Cargando…
JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites
MOTIVATION: Circular RNA (circRNA) is a novel class of long non-coding RNAs that have been broadly discovered in the eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backspliced to an upstream acceptor site. These circRNA sequences a...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8336595/ https://www.ncbi.nlm.nih.gov/pubmed/34252942 http://dx.doi.org/10.1093/bioinformatics/btab288 |
_version_ | 1783733352045477888 |
---|---|
author | Jiang, Jyun-Yu Ju, Chelsea J -T Hao, Junheng Chen, Muhao Wang, Wei |
author_facet | Jiang, Jyun-Yu Ju, Chelsea J -T Hao, Junheng Chen, Muhao Wang, Wei |
author_sort | Jiang, Jyun-Yu |
collection | PubMed |
description | MOTIVATION: Circular RNA (circRNA) is a novel class of long non-coding RNAs that have been broadly discovered in the eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backspliced to an upstream acceptor site. These circRNA sequences are conserved across species. More importantly, rising evidence suggests their vital roles in gene regulation and association with diseases. As the fundamental effort toward elucidating their functions and mechanisms, several computational methods have been proposed to predict the circular structure from the primary sequence. Recently, advanced computational methods leverage deep learning to capture the relevant patterns from RNA sequences and model their interactions to facilitate the prediction. However, these methods fail to fully explore positional information of splice junctions and their deep interaction. RESULTS: We present a robust end-to-end framework, Junction Encoder with Deep Interaction (JEDI), for circRNA prediction using only nucleotide sequences. JEDI first leverages the attention mechanism to encode each junction site based on deep bidirectional recurrent neural networks and then presents the novel cross-attention layer to model deep interaction among these sites for backsplicing. Finally, JEDI can not only predict circRNAs but also interpret relationships among splice sites to discover backsplicing hotspots within a gene region. Experiments demonstrate JEDI significantly outperforms state-of-the-art approaches in circRNA prediction on both isoform level and gene level. Moreover, JEDI also shows promising results on zero-shot backsplicing discovery, where none of the existing approaches can achieve. AVAILABILITY AND IMPLEMENTATION: The implementation of our framework is available at https://github.com/hallogameboy/JEDI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. |
format | Online Article Text |
id | pubmed-8336595 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-83365952021-08-09 JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites Jiang, Jyun-Yu Ju, Chelsea J -T Hao, Junheng Chen, Muhao Wang, Wei Bioinformatics Regulatory and Functional Genomics MOTIVATION: Circular RNA (circRNA) is a novel class of long non-coding RNAs that have been broadly discovered in the eukaryotic transcriptome. The circular structure arises from a non-canonical splicing process, where the donor site backspliced to an upstream acceptor site. These circRNA sequences are conserved across species. More importantly, rising evidence suggests their vital roles in gene regulation and association with diseases. As the fundamental effort toward elucidating their functions and mechanisms, several computational methods have been proposed to predict the circular structure from the primary sequence. Recently, advanced computational methods leverage deep learning to capture the relevant patterns from RNA sequences and model their interactions to facilitate the prediction. However, these methods fail to fully explore positional information of splice junctions and their deep interaction. RESULTS: We present a robust end-to-end framework, Junction Encoder with Deep Interaction (JEDI), for circRNA prediction using only nucleotide sequences. JEDI first leverages the attention mechanism to encode each junction site based on deep bidirectional recurrent neural networks and then presents the novel cross-attention layer to model deep interaction among these sites for backsplicing. Finally, JEDI can not only predict circRNAs but also interpret relationships among splice sites to discover backsplicing hotspots within a gene region. Experiments demonstrate JEDI significantly outperforms state-of-the-art approaches in circRNA prediction on both isoform level and gene level. Moreover, JEDI also shows promising results on zero-shot backsplicing discovery, where none of the existing approaches can achieve. AVAILABILITY AND IMPLEMENTATION: The implementation of our framework is available at https://github.com/hallogameboy/JEDI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2021-07-12 /pmc/articles/PMC8336595/ /pubmed/34252942 http://dx.doi.org/10.1093/bioinformatics/btab288 Text en © The Author(s) 2021. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Regulatory and Functional Genomics Jiang, Jyun-Yu Ju, Chelsea J -T Hao, Junheng Chen, Muhao Wang, Wei JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title | JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title_full | JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title_fullStr | JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title_full_unstemmed | JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title_short | JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites |
title_sort | jedi: circular rna prediction based on junction encoders and deep interaction among splice sites |
topic | Regulatory and Functional Genomics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8336595/ https://www.ncbi.nlm.nih.gov/pubmed/34252942 http://dx.doi.org/10.1093/bioinformatics/btab288 |
work_keys_str_mv | AT jiangjyunyu jedicircularrnapredictionbasedonjunctionencodersanddeepinteractionamongsplicesites AT juchelseajt jedicircularrnapredictionbasedonjunctionencodersanddeepinteractionamongsplicesites AT haojunheng jedicircularrnapredictionbasedonjunctionencodersanddeepinteractionamongsplicesites AT chenmuhao jedicircularrnapredictionbasedonjunctionencodersanddeepinteractionamongsplicesites AT wangwei jedicircularrnapredictionbasedonjunctionencodersanddeepinteractionamongsplicesites |