Next Article in Journal
Adropin Slightly Modulates Lipolysis, Lipogenesis and Expression of Adipokines but Not Glucose Uptake in Rodent Adipocytes
Previous Article in Journal
The Development of Herbicide Resistance Crop Plants Using CRISPR/Cas9-Mediated Gene Editing
Article

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

1
Department of Medical Science, University of Turin, Via Santena 19, 10126 Torino, Italy
2
Department of Pharmacy and Biotechnology (FaBiT), University of Bologna, Via Francesco Selmi 3, 40126 Bologna, Italy
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Quan Zou
Genes 2021, 12(6), 911; https://doi.org/10.3390/genes12060911
Received: 14 May 2021 / Revised: 8 June 2021 / Accepted: 9 June 2021 / Published: 12 June 2021
(This article belongs to the Section Technologies and Resources for Genetics)
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 (XWXM) and its reverse process (XMXW) must have opposite values of the free energy difference (ΔΔGWM=ΔΔGMW). 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. View Full-Text
Keywords: deep learning; protein stability; free energy changes; antisymmetry; ACDC; sequence deep learning; protein stability; free energy changes; antisymmetry; ACDC; sequence
Show Figures

Figure 1

MDPI and ACS Style

Pancotti, C.; Benevenuta, S.; Repetto, V.; Birolo, G.; Capriotti, E.; Sanavia, T.; Fariselli, P. A Deep-Learning Sequence-Based Method to Predict Protein Stability Changes Upon Genetic Variations. Genes 2021, 12, 911. https://doi.org/10.3390/genes12060911

AMA Style

Pancotti C, Benevenuta S, Repetto V, Birolo G, Capriotti E, Sanavia T, Fariselli P. A Deep-Learning Sequence-Based Method to Predict Protein Stability Changes Upon Genetic Variations. Genes. 2021; 12(6):911. https://doi.org/10.3390/genes12060911

Chicago/Turabian Style

Pancotti, Corrado, Silvia Benevenuta, Valeria Repetto, Giovanni Birolo, Emidio Capriotti, Tiziana Sanavia, and Piero Fariselli. 2021. "A Deep-Learning Sequence-Based Method to Predict Protein Stability Changes Upon Genetic Variations" Genes 12, no. 6: 911. https://doi.org/10.3390/genes12060911

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop