TY - JOUR
T1 - Highly Efficient Framework for Predicting Interactions Between Proteins
AU - You, Zhu Hong
AU - Zhou, Meng Chu
AU - Luo, Xin
AU - Li, Shuai
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61373086 and Grant 61401385, in part by US National Natural Science Foundation under grant CMMI-1162482, in part by the Pioneer Hundred Talents Program of Chinese Academy of Sciences, in part by the Young Scientist Foundation of Chongqing under Grant cstc2014kjrcqnrc40005, and in part by the Fundamental Research Funds for the Central Universities under Grant 106112015CDJXY180005. This paper was recommended by Associate Editor S. Yang.
Publisher Copyright:
© 2016 IEEE.
PY - 2017/3
Y1 - 2017/3
N2 - Protein-protein interactions (PPIs) play a central role in many biological processes. Although a large amount of human PPI data has been generated by high-throughput experimental techniques, they are very limited compared to the estimated 130 000 protein interactions in humans. Hence, automatic methods for human PPI-detection are highly desired. This work proposes a novel framework, i.e., Low-rank approximation-kernel Extreme Learning Machine (LELM), for detecting human PPI from a protein's primary sequences automatically. It has three main steps: 1) mapping each protein sequence into a matrix built on all kinds of adjacent amino acids; 2) applying the low-rank approximation model to the obtained matrix to solve its lowest rank representation, which reflects its true subspace structures; and 3) utilizing a powerful kernel extreme learning machine to predict the probability for PPI based on this lowest rank representation. Experimental results on a large-scale human PPI dataset demonstrate that the proposed LELM has significant advantages in accuracy and efficiency over the state-of-art approaches. Hence, this work establishes a new and effective way for the automatic detection of PPI.
AB - Protein-protein interactions (PPIs) play a central role in many biological processes. Although a large amount of human PPI data has been generated by high-throughput experimental techniques, they are very limited compared to the estimated 130 000 protein interactions in humans. Hence, automatic methods for human PPI-detection are highly desired. This work proposes a novel framework, i.e., Low-rank approximation-kernel Extreme Learning Machine (LELM), for detecting human PPI from a protein's primary sequences automatically. It has three main steps: 1) mapping each protein sequence into a matrix built on all kinds of adjacent amino acids; 2) applying the low-rank approximation model to the obtained matrix to solve its lowest rank representation, which reflects its true subspace structures; and 3) utilizing a powerful kernel extreme learning machine to predict the probability for PPI based on this lowest rank representation. Experimental results on a large-scale human PPI dataset demonstrate that the proposed LELM has significant advantages in accuracy and efficiency over the state-of-art approaches. Hence, this work establishes a new and effective way for the automatic detection of PPI.
KW - Big data
KW - feature extraction
KW - kernel extreme learning machine (K-ELM)
KW - low-rank approximation (LRA)
KW - protein-protein interactions (PPIs)
KW - support vector machine (SVM)
UR - http://www.scopus.com/inward/record.url?scp=85047726651&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047726651&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2016.2524994
DO - 10.1109/TCYB.2016.2524994
M3 - Article
C2 - 28113829
AN - SCOPUS:85047726651
SN - 2168-2267
VL - 47
SP - 731
EP - 743
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 3
M1 - 7444177
ER -