Predicting transcription factor binding sites using DNA shape features based on shared hybrid deep learning architecture

Siguo Wang; Qinhu Zhang; Zhen Shen; Ying He; Zhen-Heng Chen; Jianqiang Li; De-Shuang Huang

doi:10.1016/j.omtn.2021.02.014

Predicting transcription factor binding sites using DNA shape features based on shared hybrid deep learning architecture

Mol Ther Nucleic Acids. 2021 Feb 18:24:154-163. doi: 10.1016/j.omtn.2021.02.014. eCollection 2021 Jun 4.

Authors

Siguo Wang¹, Qinhu Zhang^{1

2}, Zhen Shen³, Ying He¹, Zhen-Heng Chen⁴, Jianqiang Li⁴, De-Shuang Huang¹

Affiliations

¹ The Institute of Machine Learning and Systems Biology, School of Electronics and Information Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, China.
² Translational Medical Center for Stem Cell Therapy and Institute for Regenerative Medicine, Shanghai East Hospital, Tongji University, Siping Road 1239, Shanghai 200092, China.
³ School of Computer and Software, Nanyang Institute of Technology, Changjiang Road 80, Nanyang, Henan 473004, China.
⁴ College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China.

Abstract

The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. Recent research has shown that the double helix structure of nucleotides plays an important role in improving the accuracy and interpretability of transcription factor binding sites (TFBSs). Although several computational methods have been designed to take both DNA sequence and DNA shape features into consideration simultaneously, how to design an efficient model is still an intractable topic. In this paper, we proposed a hybrid convolutional recurrent neural network (CNN/RNN) architecture, CRPTS, to predict TFBSs by combining DNA sequence and DNA shape features. The novelty of our proposed method relies on three critical aspects: (1) the application of a shared hybrid CNN and RNN has the ability to efficiently extract features from large-scale genomic sequences obtained by high-throughput technology; (2) the common patterns were found from DNA sequences and their corresponding DNA shape features; (3) our proposed CRPTS can capture local structural information of DNA sequences without completely relying on DNA shape data. A series of comprehensive experiments on 66 in vitro datasets derived from universal protein binding microarrays (uPBMs) shows that our proposed method CRPTS obviously outperforms the state-of-the-art methods.

Keywords: DNA sequence; DNA shape features; hybrid convolutional neural network; recurrent neural network; transcription factor binding sites.