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 (XW → XM) and its reverse process (XM → XW) must have opposite values of the free energy difference (∆∆GWM = −∆∆GMW). 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.

A deep-learning sequence-based method to predict protein stability changes upon genetic variations

Pancotti C.;Benevenuta S.;Repetto V.;Birolo G.;Sanavia T.
Co-last
;
Fariselli P.
2021-01-01

Abstract

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 (XW → XM) and its reverse process (XM → XW) must have opposite values of the free energy difference (∆∆GWM = −∆∆GMW). 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.
2021
12
6
911
911
ACDC; Antisymmetry; Deep learning; Free energy changes; Protein stability; Sequence
Pancotti C.; Benevenuta S.; Repetto V.; Birolo G.; Capriotti E.; Sanavia T.; Fariselli P.
File in questo prodotto:
File Dimensione Formato  
genes-12-00911-v2.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 4.32 MB
Formato Adobe PDF
4.32 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1795390
Citazioni
  • ???jsp.display-item.citation.pmc??? 8
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 19
social impact