Title
Predicting the Subcellular Localization of Multi-site Protein Based on Fusion Feature and Multi-label Deep Forest Model
Abstract
Protein is the basis of life activities and plays an irreplaceable role. Proteins usually have a specific biochemical environment that is closely related to protein function, so understanding the subcellular localization information of proteins can provide powerful help for the research of drugs for the treatment of diseases. The prediction of protein subcellular localization is a very basic and significant in bioinformatics. In this paper, we propose a method for predicting the subcellular localization of multi-site bacterial proteins. Based on position-specific scoring matrix (PSSM) containing evolutionary information, we first extract two new features to represent proteins, of which one is from functional amino acid analysis and another is from Jensen-Shannon (JS) divergence analysis. After combining two features, we obtain a new fusion feature which contains more information and input it into the multi-label deep forest (MLDF) model for subcellular localization prediction of multi-site proteins. Experimental results on Gram-positive data set show the effectiveness of the proposed method.
Year
DOI
Venue
2022
10.1007/978-3-031-13829-4_28
INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2022, PT II
Keywords
DocType
Volume
Multi-site protein subcellular localization, PSSM, JS divergence, Multi-label deep forest
Conference
13394
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Hongri Yang100.34
Qingfang Meng200.34
Yuehui Chen300.34
Lianxin Zhong400.34