Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jul 23;8(7):767.
doi: 10.3390/cells8070767.

Ensemble of Deep Recurrent Neural Networks for Identifying Enhancers via Dinucleotide Physicochemical Properties

Kok Keng Tan  1 , Nguyen Quoc Khanh Le  2 , Hui-Yuan Yeh  3 , Matthew Chin Heng Chua  4
Affiliations

Ensemble of Deep Recurrent Neural Networks for Identifying Enhancers via Dinucleotide Physicochemical Properties

Kok Keng Tan et al. Cells. .

Abstract

Enhancers are short deoxyribonucleic acid fragments that assume an important part in the genetic process of gene expression. Due to their possibly distant location relative to the gene that is acted upon, the identification of enhancers is difficult. There are many published works focused on identifying enhancers based on their sequence information, however, the resulting performance still requires improvements. Using deep learning methods, this study proposes a model ensemble of classifiers for predicting enhancers based on deep recurrent neural networks. The input features of deep ensemble networks were generated from six types of dinucleotide physicochemical properties, which had outperformed the other features. In summary, our model which used this ensemble approach could identify enhancers with achieved sensitivity of 75.5%, specificity of 76%, accuracy of 75.5%, and MCC of 0.51. For classifying enhancers into strong or weak sequences, our model reached sensitivity of 83.15%, specificity of 45.61%, accuracy of 68.49%, and MCC of 0.312. Compared to the benchmark result, our results had higher performance in term of most measurement metrics. The results showed that deep model ensembles hold the potential for improving on the best results achieved to date using shallow machine learning methods.

Keywords: biocomputing; dinucleotide physicochemical properties; enhancer DNA; ensemble deep learning; gene expression; high performance; transcription factor.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
A neural network model with 1 convolution 1D and 1 max pooling layer before bi-directional recurrent and fully-connected layers.
Figure 2
Figure 2
A neural network model with 2 single-direction gated recurrent unit (GRU) layers and 1 fully-connected layer.
Figure 3
Figure 3
An example of model training using warm restarts. The cycles are apparent in the plot. The y axis is accuracy; the x axis is epochs.
Figure 4
Figure 4
Receiver Operating Characteristic (ROC) Curve for all single and ensemble models. (a) Layer 1 classification, (b) Layer 2 classification.
Figure 5
Figure 5
Comparative performance among different predictors. (a) Comparison on layer 1, (b) Comparison on layer 2.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Blackwood E.M., Kadonaga J.T. Going the Distance: A Current View of Enhancer Action. Science. 1998;281:60–63. doi: 10.1126/science.281.5373.60. - DOI - PubMed
    1. Pennacchio L.A., Bickmore W., Dean A., Nobrega M.A., Bejerano G. Enhancers: Five essential questions. Nat. Rev. Genet. 2013;14:288–295. doi: 10.1038/nrg3458. - DOI - PMC - PubMed
    1. Boyle A.P., Song L., Lee B.K., London D., Keefe D., Birney E., Iyer V.R., Crawford G.E., Furey T.S. High-resolution genome-wide in vivo footprinting of diverse transcription factors in human cells. Genome Res. 2011;21:456–464. doi: 10.1101/gr.112656.110. - DOI - PMC - PubMed
    1. Rhie S.K., Tak Y.G., Guo Y., Yao L., Shen H., Coetzee G.A., Laird P.W., Farnham P.J. Identification of activated enhancers and linked transcription factors in breast, prostate, and kidney tumors by tracing enhancer networks using epigenetic traits. Epigenetics Chromatin. 2016;9:50. doi: 10.1186/s13072-016-0102-4. - DOI - PMC - PubMed
    1. Blinka S., Reimer M.H., Pulakanti K., Pinello L., Yuan G.C., Rao S. Identification of Transcribed Enhancers by Genome-Wide Chromatin Immunoprecipitation Sequencing. In: Ørom U.A., editor. Enhancer RNAs: Methods and Protocols. Humana Press; New York, NY, USA: 2017. pp. 91–109. - PMC - PubMed

Publication types

LinkOut - more resources