Protein single-model quality assessment by feature-based probability density functions

TL;DR

Qprob is a novel protein single-model quality assessment method that uses feature-based probability density functions, demonstrating top performance in CASP11 and aiding in accurate protein structure prediction.

Contribution

Introduces Qprob, a new method using probability density functions for protein model quality assessment, outperforming existing methods in blind tests.

Findings

Qprob ranks among top single-model QA methods in CASP11.

Qprob significantly improves protein structure prediction accuracy.

The method is effective for assessing hard-to-predict protein models.

Abstract

Protein quality assessment (QA) has played an important role in protein structure prediction. We developed a novel single-model quality assessment method - Qprob. Qprob calculates the absolute error for each protein feature value against the true quality scores (i.e. GDT-TS scores) of protein structural models, and uses them to estimate its probability density distribution for quality assessment. Qprob has been blindly tested on the 11th Critical Assessment of Techniques for Protein Structure Prediction (CASP11) as MULTICOM-NOVEL server. The official CASP result shows that Qprob ranks as one of the top single-model QA methods. In addition, Qprob makes contributions to our protein tertiary structure predictor MULTICOM, which is officially ranked 3rd out of 143 predictors. The good performance shows that Qprob is good at assessing the quality of models of hard targets. These results demonstrate that this new probability density distribution based method is effective for protein single-model quality assessment and is useful for protein structure prediction. The webserver and software packages of Qprob are available at: http://calla.rnet.missouri.edu/qprob/.