Detail publikace
Prediction of Critical Residues in Protein Structures using Amino Acid Networks
Martínek Tomáš, doc. Ing., Ph.D. (UPSY)
Bednář David (FIT)
Damborský Jiří, prof. Mgr., Dr. (UMEL)
For the engineering of improved proteins, it is important to know which residues in the protein sequence are important and whether their replacement will have a big influence on protein function, stability or other properties. Knowledge about critical residues can be used either for prediction of an impact of substitutions in protein sequence or for selecting the best spots in the protein for mutagenesis by site-directed techniques or directed evolution. Limitations of the traditional protein design tools like FoldX [1] or Rosetta [2] are their speed and accuracy particularly at the solvent exposed surfaces. The amino acid network analysis [3] is alternative to modelling the proteins using the force-field calculations and then selecting the most important amino acid residues based on the energies. An amino acid network is a graph derived from protein structure based on contacts or interactions between the residues. Our approach to prediction of critical amino acid residues is to create an amino acid network from a protein, compute network parameters, then add physico-chemical and biological properties of amino acids and use all these parameters as features for machine learning. Currently we are focusing on the residues critical for protein stability. We are using the dataset of 2893 mutations from 150 proteins with experimentally measured stabilities [4] for testing of our method. Our method is significantly faster and gives comparable results to the force-field calculations based on preliminary results. 1. Schymkowitz, J., Borg, J., Stricher, F., Nys, R., Rousseau, F. and Serrano, L. (2005) The FoldX web server: an online force field. Nucleic Acids Research, 33, W382-W388. 2. Kellogg, E.H., Leaver-Fay, A. and Baker, D. (2011) Role of conformational sampling in computing mutation-induced changes in protein structure and stability. Proteins, 79, 830-838. 3. Grewal, R., & Roy, S. (2015). Modeling proteins as residue interaction networks. Protein and Peptide Letters, 22, 923-933. FireProtDB: https://loschmidt.chemi.muni.cz/fireprotdb/.
@misc{BUT162278,
author="Lenka {Sumbalová} and Tomáš {Martínek} and David {Bednář} and Jiří {Damborský}",
title="Prediction of Critical Residues in Protein Structures using Amino Acid Networks",
booktitle="ISMB/ECCB 2019",
year="2019",
pages="1",
address="Basilej",
note="presentation, poster"
}