SAAFEC-SEQ: A Sequence-Based Method for Predicting the Effect of Single Point Mutations on Protein Thermodynamic Stability

Gen Li,Shailesh Kumar Panday,Emil Alexov

doi:10.3390/ijms22020606

Gen Li, Shailesh Kumar Panday + Show 1 more

Open Access

https://doi.org/10.3390/ijms22020606

Copy DOI

Abstract

Modeling the effect of mutations on protein thermodynamics stability is useful for protein engineering and understanding molecular mechanisms of disease-causing variants. Here, we report a new development of the SAAFEC method, the SAAFEC-SEQ, which is a gradient boosting decision tree machine learning method to predict the change of the folding free energy caused by amino acid substitutions. The method does not require the 3D structure of the corresponding protein, but only its sequence and, thus, can be applied on genome-scale investigations where structural information is very sparse. SAAFEC-SEQ uses physicochemical properties, sequence features, and evolutionary information features to make the predictions. It is shown to consistently outperform all existing state-of-the-art sequence-based methods in both the Pearson correlation coefficient and root-mean-squared-error parameters as benchmarked on several independent datasets. The SAAFEC-SEQ has been implemented into a web server and is available as stand-alone code that can be downloaded and embedded into other researchers’ code.

Highlights

Proteins carry their function by adopting a particular 3D structure and the ability to fold into a 3D structure is governed by the folding free energy
Computational approaches that can accurately predict the change of the folding free energy (∆∆G) caused by mutations are highly desirable [5,6]
The Single Amino Acid Folding free Energy Changes (SAAFEC)-SEQ comes as a standhttp://compbio.clemson.edu/SAAFEC-SEQ/index.php

Summary

Introduction

Proteins carry their function by adopting a particular 3D structure and the ability to fold into a 3D structure is governed by the folding free energy. Assessing the effect of amino acid mutations on the folding free energy (∆∆G) is essential for evaluating the effect of mutations on structural stability of proteins [1,2]. While experimental investigations are preferred, they are too expensive and time consuming to be applied on a large number of cases [3,4]. Computational approaches that can accurately predict the change of the folding free energy (∆∆G) caused by mutations are highly desirable [5,6]

Methods

Results

Conclusion