PRED_PPI: a server for predicting protein-protein interactions based on sequence data with probability assignment

Abstract

Background: Protein-protein interactions (PPIs) are crucial for almost all cellular processes, including metabolic cycles, DNA transcription and replication, and signaling cascades. Given the importance of PPIs, several methods have been developed to detect them. Since the experimental methods are time-consuming and expensive, developing computational methods for effectively identifying PPIs is of great practical significance.

Findings: Most previous methods were developed for predicting PPIs in only one species, and do not account for probability estimations. In this work, a relatively comprehensive prediction system was developed, based on a support vector machine (SVM), for predicting PPIs in five organisms, specifically humans, yeast, Drosophila, Escherichia coli, and Caenorhabditis elegans. This PPI predictor includes the probability of its prediction in the output, so it can be used to assess the confidence of each SVM prediction by the probability assignment. Using a probability of 0.5 as the threshold for assigning class labels, the method had an average accuracy for detecting protein interactions of 90.67% for humans, 88.99% for yeast, 90.09% for Drosophila, 92.73% for E. coli, and 97.51% for C. elegans. Moreover, among the correctly predicted pairs, more than 80% were predicted with a high probability of >/=0.8, indicating that this tool could predict novel PPIs with high confidence.

Conclusions: Based on this work, a web-based system, Pred_PPI, was constructed for predicting PPIs from the five organisms. Users can predict novel PPIs and obtain a probability value about the prediction using this tool. Pred_PPI is freely available at http://cic.scu.edu.cn/bioinformatics/predict_ppi/default.html.

Figure 1

Curves of prediction accuracy versus probability threshold. The figure shows the average prediction accuracy of the method under the different probability thresholds of 0.5, 0.6, 0.7, 0.8 and 0.9 respectively. For predictors of five species, the total prediction accuracy was obtained by averaging those of five test sets.

Figure 2

The frequency distributions of the correctly predicted samples within different probability intervals. Among the correctly predicted samples under the default probability threshold of 0.5, the relative frequency distributions of them within different probability intervals are represented by this figure.

Figure 3

Screen shot of the input page of Pred_PPI. This figure shows how the users use the web server to input the query proteins 'A' and 'B' whose interaction needs to be predicted. Before submitting, users should select the respective predictor of one species that the query proteins belong to.

Figure 4

Screen shot of the output page of Pred_PPI. This figure shows the prediction result in the output page. The user will get the actual interaction probability between the query proteins.