Deep multi-scale Gaussian residual networks for contextual-aware translation initiation site recognition

Abstract

The dysregulation of the translation initiation causes some cancers and metabolic disorders. However, the experimental verification of translation initiation sites (TIS) is expensive and small-scale, and the co-occurrence interaction relationship from genomic sequences is essential for knowledge discovery of TIS. In this work, a deep Gaussian residual neural computational model (GNet) is proposed to learn dynamic embeddings for parameter learning of discriminative features via context-aware modeling, and accurately identify TIS via co-occurrence embedding. GNet includes multi-scale Gaussian gated convolutional networks and bidirectional gated recurrent units. Particularly, a Gaussian gated linear unit is devised to extract local co-occurrence embedding vectors of genomic sequences, and the unit can reduce vanishing gradient problems and enable the recognition model to obtain powerful learning capabilities. Moreover, a stochastic linear skip gated connection is designed to boost the information exchange and extract complex contextual features between low and high layers, and vanishing gradients can be largely alleviated during training. Then, the gated recurrent unit is used to extract global long-term dependency features via identity connections. Consequently, to obtain global embedding information of sequences, a concatenation operation is used to fuse local and long discriminative features. Experiments demonstrate that GNet is an efficient and effective TIS recognition model and achieves remarkable results over state-of-the-art methods.