Format

Send to

Choose Destination
Int J Mol Sci. 2018 Jan 8;19(1). pii: E183. doi: 10.3390/ijms19010183.

Assessing the Performances of Protein Function Prediction Algorithms from the Perspectives of Identification Accuracy and False Discovery Rate.

Yu CY1,2, Li XX3,4, Yang H5,6, Li YH7,8, Xue WW9, Chen YZ10, Tao L11, Zhu F12,13.

Author information

1
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. yucy@cqu.edu.cn.
2
Innovative Drug Research and Bioinformatics Group, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. yucy@cqu.edu.cn.
3
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. lixiaoxu@cqu.edu.cn.
4
Innovative Drug Research and Bioinformatics Group, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. lixiaoxu@cqu.edu.cn.
5
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. yangh0921@cqu.edu.cn.
6
Innovative Drug Research and Bioinformatics Group, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. yangh0921@cqu.edu.cn.
7
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. liyh@cqu.edu.cn.
8
Innovative Drug Research and Bioinformatics Group, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. liyh@cqu.edu.cn.
9
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. xueww@cqu.edu.cn.
10
Bioinformatics and Drug Design Group, Department of Pharmacy, and Center for Computational Science and Engineering, National University of Singapore, Singapore 117543, Singapore. 20121802134@cqu.edu.cn.
11
School of Medicine, Hangzhou Normal University, Hangzhou 310012, China. linntaoo@hotmail.com.
12
Innovative Drug Research and Bioinformatics Group, School of Pharmaceutical Sciences and Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 401331, China. zhufeng.ns@gmail.com.
13
Innovative Drug Research and Bioinformatics Group, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China. zhufeng.ns@gmail.com.

Abstract

The function of a protein is of great interest in the cutting-edge research of biological mechanisms, disease development and drug/target discovery. Besides experimental explorations, a variety of computational methods have been designed to predict protein function. Among these in silico methods, the prediction of BLAST is based on protein sequence similarity, while that of machine learning is also based on the sequence, but without the consideration of their similarity. This unique characteristic of machine learning makes it a good complement to BLAST and many other approaches in predicting the function of remotely relevant proteins and the homologous proteins of distinct function. However, the identification accuracies of these in silico methods and their false discovery rate have not yet been assessed so far, which greatly limits the usage of these algorithms. Herein, a comprehensive comparison of the performances among four popular prediction algorithms (BLAST, SVM, PNN and KNN) was conducted. In particular, the performance of these methods was systematically assessed by four standard statistical indexes based on the independent test datasets of 93 functional protein families defined by UniProtKB keywords. Moreover, the false discovery rates of these algorithms were evaluated by scanning the genomes of four representative model organisms (Homo sapiens, Arabidopsis thaliana, Saccharomyces cerevisiae and Mycobacterium tuberculosis). As a result, the substantially higher sensitivity of SVM and BLAST was observed compared with that of PNN and KNN. However, the machine learning algorithms (PNN, KNN and SVM) were found capable of substantially reducing the false discovery rate (SVM < PNN < KNN). In sum, this study comprehensively assessed the performance of four popular algorithms applied to protein function prediction, which could facilitate the selection of the most appropriate method in the related biomedical research.

KEYWORDS:

BLAST; false discovery rate; machine learning; protein function prediction; support vector machine

PMID:
29316706
PMCID:
PMC5796132
DOI:
10.3390/ijms19010183
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center