Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities

Published in

(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

deepRAM, an end-to-end deep learning tool that provides an implementation of a wide selection of architectures, finds that deeper more complex architectures provide a clear advantage with sufficient training data, and that hybrid CNN/RNN architectures outperform other methods in terms of accuracy.

Abstract

Abstract Motivation Deep learning architectures have recently demonstrated their power in predicting DNA- and RNA-binding specificity. Existing methods fall into three classes: Some are based on convolutional neural networks (CNNs), others use recurrent neural networks (RNNs) and others rely on hybrid architectures combining CNNs and RNNs. However, based on existing studies the relative merit of the various architectures remains unclear. Results In this study we present a systematic exploration of deep learning architectures for predicting DNA- and RNA-binding specificity. For this purpose, we present deepRAM, an end-to-end deep learning tool that provides an implementation of a wide selection of architectures; its fully automatic model selection procedure allows us to perform a fair and unbiased comparison of deep learning architectures. We find that deeper more complex architectures provide a clear advantage with sufficient training data, and that hybrid CNN/RNN architectures outperform other methods in terms of accuracy. Our work provides guidelines that can assist the practitioner in choosing an appropriate network architecture, and provides insight on the difference between the models learned by convolutional and recurrent networks. In particular, we find that although recurrent networks improve model accuracy, this comes at the expense of a loss in the interpretability of the features learned by the model. Availability and implementation The source code for deepRAM is available at https://github.com/MedChaabane/deepRAM. Supplementary information Supplementary data are available at Bioinformatics online.

Authors

Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities

Published in

(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

References46 items

Recurrent Neural Network for Predicting Transcription Factor Binding Sites

Troubling Trends in Machine Learning Scholarship

Dilated Convolutions for Modeling Long-Distance Genomic Dependencies

On the State of the Art of Evaluation in Neural Language Models

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

Sequential regulatory activity prediction across chromosomes with convolutional neural networks

Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks

Fast and Accurate Sequence Labeling with Iterated Dilated Convolutions

DeeperBind: Enhancing Prediction of Sequence Specificities of DNA Binding Proteins

Deep learning for computational biology

Convolutional neural network architectures for predicting DNA–protein binding

Orthogonal matrix factorization enables integrative analysis of multiple RNA binding proteins

DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences

Multi-Scale Context Aggregation by Dilated Convolutions

Predicting effects of noncoding variants with deep learning–based sequence model

Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

Advances in natural language processing

Revealing protein–lncRNA interaction

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

DoRiNA 2.0—upgrading the doRiNA database of RNA interactions in post-transcriptional regulation

A census of human RNA-binding proteins

Sequence to Sequence Learning with Neural Networks

On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

Protein–DNA binding: complexities and multi-protein codes

JASPAR 2014: an extensively expanded and updated open-access database of transcription factor binding profiles

Distributed Representations of Words and Phrases and their Compositionality

A compendium of RNA-binding motifs for decoding gene regulation

Recurrent neural networks

ImageNet classification with deep convolutional neural networks

An Integrated Encyclopedia of DNA Elements in the Human Genome

Systematic evaluation of factors influencing ChIP-seq fidelity

RNAcontext: A New Method for Learning the Sequence and Structure Binding Preferences of RNA-Binding Proteins

Origins of specificity in protein-DNA recognition.

Quantifying similarity between motifs

The ENCODE (ENCyclopedia Of DNA Elements) Project

WebLogo: a sequence logo generator.

Long Short-Term Memory

Learning long-term dependencies with gradient descent is difficult

Continuous

Recurrent Neural Networks

2016) DeeperBind: enhancing prediction

Deep Learning

Rectifier Nonlinearities Improve Neural Network Acoustic Models

FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597

DNA binding sites: representation and discovery

Gradient-based learning applied to document recognition

TL;DR

Abstract

Authors

TL;DR

Abstract

Authors

References46 items

Recurrent Neural Network for Predicting Transcription Factor Binding Sites

Troubling Trends in Machine Learning Scholarship

Dilated Convolutions for Modeling Long-Distance Genomic Dependencies

On the State of the Art of Evaluation in Neural Language Models

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

Sequential regulatory activity prediction across chromosomes with convolutional neural networks

Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks

Fast and Accurate Sequence Labeling with Iterated Dilated Convolutions

DeeperBind: Enhancing Prediction of Sequence Specificities of DNA Binding Proteins

Deep learning for computational biology

Convolutional neural network architectures for predicting DNA–protein binding

Orthogonal matrix factorization enables integrative analysis of multiple RNA binding proteins

DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences

Multi-Scale Context Aggregation by Dilated Convolutions

Predicting effects of noncoding variants with deep learning–based sequence model

Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

Advances in natural language processing

Revealing protein–lncRNA interaction

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

DoRiNA 2.0—upgrading the doRiNA database of RNA interactions in post-transcriptional regulation

A census of human RNA-binding proteins

Sequence to Sequence Learning with Neural Networks

On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

Protein–DNA binding: complexities and multi-protein codes

JASPAR 2014: an extensively expanded and updated open-access database of transcription factor binding profiles

Distributed Representations of Words and Phrases and their Compositionality

A compendium of RNA-binding motifs for decoding gene regulation

Recurrent neural networks

ImageNet classification with deep convolutional neural networks

An Integrated Encyclopedia of DNA Elements in the Human Genome

Systematic evaluation of factors influencing ChIP-seq fidelity

RNAcontext: A New Method for Learning the Sequence and Structure Binding Preferences of RNA-Binding Proteins

Origins of specificity in protein-DNA recognition.

Quantifying similarity between motifs

The ENCODE (ENCyclopedia Of DNA Elements) Project

WebLogo: a sequence logo generator.

Long Short-Term Memory

Learning long-term dependencies with gradient descent is difficult

Continuous

Recurrent Neural Networks

2016) DeeperBind: enhancing prediction

Deep Learning

Rectifier Nonlinearities Improve Neural Network Acoustic Models

FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597

DNA binding sites: representation and discovery

Gradient-based learning applied to document recognition

Field of Study

Journal Information

Name

Page

Volume