Predicting subcellular location of protein with evolution information and sequence-based deep learning

• Published in: BMC bioinformatics Vol. 22; no. 1; pp. 1 - 515
• Main Authors: Liao, Zhijun, Pan, Gaofeng, Sun, Chao, Tang, Jijun
• Format: Journal Article
• Language: English
• Published: London BioMed Central Ltd 22.10.2021; BioMed Central; BMC
• Subjects: Accuracy; Algorithms; Amino acid sequence; Amino acids; Artificial intelligence; Artificial neural networks; Classification; Datasets; Deep learning; Evolution; Evolution information; Feature extraction; Learning algorithms; Localization; Long short-term memory; Machine learning; Methods; Multiple label classification; Neural networks; Predictions; Protein research; Protein sequence; Proteins; Subcellular prediction; Support vector machines; China
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-021-04404-0

Protein subcellular localization prediction plays an important role in biology research. Since traditional methods are laborious and time-consuming, many machine learning-based prediction methods have been proposed. However, most of the proposed methods ignore the evolution information of proteins. In order to improve the prediction accuracy, we present a deep learning-based method to predict protein subcellular locations. Our method utilizes not only amino acid compositions sequence but also evolution matrices of proteins. Our method uses a bidirectional long short-term memory network that processes the entire protein sequence and a convolutional neural network that extracts features from protein sequences. The position specific scoring matrix is used as a supplement to protein sequences. Our method was trained and tested on two benchmark datasets. The experiment results show that our method yields accurate results on the two datasets with an average precision of 0.7901, ranking loss of 0.0758 and coverage of 1.2848. The experiment results show that our method outperforms five methods currently available. According to those experiments, we can see that our method is an acceptable alternative to predict protein subcellular location.