A New Method Combining DNA Shape Features to Improve the Prediction Accuracy of Transcription Factor Binding Sites

Abstract

Identifying transcription factor (TF) binding sites (TFBSs) has play an important role in the computational inference of gene regulation. With the development of high-throughput technologies, there have been many conventional methods and deep learning models used in the identification of TFBSs. However, most methods are designed to predict TFBSs only based on raw DNA sequence leads to low accuracy. Therefore, we propose a Dual-channel Convolutional neural network (CNN) model combining DNA sequences and DNA Shape features to predict TFBSs, named DCDS. In the DCDS model, the convolution layer captures low-level features from input data and parallel pooling operations are used to find the most significant activation signal in a sequence for each filter to improve the prediction accuracy of TFBSs. We conduct a series of experiments on 66 in vitro datasets and experimental results show that proposed model DCDS is superior to some state-of-the-art methods.