Amino Acids

, Volume 38, Issue 1, pp 263–270

Identifying protein–protein interaction sites in transient complexes with temperature factor, sequence profile and accessible surface area

Original Article

DOI: 10.1007/s00726-009-0245-8

Cite this article as:
Liu, R., Jiang, W. & Zhou, Y. Amino Acids (2010) 38: 263. doi:10.1007/s00726-009-0245-8


Transient protein–protein interactions play a vital role in many biological processes, such as cell regulation and signal transduction. A nonredundant dataset of 130 protein chains extracted from transient complexes was used to analyze the features of transient interfaces. It was found that besides the two well-known features, sequence profile and accessible surface area (ASA), the temperature factor (B-factor) can also reflect the differences between interface and the rest of protein surface. These features were utilized to construct support vector machine (SVM) classifiers to identify interaction sites. The results of threefold cross-validation on the nonredundant dataset show that when B-factor was used as an additional feature, the prediction performance can be improved significantly. The sensitivity, specificity and correlation coefficient were raised from 54 to 62%, 41 to 45% and 0.20 to 0.29, respectively. To further illustrate the effectiveness of our method, the classifiers were tested with an independent set of 53 nonhomologous protein chains derived from benchmark 2.0. The sensitivity, specificity and correlation coefficient of the classifier based on the three features were 63%, 45% and 0.33, respectively. It is indicated that our classifiers are robust and can be applied to complement experimental techniques in studying transient protein–protein interactions.


Protein–protein interactionsTransient interfaceSequence profileTemperature factorAccessible surface areaSupport vector machine

Supplementary material

726_2009_245_MOESM1_ESM.doc (54 kb)
The list of 130 chains and corresponding partner chains (DOC 54 kb)

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  1. 1.Hubei Bioinformatics and Molecular Imaging Key Laboratory, College of Life Science and TechnologyHuazhong University of Science and TechnologyWuhanChina