EUVIMEDEUVIMED entdecken
Crossref

Peptide classification from statistical analysis of nanopore sensing experiments

Julian Hoßbach iD, Samuel Tovey iD, Tobias Ensslen iD, Jan C Behrends iD, Christian Holm iD

The Journal of Chemical Physics · 28.02.2025 · 162 (8)

DOI: 10.1063/5.0250399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 25.02.2025. Verfasst von Julian Hoßbach und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany. Hauptthemen laut MEDLINE: Nanopores, Peptides. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Bundesministerium für Bildung und Forschung, Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Peptide classification using nanopore-based devices promises to be a breakthrough method in basic research, diagnostics, and analytics. However, the measured blockage currents suffer from a low signal-to-noise ratio and a high information density that has hitherto not been fully deciphered. Some simple machine learning approaches using average current blockade depths and dwell-times have been investigated to improve this situation. In this work, a comprehensive statistical analysis of nanopore current signals is performed and demonstrated to be sufficient for classifying up to 42 peptides with over 70% accuracy. Two sets of features, the statistical moments and the catch22 set, are compared both in their representations and after training small classifier neural networks. We demonstrate that complex features of the events, captured in both the catch22 set and the central moments, are key to classifying peptides with otherwise similar mean currents. These results highlight the efficacy of purely statistical analysis of nanopore data and suggest a path forward for more sophisticated classification techniques.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NanoporesPeptidesMachine LearningNeural Networks, ComputerSignal-To-Noise Ratio

Substanzen

Peptides

Autor:innen und Institutionen

  • Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany.
  • Laboratory for Membrane Physiology and Technology, Department of Physiology, Faculty of Medicine, University of Freiburg, 79104 Freiburg, Germany.

ORCID-Profile: Julian Hoßbach, Samuel Tovey, Tobias Ensslen, Jan C Behrends, Christian Holm

Förderung

  • Bundesministerium für Bildung und Forschung
  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Hoßbach, J., Tovey, S., Ensslen, T., Behrends, J. C., & Holm, C. (2025). Peptide classification from statistical analysis of nanopore sensing experiments. The Journal of Chemical Physics, 162(8). https://doi.org/10.1063/5.0250399

Vancouver

Hoßbach J, Tovey S, Ensslen T, Behrends JC, Holm C. Peptide classification from statistical analysis of nanopore sensing experiments. The Journal of Chemical Physics. 2025;162(8). doi:10.1063/5.0250399

BibTeX
@article{Hobach2025,
  author = {Hoßbach, Julian and Tovey, Samuel and Ensslen, Tobias and Behrends, Jan C and Holm, Christian},
  title = {Peptide classification from statistical analysis of nanopore sensing experiments},
  journal = {The Journal of Chemical Physics},
  year = {2025},
  volume = {162},
  number = {8},
  doi = {10.1063/5.0250399}
}
Kostenlos starten →