EUVIMEDEUVIMED entdecken
Crossref

DeepPD: A Deep Learning Method for Predicting Peptide Detectability Based on Multi-feature Representation and Information Bottleneck

Fenglin Li, Yannan Bin, Jianping Zhao, Chunhou Zheng

Interdisciplinary Sciences: Computational Life Sciences · 2025

DOI: 10.1007/s12539-024-00665-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Interdisciplinary Sciences: Computational Life Sciences, 2025. Verfasst von Fenglin Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and System Science, Xinjiang University, Urumqi, 830046, China. Hauptthemen laut MEDLINE: Deep Learning, Peptides, Proteomics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: the open fund of Information Materials and Intelligent Sensing Laboratory of Anhui Province, the National Natural Science Foundation of China, the grant of National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Peptide detectability measures the relationship between the protein composition and abundance in the sample and the peptides identified during the analytical procedure. This relationship has significant implications for the fundamental tasks of proteomics. Existing methods primarily rely on a single type of feature representation, which limits their ability to capture the intricate and diverse characteristics of peptides. In response to this limitation, we introduce DeepPD, an innovative deep learning framework incorporating multi-feature representation and the information bottleneck principle (IBP) to predict peptide detectability. DeepPD extracts semantic information from peptides using evolutionary scale modeling 2 (ESM-2) and integrates sequence and evolutionary information to construct the feature space collaboratively. The IBP effectively guides the feature learning process, minimizing redundancy in the feature space. Experimental results across various datasets demonstrate that DeepPD outperforms state-of-the-art methods. Furthermore, we demonstrate that DeepPD exhibits competitive generalization and transfer learning capabilities across diverse datasets and species. In conclusion, DeepPD emerges as the most effective method for predicting peptide detectability, showcasing its potential applicability to other protein sequence prediction tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPeptidesProteomicsComputational BiologyAlgorithmsHumansDatabases, Protein

Stichwörter der Autor:innen

Deep learningInformation bottleneckMulti-feature representationPeptide detectabilityProtein language model

Substanzen

Peptides

Autor:innen und Institutionen

  • College of Mathematics and System Science, Xinjiang University, Urumqi, 830046, China.
  • Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Information Materials and Intelligent Sensing Laboratory of Anhui Province, and School of Artificial Intelligence, Anhui University…
  • College of Mathematics and System Science, Xinjiang University, Urumqi, 830046, China. zhaojianping@126.com.
  • College of Mathematics and System Science, Xinjiang University, Urumqi, 830046, China. zhengch99@126.com.

Förderung

  • the open fund of Information Materials and Intelligent Sensing Laboratory of Anhui Province
  • the National Natural Science Foundation of China
  • the grant of National Key R&D Program of China
  • the Autonomous Region "Tianshan Talents" Young Top Talents-Young Scientific and Technological Innovation Talents
  • the Autonomous Region “Tianshan Talents” Young Top Talents-Young Scientific and Technological Innovation Talents

Zitieren

APA

Li, F., Bin, Y., Zhao, J., & Zheng, C. (2025). DeepPD: A Deep Learning Method for Predicting Peptide Detectability Based on Multi-feature Representation and Information Bottleneck. Interdisciplinary Sciences: Computational Life Sciences. https://doi.org/10.1007/s12539-024-00665-4

Vancouver

Li F, Bin Y, Zhao J, Zheng C. DeepPD: A Deep Learning Method for Predicting Peptide Detectability Based on Multi-feature Representation and Information Bottleneck. Interdisciplinary Sciences: Computational Life Sciences. 2025. doi:10.1007/s12539-024-00665-4

BibTeX
@article{Li2025,
  author = {Li, Fenglin and Bin, Yannan and Zhao, Jianping and Zheng, Chunhou},
  title = {DeepPD: A Deep Learning Method for Predicting Peptide Detectability Based on Multi-feature Representation and Information Bottleneck},
  journal = {Interdisciplinary Sciences: Computational Life Sciences},
  year = {2025},
  doi = {10.1007/s12539-024-00665-4}
}
Kostenlos starten →