Generation of peptide detectability datasets from single DIA experiment for prediction model fine-tuning
Bioinformatics Advances · 07.01.2026 · 6 (1)
DOI: 10.1093/bioadv/vbag180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 25.06.2026. Verfasst von Léo Schneider und 4 weiteren Autor:innen. Beteiligte Einrichtung: Université Claude Bernard Lyon1, ISA, UMR5280, CNRS, ISA, Villerbanne, Rhone-Alpes 69100, France. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: French National Research.
Abstract (Originalsprache)
Motivation Accurate prediction of peptide detectability in mass spectrometry-based proteomics is critical for improving both protein identification and quantification. Current models generally estimate detectability from amino acid sequences; however, peptide detectability is influenced by the instruments, acquisition methods, and experimental conditions, limiting the applicability of sequence-based models. State-of-the-art approaches mitigate this issue by fine-tuning models for each experimental setup, yet this strategy demands extensive training datasets—often comprising up to 300 000 peptides—incurring substantial experimental and computational costs. Results In this study, we present a complementary approach for generating peptide detectability datasets directly from a single DIA experiment. These datasets enable fine-tuning of prediction models with minimal raw data, while improving adaptation to specific experimental conditions. This strategy substantially reduces both the data and cost requirements typically associated with model training. Furthermore, we show that filtering search libraries based on predicted detectability increases peptide identification rates and decreases computational time. Availability and implementation Code is available on https://github.com/leoschn/Detectability. Data are available via ProteomeXchange with identifier https://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD076276PXD076276.
Autor:innen und Institutionen
- Université Claude Bernard Lyon1, ISA, UMR5280, CNRS, ISA, Villerbanne, Rhone-Alpes 69100, France.
- Ecole Centrale de Lyon, CNRS, INSA Lyon, Universite Claude Bernard Lyon 1, Université Lumière Lyon 2, UMR5205, LIRIS, Ecully, Rhone-Alpes 69130, France.
ORCID-Profile: Léo Schneider, Julie Flecheux, Zied Bouyahia, Stéphane Derrode, Jérome Lemoine
Förderung
- French National Research
Zitieren
APA
Schneider, L., Flecheux, J., Bouyahia, Z., Derrode, S., & Lemoine, J. (2026). Generation of peptide detectability datasets from single DIA experiment for prediction model fine-tuning. Bioinformatics Advances, 6(1). https://doi.org/10.1093/bioadv/vbag180
Vancouver
Schneider L, Flecheux J, Bouyahia Z, Derrode S, Lemoine J. Generation of peptide detectability datasets from single DIA experiment for prediction model fine-tuning. Bioinformatics Advances. 2026;6(1). doi:10.1093/bioadv/vbag180
BibTeX
@article{Schneider2026,
author = {Schneider, Léo and Flecheux, Julie and Bouyahia, Zied and Derrode, Stéphane and Lemoine, Jérome},
title = {Generation of peptide detectability datasets from single DIA experiment for prediction model fine-tuning},
journal = {Bioinformatics Advances},
year = {2026},
volume = {6},
number = {1},
doi = {10.1093/bioadv/vbag180}
}
EUVIMED