Learning spatiotemporal embedding with gated convolutional recurrent networks for translation initiation site prediction

Abstract

Accurately predicting translation initiation sites (TIS) from genomic sequences is crucial for understanding gene regulation and function. TIS prediction methods’ feature vectors are not discriminative enough to lead to unsatisfactory predictive results. In this work, we devise an efficient gated convolutional recurrent network (GCR-Net) with residual learning to dynamically extract dependency patterns of raw genomic sequences in an efficient fusion strategy and successfully improve the performance of the TIS prediction. GCR-Net mainly includes exponential gated convolutional residual networks (EGCRN) and bidirectional gated recurrent unit (Bi-GRU) networks. Particularly, we devise the novel EGCRN to extract multiple complex patterns of the spatial dimension from genomic sequences, where we design an exponential gated linear unit (EGLU) to reduce the vanishing gradient problem. Moreover, we combine EGLU with shortcut connections to develop the stacked gated mechanism based on convolutions that benefit information propagation across layers. Then, we use Bi-GRU with identity connections to learn long-term dependency patterns of the temporal dimension from genomic sequences. Besides, we evaluate our GCR-Net model on four TIS datasets, and experiments demonstrate that GCR-Net is an efficient deep learning-based TIS prediction tool and obtains superior performance compared to the baseline methods.