B-factor prediction in proteins using a sequence-based deep learning model

Akash Pandey; Elaine Liu; Jacob Graham; Wei Chen; Sinan Keten

doi:10.1016/j.patter.2023.100805

B-factor prediction in proteins using a sequence-based deep learning model

Patterns (N Y). 2023 Aug 4;4(9):100805. doi: 10.1016/j.patter.2023.100805. eCollection 2023 Sep 8.

Authors

Akash Pandey¹, Elaine Liu¹, Jacob Graham¹, Wei Chen¹, Sinan Keten^{1

2}

Affiliations

¹ Department of Mechanical Engineering, Northwestern University, Evanston, IL, USA.
² Department of Civil and Environmental Engineering, Northwestern University, Evanston, IL, USA.

Abstract

B factors provide critical insight into protein dynamics. Predicting B factors of an atom in new proteins remains challenging as it is impacted by their neighbors in Euclidean space. Previous learning methods developed have resulted in low Pearson correlation coefficients beyond the training set due to their limited ability to capture the effect of neighboring atoms. With the advances in deep learning methods, we develop a sequence-based model that is tested on 2,442 proteins and outperforms the state-of-the-art models by 30%. We find that the model learns that the B factor of a site is prominently affected by atoms within a 12-15 Å radius, which is in excellent agreement with cutoffs from protein network models. The ablation study revealed that the B factor can largely be predicted from the primary sequence alone. Based on the abovementioned points, our model lays a foundation for predicting other properties that are correlated with the B factor.