Identification Exon Skipping Events From High-Throughput RNA Sequencing Data

The emergence of next-generation high-throughput RNA sequencing (RNA-Seq) provides tremendous opportunities for researchers to analyze alternative splicing on a genome-wide scale. However, accurate identification of alternative splicing events from RNA-Seq data has remained an unresolved challenge i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on nanobioscience 2015-07, Vol.14 (5), p.562-569
Main Authors: Bai, Yang, Ji, Shufan, Jiang, Qinghua, Wang, Yadong
Format: Magazinearticle
Language:English
Subjects:
alternative splicing
Alternative Splicing - genetics
Bioinformatics
Brain
Brain - metabolism
classifier
Computational Biology - methods
Databases, Genetic
Decision Trees
exon skipping
Exons - genetics
Feature extraction
feature selection
Forests
Gene sequencing
Genomics
High-Throughput Nucleotide Sequencing - methods
Human
Humans
MICROSTRUCTURES
Muscle, Skeletal - metabolism
Muscles
Nanobioscience
Nanostructure
Ribonucleic acids
RNA-Seq
ROC Curve
Sequence Analysis, RNA - methods
Silicon
Splicing
YTTRIUM OXIDE
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The emergence of next-generation high-throughput RNA sequencing (RNA-Seq) provides tremendous opportunities for researchers to analyze alternative splicing on a genome-wide scale. However, accurate identification of alternative splicing events from RNA-Seq data has remained an unresolved challenge in next-generation sequencing (NGS) studies. Identifying exon skipping (ES) events is an essential part in genome-wide alternative splicing event identification. In this paper, we propose a novel method ESFinder, a random forest classifier to identify ES events from RNA-Seq data. ESFinder conducts thorough studies on predicting features and figures out proper features according to their relevance for ES event identification. Experimental results on real human skeletal muscle and brain RNA-Seq data show that ESFinder could effectively predict ES events with high predictive accuracy. The codes of ESFinder are available at http://mlg.hit.edu.cn/ybai/ES/ESFinder.html.
ISSN:1536-1241
1558-2639
DOI:10.1109/TNB.2015.2419812