Dasheng Chen and Leyi Wei* Pages 661 - 668 ( 8 )
Background: DNA and protein are important components of living organisms. DNA binding protein is a helicase, which is a protein specifically responsible for binding to DNA single- stranded regions. It is a necessary component for DNA replication, recombination and repair, and plays a key role in the function of various biomolecules. Although there are already some classification prediction methods for this protein, the use of graph neural networks for this work is still limited.
Objective: The classification of unknown protein sequences into the correct categories, subcategories and families is important for biological sciences. In this article, using graph neural networks, we developed a novel predictor GCN-DBP for protein classification prediction.
Methods: Each protein sequence is treated as a document in this study, and then segment the words according to the concept of k-mer, thereby, finally achieving the purpose of segmenting the document. This research aims to use document word relationships and word co-occurrence as a corpus to construct a text graph, and then learn protein sequence information by two-layer graph convolutional networks.
Results: Finally, we tested GCN-DBP on the independent data set PDB2272, and its accuracy reached 64.17% and MCC was 28.32%. Moreover, in order to compare the proposed method with other existing methods, we have conducted more experiments.
Conclusion: The results show that the proposed method is superior to the other four methods and will be a useful tool.
DNA-binding proteins, Graph Convolutional Network (GCN), protein sequence, sequence classification, deep learning, k-mer spectrum.
College of Intelligence and Computing, Tianjin University, Tianjin, School of Software, Shandong University, Jinan