Abstract
Transcription factors (TFs) regulate the gene expression of their target genes by binding to the regulatory sequences of target genes (e.g., promoters and enhancers). To fully understand gene regulatory mechanisms, it is crucial to decipher the relationships between TFs and DNA sequences. Moreover, studies such as GWAS and eQTL have verified that most disease-related variants exist in non-coding regions, and highlighted the necessity to identify such variants that cause diseases by interrupting TF binding mechanisms. To do this, it is necessary to build a prediction model that precisely predicts the binding relationships between TFs and DNA sequences. Recently, deep learning based models have been proposed and have shown competitive results on a transcription factor binding site prediction task. However, it is difficult to interpret the prediction results obtained from the previous models. In addition, the previous models assumed all the sequence regions in the input DNA sequence have the same importance for predicting TF-binding, although sequence regions containing TF-binding-associated signals such as TF-binding motifs should be captured more than other regions. To address these challenges, we propose TBiNet, an attention based interpretable deep neural network for predicting transcription factor binding sites. Using the attention mechanism, our method is able to assign more importance on the actual TF binding sites in the input DNA sequence. TBiNet outperforms the current state-of-the-art methods (DeepSea and DanQ) quantitatively in the TF-DNA binding prediction task. Moreover, TBiNet is more effective than the previous models in discovering known TF-binding motifs.
Highlights
We describe the following three components which our model is built upon: CNN, Long Short-Term Memory (LSTM), and an attention mechanism.Convolutional neural network.Convolutional Neural Network (CNN) consists of convolution layers usually followed by pooling layers with trainable weights and biases
We visualize the motifs found by CNN kernels from TBiNet that are matched with known transcription factor (TF) binding motifs
We analyze the attention layer in TBiNet to understand how the attention mechanism helps improve the performance of TF binding site prediction
Summary
Convolutional Neural Network (CNN) consists of convolution layers usually followed by pooling layers with trainable weights and biases. A convolution layer takes a grid-like input and performs convolution operation using kernels which extract spatial information from inputs. A pooling layer compresses the information and reduces the spatial size of the input representation. There are many researches on TF-DNA binding prediction tasks. D eepBind[5] and DeepSea[10] treated a one-hot encoded DNA sequence as a 1D image and applied CNN to that sequence[8] systematically explored how different architectures of CNN can affect performance on the TF-DNA binding task. One advantage of applying CNN to the TF-DNA binding task is that kernels in a CNN can learn TF binding motifs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
