CAE-CNN: Predicting transcription factor binding site with convolutional autoencoder and convolutional neural network

作者：

Highlights：

• Integrate the unsupervised and supervised method to predict the TF binding site.

• CAE-CNN share the parameters, so the training time can be significantly reduced.

• Effectively gradient-based training the model by the gating units.

• Only use positive samples for pre-training to reduce the noise and improve accuracy.

摘要

•Integrate the unsupervised and supervised method to predict the TF binding site.•CAE-CNN share the parameters, so the training time can be significantly reduced.•Effectively gradient-based training the model by the gating units.•Only use positive samples for pre-training to reduce the noise and improve accuracy.

论文关键词：Transcription factor binding sites,Convolutional neural networks,Motif discovery,Bioinformatics,Autoencoder

论文评审过程：Received 3 October 2020, Revised 14 May 2021, Accepted 9 June 2021, Available online 19 June 2021, Version of Record 22 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115404