BertSNR: an interpretable deep learning framework for single-nucleotide resolution identification of transcription factor binding sites based on DNA language model
Bioinformatics · 2024
DOI: 10.1093/bioinformatics/btae461 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Hanyu Luo und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China. Hauptthemen laut MEDLINE: Deep Learning, Transcription Factors. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Transcription factors are pivotal in the regulation of gene expression, and accurate identification of transcription factor binding sites (TFBSs) at high resolution is crucial for understanding the mechanisms underlying gene regulation. The task of identifying TFBSs from DNA sequences is a significant challenge in the field of computational biology today. To address this challenge, a variety of computational approaches have been developed. However, these methods face limitations in their ability to achieve high-resolution identification and often lack interpretability. Results We propose BertSNR, an interpretable deep learning framework for identifying TFBSs at single-nucleotide resolution. BertSNR integrates sequence-level and token-level information by multi-task learning based on pre-trained DNA language models. Benchmarking comparisons show that our BertSNR outperforms the existing state-of-the-art methods in TFBS predictions. Importantly, we enhanced the interpretability of the model through attentional weight visualization and motif analysis, and discovered the subtle relationship between attention weight and motif. Moreover, BertSNR effectively identifies TFBSs in promoter regions, facilitating the study of intricate gene regulation. Availability and implementation The BertSNR source code can be found at https://github.com/lhy0322/BertSNR.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China.
- School of Computer Science, University of South China, Hengyang, Hunan 421001, China.
- Department of Health Outcome and Biomedical Informatics, University of Florida, Gainesville, FL 32611, United States.
- Center for Artificial Intelligence in Drug Discovery, School of Medicine, Case Western Reserve University, Cleveland, OH 44106, United States.
ORCID-Profile: Min Zeng, Pingjian Ding, Min Li
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Luo, H., Tang, L., Zeng, M., Yin, R., Ding, P., Luo, L., & Li, M. (2024). BertSNR: an interpretable deep learning framework for single-nucleotide resolution identification of transcription factor binding sites based on DNA language model. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae461
Vancouver
Luo H, Tang L, Zeng M, Yin R, Ding P, Luo L, et al. BertSNR: an interpretable deep learning framework for single-nucleotide resolution identification of transcription factor binding sites based on DNA language model. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae461
BibTeX
@article{Luo2024,
author = {Luo, Hanyu and Tang, Li and Zeng, Min and Yin, Rui and Ding, Pingjian and Luo, Lingyun and Li, Min},
title = {BertSNR: an interpretable deep learning framework for single-nucleotide resolution identification of transcription factor binding sites based on DNA language model},
journal = {Bioinformatics},
year = {2024},
doi = {10.1093/bioinformatics/btae461}
}
EUVIMED