TY - JOUR

T1 - DeepLocRNA

T2 - an interpretable deep learning model for predicting RNA subcellular localization with domain-specific transfer-learning

AU - Wang, Jun

AU - Horlacher, Marc

AU - Cheng, Lixin

AU - Winther, Ole

N1 - Publisher Copyright: © The Author(s) 2024. Published by Oxford University Press.

PY - 2024

Y1 - 2024

N2 - 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/.

AB - 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/.

U2 - 10.1093/bioinformatics/btae065

DO - 10.1093/bioinformatics/btae065

M3 - Journal article

C2 - 38317052

AN - SCOPUS:85185964229

VL - 40

JO - Bioinformatics (Online)

JF - Bioinformatics (Online)

SN - 1367-4811

IS - 2

M1 - btae065

ER -