Efficient utilization on PSSM combining with recurrent neural network for membrane protein types prediction. (August 2019)

• Record Type: Journal Article
• Authors: Wang, Shunfang; Li, Mingyuan; Guo, Lei; Cao, Zicheng; Fei, Yu
• Is Part Of: Computational biology and chemistry. Volume 81(2019)
• Page Start: 9
• Page End: 15
• Publication Date: 2019-08
• Subjects: Membrane protein types prediction -- Long short-term memory -- Position-Specific scoring matrix -- Deep learning; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2019.107094
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: Highly utilized PSSM for membrane protein types prediction without any matrix structure destruction and information loss. Design a refined network architecture of two-layer bidirectional LSTM, with Batch Normalization, Dropout and LeakyReLU. Explore the power of feature representation in the network and propose a way to combine it with other feature representations. Abstract: Position-Specific Scoring Matrix (PSSM) is an excellent feature extraction method that was proposed early in protein classifying prediction, but within the restriction of feature shape in PSSM, researchers make a lot attempts to process it so that PSSM can be input to the traditional machine learning algorithms. These processes drop information provided by PSSM in a way thus the feature representation is limited. Moreover, the high-dimensional feature representation of PSSM makes it incompatible with other feature extraction methods. We use the PSSM as the input of Recurrent Neural Network without any post-processing, the amino acids in protein sequences are regarded as time step in RNN. This way takes full advantage of the information that PSSM provides. In this study, the PSSM is input to the model directly and the internal information of PSSM is fully utilized, we propose an end-to-end solution and achieve state-of-the-art performance. Ultimately, the exploration of how to combine PSSM with traditional feature extraction methods is carried out and achieve slightly improved performance. Our network architecture is implemented in Python and is available athttps://github.com/YellowcardD/RNN-for-membrane-protein-types-prediction .