Corpus ID: 11718046

Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice Junctions

@inproceedings{Lee2015BoostedCR,
  title={Boosted Categorical Restricted Boltzmann Machine for Computational Prediction of Splice Junctions},
  author={Taehoon Lee and Sungroh Yoon},
  booktitle={ICML},
  year={2015}
}
Splicing refers to the elimination of noncoding regions in transcribed pre-messenger ribonucleic acid (RNA). Discovering splice sites is an important machine learning task that helps us not only to identify the basic units of genetic heredity but also to understand how different proteins are produced. Existing methods for splicing prediction have produced promising results, but often show limited robustness and accuracy. In this paper, we propose a deep belief network-basedmethodology for… Expand
Discerning novel splice junctions derived from RNA-seq alignment: a deep learning approach
TLDR
A deep learning based splice junction sequence classifier, named DeepSplice, which employs convolutional neural networks to classify candidate splice junctions and outperforms state-of-the-art methods for splice site classification when applied to the popular benchmark dataset HS3D. Expand
SpliceRover: interpretable convolutional neural networks for improved splice site prediction
TLDR
This paper presents SpliceRover, a predictive deep learning approach that outperforms the state‐of‐the‐art in splice site prediction, and introduces an approach to visualize the biologically relevant information learnt that is able to recover features known to be important for splicing site prediction. Expand
DNA-Level Splice Junction Prediction using Deep Recurrent Neural Networks
TLDR
Deep recurrent neural networks are exploited to model DNA sequences and to detect splice junctions thereon and the proposed approach significantly outperforms not only conventional machine learning-based methods but also a recent state-of-the-art deep belief network-based technique in terms of prediction accuracy. Expand
DeepSplice: Deep classification of novel splice junctions revealed by RNA-seq
  • Yi Zhang, Xinan Liu, J. MacLeod, Jinze Liu
  • Biology, Computer Science
  • 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
  • 2016
TLDR
Deep convolutional neural networks are employed for a novel splice junction classification tool named DeepSplice that outperforms state-of-the-art methods for predicting splice sites, shows high computational efficiency and can be applied to self-defined training data by users. Expand
SpliceVec: distributed feature representations for splice junction prediction
TLDR
Distributed feature representation, SpliceVec, is introduced to avoid explicit and biased feature extraction generally adopted for feature extraction in natural language processing tasks and is consistent in its performance even with reduced dataset and class-imbalanced dataset. Expand
SpliceVec: Distributed feature representations for splice junction prediction
TLDR
Distributed feature representation, SpliceVec, is introduced to avoid explicit and biased feature extraction generally adopted for feature extraction in natural language processing tasks and is consistent in its performance even with reduced dataset and class-imbalanced dataset. Expand
SpliceFinder: ab initio prediction of splice sites using convolutional neural network
TLDR
A new ab initio splice site prediction tool, SpliceFinder, which generates less false positives and can detect non-canonical splice sites, and is transferable to other species without retraining. Expand
RNA Splice Sites Classification Using Convolutional Neural Network Models
RNA splicing refers to the elimination of noncoding region on transcribed pre-messenger ribonucleic acid (RNA). Identifying splicing site is an essential step which can be used to gain novel insightsExpand
Predicting the effect of variants on splicing using Convolutional Neural Networks
TLDR
A framework to elaborate on the utility of CNNs to assess the effect of splice variants on the identification of potential disease-causing variants that disrupt the RNA splicing process and results support that the proposed framework could be applied in future genetic studies to identify disease causing loci involving the splicing mechanism. Expand
Splice2Deep: An ensemble of deep convolutional neural networks for improved splice site prediction in genomic DNA
TLDR
The results of this study demonstrated that Splice2Deep both achieved a considerably reduced error rate compared to other state-of-the-art models and the ability to accurately recognize SS in other organisms for which the model was not trained, enabling annotation of poorly studied or newly sequenced genomes. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
Deep learning of the tissue-regulated splicing code
TLDR
The deep architecture surpasses the performance of the previous Bayesian method for predicting AS patterns and demonstrates that deep architectures can be beneficial, even with a moderately sparse dataset. Expand
Accurate splice site prediction using support vector machines
TLDR
The performance estimates indicate that splice sites can be recognized very accurately in these genomes and that the method outperforms many other methods including Markov Chains, GeneSplicer and SpliceMachine. Expand
Detection of splice junctions from paired-end RNA-seq data by SpliceMap
TLDR
A computational method, SpliceMap, to detect splice junctions from RNA-seq data is presented, which does not depend on any existing annotation of gene structures and is capable of finding novel splicing junctions with high sensitivity and specificity. Expand
SpliceMachine: predicting splice sites from high-dimensional local context representations
TLDR
A novel publicly available splice site prediction tool named SpliceMachine is presented that shows state-of-the-art prediction performance on Arabidopsis thaliana and human sequences, performs a computationally fast annotation and can be trained by the user on its own data. Expand
An approach of encoding for prediction of splice sites using SVM.
TLDR
The results showed that PN with FDTF encoding as input to SVM led to the most reliable recognition of splice sites and the accuracy for the prediction of true donor sites and false sites were 96.3%, 93.7%, respectively. Expand
MapSplice: Accurate mapping of RNA-seq reads for splice junction discovery
TLDR
A second generation splice detection algorithm, MapSplice, whose focus is high sensitivity and specificity in the detection of splices as well as CPU and memory efficiency is introduced, which indicates that Map Splice is a highly accurate algorithm for the alignment of RNA-seq reads to splice junctions. Expand
Improved splice site detection in Genie
TLDR
An improved splice site predictor for the genefinding program Genie is presented and it is shown that Genie shows significant improvements in the sensitivity and specificity of gene structure identification. Expand
Splice site identification using probabilistic parameters and SVM classification
BackgroundRecent advances and automation in DNA sequencing technology has created a vast amount of DNA sequence data. This increasing growth of sequence data demands better and efficient analysisExpand
TopHat: discovering splice junctions with RNA-Seq
TLDR
The TopHat pipeline is much faster than previous systems, mapping nearly 2.2 million reads per CPU hour, which is sufficient to process an entire RNA-Seq experiment in less than a day on a standard desktop computer. Expand
Deep Spatio-Temporal Architectures and Learning for Protein Structure Prediction
TLDR
A novel deep machine-learning architecture which consists of a multidimensional stack of learning modules which leads to an accuracy for difficult long-range contacts of about 30%, roughly 10% above the state-of-the-art. Expand
...
1
2
3
4
5
...