loading page

Combining Pairwise Structural Similarity and Deep Learning Interface Contact Prediction to Estimate Protein Complex Model Accuracy in CASP15
  • +2
  • Jianlin Cheng,
  • Raj Roy,
  • Jian Liu,
  • Nabin Giri,
  • Zhiye Guo
Jianlin Cheng
University of Missouri

Corresponding Author:[email protected]

Author Profile
Raj Roy
University of Missouri
Author Profile
Jian Liu
University of Missouri
Author Profile
Nabin Giri
University of Missouri
Author Profile
Zhiye Guo
University of Missouri
Author Profile

Abstract

Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural models are of low quality and similar to each other. To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. It blindly participated in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 and ranked first out of 24 predictors in estimating the global accuracy of assembly models. The average per-target correlation coefficient between the model quality scores predicted by MULTICOM_qa and the true quality scores of the models of CASP15 assembly targets is 0.66. The average per-target ranking loss in using the predicted quality scores to rank the models is 0.14. It was able to select good models for most targets. Moreover, several key factors (i.e., target difficulty, model sampling difficulty, skewness of model quality, and similarity between good/bad models) for EMA are identified and analayzed. The results demonstrate that combining the multi-model method (PSS) with the complementary single-model method (ICPS) is a promising approach to EMA.
13 Mar 2023Submitted to PROTEINS: Structure, Function, and Bioinformatics
13 Mar 2023Submission Checks Completed
13 Mar 2023Assigned to Editor
13 Mar 2023Review(s) Completed, Editorial Evaluation Pending
14 Mar 2023Reviewer(s) Assigned
12 Apr 2023Editorial Decision: Revise Major
15 May 20231st Revision Received
15 May 2023Submission Checks Completed
15 May 2023Assigned to Editor
15 May 2023Review(s) Completed, Editorial Evaluation Pending
15 May 2023Reviewer(s) Assigned
05 Jun 2023Editorial Decision: Revise Minor
08 Jun 20232nd Revision Received
08 Jun 2023Submission Checks Completed
08 Jun 2023Assigned to Editor
08 Jun 2023Review(s) Completed, Editorial Evaluation Pending
08 Jun 2023Editorial Decision: Accept