DeepLocRNA: an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning
Bioinformatics · 01.02.2024 · 40 (2)
DOI: 10.1093/bioinformatics/btae065 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 05.02.2024. Verfasst von Jun Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Bioinformatics Centre, Department of Biology, University of Copenhagen, København Ø 2100, Denmark. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council, Novo Nordisk Fonden, Danish National Research Foundation.
Abstract (Originalsprache)
Motivation Accurate prediction of RNA subcellular localization plays an important role in understanding cellular processes and functions. Although post-transcriptional processes are governed by trans-acting RNA binding proteins (RBPs) through interaction with cis-regulatory RNA motifs, current methods do not incorporate RBP-binding information. Results In this article, we propose DeepLocRNA, an interpretable deep-learning model that leverages a pre-trained multi-task RBP-binding prediction model to predict the subcellular localization of RNA molecules via fine-tuning. We constructed DeepLocRNA using a comprehensive dataset with variant RNA types and evaluated it on the held-out dataset. Our model achieved state-of-the-art performance in predicting RNA subcellular localization in mRNA and miRNA. It has also demonstrated great generalization capabilities, performing well on both human and mouse RNA. Additionally, a motif analysis was performed to enhance the interpretability of the model, highlighting signal factors that contributed to the predictions. The proposed model provides general and powerful prediction abilities for different RNA types and species, offering valuable insights into the localization patterns of RNA molecules and contributing to our understanding of cellular processes at the molecular level. A user-friendly web server is available at: https://biolib.com/KU/DeepLocRNA/.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Bioinformatics Centre, Department of Biology, University of Copenhagen, København Ø 2100, Denmark.
- Computational Health Center, Helmholtz Center Munich, Neuherberg 85764, Germany.
- Shenzhen People's Hospital, First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University, Shenzhen 518020, China.
- Center for Genomic Medicine, Rigshospitalet (Copenhagen University Hospital), Copenhagen 2100, Denmark.
- Section for Cognitive Systems, Department of Applied Mathematics and Computer Science, Technical University of Denmark, Kongens Lyngby 2800, Denmark.
ORCID-Profile: Jun Wang, Marc Horlacher, Lixin Cheng
Förderung
- China Scholarship Council
- Novo Nordisk Fonden
- Danish National Research Foundation
Zitieren
APA
Wang, J., Horlacher, M., Cheng, L., & Winther, O. (2024). DeepLocRNA: an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning. Bioinformatics, 40(2). https://doi.org/10.1093/bioinformatics/btae065
Vancouver
Wang J, Horlacher M, Cheng L, Winther O. DeepLocRNA: an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning. Bioinformatics. 2024;40(2). doi:10.1093/bioinformatics/btae065
BibTeX
@article{Wang2024,
author = {Wang, Jun and Horlacher, Marc and Cheng, Lixin and Winther, Ole},
title = {DeepLocRNA: an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {2},
doi = {10.1093/bioinformatics/btae065}
}
EUVIMED