iEnhancer-DLRA: identification of enhancers and their strengths by a self-attention fusion strategy for local and global features
- 9 August 2022
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Functional Genomics
- Vol. 21 (5) , 399-407
Abstract
Identification and classification of enhancers are highly significant because they play crucial roles in controlling gene transcription. Recently, several deep learning-based methods for identifying enhancers and their strengths have been developed. However, existing methods are usually limited because they use only local or only global features. The combination of local and global features is critical to further improve the prediction performance. In this work, we propose a novel deep learning-based method, called iEnhancer-DLRA, to identify enhancers and their strengths. iEnhancer-DLRA extracts local and multi-scale global features of sequences by using a residual convolutional network and two bidirectional long short-term memory networks. Then, a self-attention fusion strategy is proposed to deeply integrate these local and global features. The experimental results on the independent test dataset indicate that iEnhancer-DLRA performs better than nine existing state-of-the-art methods in both identification and classification of enhancers in almost all metrics. iEnhancer-DLRA achieves 13.8% (for identifying enhancers) and 12.6% (for classifying strengths) improvement in accuracy compared with the best existing state-of-the-art method. This is the first time that the accuracy of an enhancer identifier exceeds 0.9 and the accuracy of the enhancer classifier exceeds 0.8 on the independent test set. Moreover, iEnhancer-DLRA achieves superior predictive performance on the rice dataset compared with the state-of-the-art method RiceENN.Keywords
Funding Information
- National Natural Science Foundation of China (11871061, 2020YFC0832405, 2019RS1060)
This publication has 47 references indexed in Scilit:
- Integrating Diverse Datasets Improves Developmental Enhancer PredictionPLOS Computational Biology, 2014
- Transcriptional enhancers: from properties to genome-wide predictionsNature Reviews Genetics, 2014
- Enhancers: five essential questionsNature Reviews Genetics, 2013
- Distant Activation of Transcription: Mechanisms of Enhancer ActionMolecular and Cellular Biology, 2012
- Genome-wide enhancer prediction from epigenetic signatures using genetic algorithm-optimized support vector machinesNucleic Acids Research, 2012
- ChIP-seq accurately predicts tissue-specific activity of enhancersNature, 2009
- Chapter 13 Long‐Range Gene Control and Genetic Disease2008
- Distinct and predictive chromatin signatures of transcriptional promoters and enhancers in the human genomeNature Genetics, 2007
- Prediction of linear B-cell epitopes using amino acid pair antigenicity scaleAmino Acids, 2007
- LSTM recurrent networks learn simple context-free and context-sensitive languagesIEEE Transactions on Neural Networks, 2001