Evaluation of Protein Structural Models Using Random Forests

TL;DR

This paper introduces a novel protein quality assessment method using random forests that predicts both local and global model quality, leveraging diverse features and combining single and multiple model assessments.

Contribution

It presents a new approach integrating multi- and single-model assessments with random forests for improved protein structure quality evaluation.

Findings

Performance comparable to state-of-the-art methods on CASP10.

Blind testing on CASP11 shows good generalization.

Combining assessment methods enhances accuracy.

Abstract

Protein structure prediction has been a grand challenge problem in the structure biology over the last few decades. Protein quality assessment plays a very important role in protein structure prediction. In the paper, we propose a new protein quality assessment method which can predict both local and global quality of the protein 3D structural models. Our method uses both multi and single model quality assessment method for global quality assessment, and uses chemical, physical, geo-metrical features, and global quality score for local quality assessment. CASP9 targets are used to generate the features for local quality assessment. We evaluate the performance of our local quality assessment method on CASP10, which is comparable with two stage-of-art QA methods based on the average absolute distance between the real and predicted distance. In addition, we blindly tested our method on CASP11, and the good performance shows that combining single and multiple model quality assessment method could be a good way to improve the accuracy of model quality assessment, and the random forest technique could be used to train a good local quality assessment model.