Journal Article

Rapid protein stability prediction using deep learning representations

Blaabjerg, Lasse M, Johansson, Kristoffer E, Jonsson, Nicolas, Boomsma, Wouter, Lindorff-Larsen, Kresten, Good, Lydia L, Stein, Amelie, Kassem, Maher M, Cagiada, Matteo

2023

Overview

Predicting the thermodynamic stability of proteins is a common and widely used step in protein engineering, and when elucidating the molecular mechanisms behind evolution and disease. Here, we present RaSP, a method for making rapid and accurate predictions of changes in protein stability by leveraging deep learning representations. RaSP performs on-par with biophysics-based methods and enables saturation mutagenesis stability predictions in less than a second per residue. We use RaSP to calculate ∼ 230 million stability changes for nearly all single amino acid changes in the human proteome, and examine variants observed in the human population. We find that variants that are common in the population are substantially depleted for severe destabilization, and that there are substantial differences between benign and pathogenic variants, highlighting the role of protein stability in genetic diseases. RaSP is freely available—including via a Web interface—and enables large-scale analyses of stability in experimental and predicted protein structures.

• Publisher: eLife Sciences Publications Ltd,eLife Sciences Publications, Ltd
• Subject: Amino acid sequence / Amino acids / Amino Acids - genetics / biophysics / Computational and Systems Biology / Computational Biology - methods / Datasets / Deep Learning / Genetic disorders / genomic variants / Humans / Learning / machine learning / Molecular modelling / Mutagenesis / Mutation / Neural networks / Predictions / Protein engineering / Protein Stability / Proteins / Proteins - metabolism / Proteomes / Saturation mutagenesis / Snow / Structural Biology and Molecular Biophysics / Tools and Resources