A Deep-Learning Sequence-Based Method to Predict Protein Stability Changes Upon Genetic Variations

Several studies have linked disruptions of protein stability and its normal functions to disease. Therefore, during the last few decades, many tools have been developed to predict the free energy changes upon protein residue variations. Most of these methods require both sequence and structure information to obtain reliable predictions. However, the lower number of protein structures available with respect to their sequences, due to experimental issues, drastically limits the application of these tools. In addition, current methodologies ignore the antisymmetric property characterizing the thermodynamics of the protein stability: a variation from wild-type to a mutated form of the protein structure (X-W -> X-M) and its reverse process (X-M -> X-W) must have opposite values of the free energy difference (Delta Delta G(WM) = -Delta Delta G(MW)). Here we propose ACDC-NN-Seq, a deep neural network system that exploits the sequence information and is able to incorporate into its architecture the antisymmetry property. To our knowledge, this is the first convolutional neural network to predict protein stability changes relying solely on the protein sequence. We show that ACDC-NN-Seq compares favorably with the existing sequence-based methods.

Automated summary

Multiple studies have linked disruptions in protein stability to diseases, leading to the development of tools to predict free energy changes upon protein residue variations. However, the lower number of available protein structures compared to sequences limits the application of these tools. The proposed ACDC-NN-Seq is the first convolutional neural network to predict protein stability changes solely based on protein sequence and shows promising results compared to existing methods.