomics technology that determines sparse amino acid sequences for many individual peptide molecules in a highly parallelized fashion. Whatprot uses Hidden Markov Models (HMMs) to represent the states of each peptide undergoing the various chemical processes during fluorosequencing, and applies these in a Bayesian classifier, in combination with pre-filtering by a k-Nearest Neighbors (kNN) classifier trained on large volumes of simulated fluorosequencing data. We have found that by combining the HMM based Bayesian classifier with the kNN pre-filter, we are able to retain the benefits of both, achieving both tractable runtimes and acceptable precision and recall for identifying peptides and their parent proteins from complex mixtures, outperforming the capabilities of either classifier on its own. Whatprot’s hybrid kNN-HMM approach enables the efficient interpretation of fluorosequencing data using a full proteome reference database and should now also enable improved sequencing error rate estimates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsPeptidesAmino Acid SequenceBayes TheoremProteinsMarkov Chains

Substanzen

PeptidesProteins

Autor:innen und Institutionen

  • Oden Institute, The University of Texas at Austin, Austin, Texas, United States of America.
  • Erisyon Inc., Austin, Texas, United States of America.
  • Department of Molecular Biosciences, The University of Texas at Austin, Austin, Texas, United States of America.

ORCID-Profile: Matthew Beauregard Smith, Edward M Marcotte

Förderung

  • NIGMS NIH HHS
  • NICHD NIH HHS
  • Computational Sciences, Engineering, and Mathematics graduate program fellowship from the Oden Institute at the University of Texas at Austin
  • Erisyon Inc.
  • National Institute of General Medical Sciences
  • Eunice Kennedy Shriver National Institute of Child Health and Human Development
  • Welch Foundation

Zitieren

APA

Smith, M. B., Simpson, Z. B., & Marcotte, E. M. (2023). Amino acid sequence assignment from single molecule peptide sequencing data using a two-stage classifier. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1011157

Vancouver

Smith MB, Simpson ZB, Marcotte EM. Amino acid sequence assignment from single molecule peptide sequencing data using a two-stage classifier. PLOS Computational Biology. 2023. doi:10.1371/journal.pcbi.1011157

BibTeX
@article{Smith2023,
  author = {Smith, Matthew Beauregard and Simpson, Zack Booth and Marcotte, Edward M},
  title = {Amino acid sequence assignment from single molecule peptide sequencing data using a two-stage classifier},
  journal = {PLOS Computational Biology},
  year = {2023},
  doi = {10.1371/journal.pcbi.1011157}
}
Kostenlos starten →