Predicting helix–helix interactions from residue contacts in membrane proteins

Abstract

Motivation: Helix–helix interactions play a critical role in the structure assembly, stability and function of membrane proteins. On the molecular level, the interactions are mediated by one or more residue contacts. Although previous studies focused on helix-packing patterns and sequence motifs, few of them developed methods specifically for contact prediction.Results: We present a new hierarchical framework for contact prediction, with an application in membrane proteins. The hierarchical scheme consists of two levels: in the first level, contact residues are predicted from the sequence and their pairing relationships are further predicted in the second level. Statistical analyses on contact propensities are combined with other sequence and structural information for training the support vector machine classifiers. Evaluated on 52 protein chains using leave-one-out cross validation (LOOCV) and an independent test set of 14 protein chains, the two-level approach consistently improves the conventional direct approach in prediction accuracy, with 80% reduction of input for prediction. Furthermore, the predicted contacts are then used to infer interactions between pairs of helices. When at least three predicted contacts are required for an inferred interaction, the accuracy, sensitivity and specificity are 56%, 40% and 89%, respectively. Our results demonstrate that a hierarchical framework can be applied to eliminate false positives (FP) while reducing computational complexity in predicting contacts. Together with the estimated contact propensities, this method can be used to gain insights into helix-packing in membrane proteins.Availability: http://bio-cluster.iis.sinica.edu.tw/TMhit/Contact: tsung@iis.sinica.edu.twSupplementary information:Supplementary data are available at Bioinformatics online.

Single-spanning transmembrane domains in cell growth and cell-cell interactions

“…Contact map predictors were implemented using Neural Networks 89 and Support Vector Machine (Tmhit). 90 Their accuracy was argued to be between 31-57%. To our knowledge, those recently developed methods have not been applied to the prediction of associations of single spanning TM proteins.…”

Accurate de novo structure prediction of large transmembrane protein domains using fragment-assembly and correlated mutation analysis

“…This allowed the prediction of 12 small TMP domains of up to 150 residues to within 4 Å rmsd of the native structures suggesting that the essential physical properties that govern the solvation and stability of TMPs were being captured. A subsequent development allowed a small number of distance constraints to be applied to helix-helix packing arrangements, predicted from sequence (15)(16)(17) or identified from experimental data, allowing larger structures of between 90 and 300 residues with a diverse range of topologies to be predicted with reasonable accuracy (18). Results showed that only a single constraint was sometimes enough to enrich the population of near-native models; whereas, models within 4 Å of the native structure could be achieved in four cases.…”

New Perspectives in Predicting Membrane Protein-Protein Interactions

“…In a recent publication, a two-level hierarchical method based on support vector machine (SVM) was proposed. In this study, they built two layers of SVMs (Lo et al, 2009). The first layer of SVM was to predict contact residues.…”