How negative sampling shapes the performance of transcription factor binding site prediction models
Bioinformatics · 03.02.2026 · 42 (2)
DOI: 10.1093/bioinformatics/btag048 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 27.01.2026. Verfasst von Natan Tourne und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Analysis and Mathematical Modelling, Ghent University, Ghent 9000, Belgium. Hauptthemen laut MEDLINE: Transcription Factors, Computational Biology. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Flemish Government under the "Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen" Programme, Flemish Government under the “Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen” Programme.
Abstract (Originalsprache)
Motivation Transcription factors (TFs) are key players in gene regulation and development, where they activate and repress gene expression through DNA binding. Predicting transcription factor binding sites (TFBSs) has long been an active area of research, with many deep learning methods developed to tackle this problem. These models are often trained on TF ChIP-seq data, which is generally seen as only providing positive samples. The choice of datasets and negative sampling techniques is a critical yet often overlooked aspect of this work. Results In this study, we investigate the impact of different negative sampling techniques on TFBS prediction performance. We create high-quality test datasets based on ChIP-seq and ATAC-seq data, where true negatives can be identified as positions that are accessible but not bound by the TF in question. We then train models using various negative sampling techniques, including genomic sampling, shuffling, dinucleotide shuffling, neighborhood sampling, and cell line specific sampling, simulating cases where matching ATAC-seq data is not available. Our results show that, generally, metrics calculated on training datasets give inflated performance scores. Of the tested techniques, genomic sampling of negatives based on similarity to the positives performed by far the best, although still not reaching the performance of baseline models trained on high-quality datasets. Models trained on dinucleotide shuffled negatives performed poorly, despite being a common practice in the field. Our findings highlight the importance of carefully selecting negative sampling techniques for TFBS prediction, as they can significantly impact model performance and the interpretation of results. Availability and implementation The code used in this study is available at https://github.com/NatanTourne/TFBS-negatives (DOI: 10.5281/zenodo.18007567).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Data Analysis and Mathematical Modelling, Ghent University, Ghent 9000, Belgium.
- Lab for Computational Biology, Integromics and Gene Regulation (CBIGR), Cancer Research Institute Ghent (CRIG), Ghent 9000, Belgium.
- Department of Biomedical Molecular Biology, Ghent University, Ghent 9000, Belgium.
- Department of Biomolecular Medicine, Ghent University, Ghent 9000, Belgium.
ORCID-Profile: Natan Tourne, Gaetan De Waele, Vanessa Vermeirssen, Willem Waegeman
Förderung
- Flemish Government under the "Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen" Programme
- Flemish Government under the “Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen” Programme
Zitieren
APA
Tourne, N., De Waele, G., Vermeirssen, V., & Waegeman, W. (2026). How negative sampling shapes the performance of transcription factor binding site prediction models. Bioinformatics, 42(2). https://doi.org/10.1093/bioinformatics/btag048
Vancouver
Tourne N, De Waele G, Vermeirssen V, Waegeman W. How negative sampling shapes the performance of transcription factor binding site prediction models. Bioinformatics. 2026;42(2). doi:10.1093/bioinformatics/btag048
BibTeX
@article{Tourne2026,
author = {Tourne, Natan and De Waele, Gaetan and Vermeirssen, Vanessa and Waegeman, Willem},
title = {How negative sampling shapes the performance of transcription factor binding site prediction models},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {2},
doi = {10.1093/bioinformatics/btag048}
}
EUVIMED