Accurate classification of membrane protein types based on sequence and evolutionary information using deep learning

• Published in: BMC bioinformatics Vol. 20; no. Suppl 25; p. 700
• Main Authors: Guo, Lei, Wang, Shunfang, Li, Mingyuan, Cao, Zicheng
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 24.12.2019; BioMed Central; BMC
• Subjects: Amino acid sequence; Amino acids; Analysis; Bioinformatics; Computational Biology; Computer applications; Criminal investigation; Datasets; Deep Learning; Information processing; Learning algorithms; Lipids; Machine learning; Membrane protein type prediction; Membrane proteins; Membrane Proteins - chemistry; Membranes; Methods; Neural networks; Novels; Performance enhancement; Performance evaluation; Proteins; Researchers; Sequence Analysis; Signal transduction; Structure-function relationships; Vector representation; Deep learning; Membrane protein type prediction; Vector representation
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-019-3275-6

Membrane proteins play an important role in the life activities of organisms. Knowing membrane protein types provides clues for understanding the structure and function of proteins. Though various computational methods for predicting membrane protein types have been developed, the results still do not meet the expectations of researchers. We propose two deep learning models to process sequence information and evolutionary information, respectively. Both models obtained better results than traditional machine learning models. Furthermore, to improve the performance of the sequence information model, we also provide a new vector representation method to replace the one-hot encoding, whose overall success rate improved by 3.81% and 6.55% on two datasets. Finally, a more effective model is obtained by fusing the above two models, whose overall success rate reached 95.68% and 92.98% on two datasets. The final experimental results show that our method is more effective than existing methods for predicting membrane protein types, which can help laboratory researchers to identify the type of novel membrane proteins.