Fast and accurate predictions of protein stability changes upon mutations using statistical potentials and neural networks: PoPMuSiC-2.0

By Yves Dehouck, Aline Grosfils, B. Folch, Dimitri Gilis, P. Bogaerts, Marianne Rooman. 2009

399 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Better prediction of functional effects for sequence variants (2015, neutral): “Some tools are focused on non-coding regions [2-4]; others focus on coding regions and predict the effects of single amino acid variants (non-synonymous single-nucleotide polymorphisms, nsSNPs, or single amino acid substitutions, SAAS) on aspects such as protein structure [5], stability [6-8], bindi”
DUET: a server for predicting effects of mutations on protein stability using an integrated computational approach (2014, methodology): “The training set is formed by 2297 randomly selected mutations drawn from the S2848 data set used by the PoPMuSiC method (13).”
Machine learning in protein engineering (2018, background): “…machine-learning models to predict the effects of mutations on stability (Tian et al., 2010; Li & Fang, 2012; Jia et al., 2015; Capriotti et al., 2005b;a; Cheng et al., 2006; Buske et al., 2009; Liu & Kang, 2012; Pires et al., 2013; Jokinen et al., 2018; Dehouck et al., 2009; Giollo et al., 2014).”
Design of novel FN3 domains with high stability by a consensus sequence approach. (2012, neutral): “0 (Dehouck et al., 2009).”
STRUM: structure-based prediction of protein stability changes upon single-point mutation (2016, methodology): “…native structure of the wild-type protein and had the DD G calculated by a linear combination of 13 knowledge-based terms on the protein structure, which resulted in a correlation of 0.8 between predicted and measured stability changes after exclusion of 10% outliers (Dehouck et al. , 2009, 2011).”
WS-SNPs&GO: a web server for predicting the deleterious effect of human protein variants using functional annotation (2013, background): “Thus, during the last few years, several methods have been developed to predict the impact of nsSNPs on protein stability [10-16], protein function [17,18] and to detect their pathologic effect [19-29].”
PoPMuSiC 2.1: a web server for the estimation of protein stability changes upon mutation and sequence optimality (2011, methodology): “More recently, approaches combining the advantages of statistical energy functions and machine learning tools have also been described [28,29].”
BeAtMuSiC: prediction of changes in protein–protein binding affinity on mutations (2013, methodology): “The weights (cid:2) i ðAÞ ( i ¼ 1 , . . . , 16) are sigmoid functions of the solvent accessibility A of the mutated residue, and were identiﬁed on the basis of a data set of experimentally measured changes in folding free energy resulting from 2648 mutations (42).”
Contact Potential for Structure Prediction of Proteins and Protein Complexes from Potts Model. (2018, methodology): “To evaluate applicability of the contact potentials to prediction of the change in the folding free energy DDG upon mutations, we used a data set of 2648 point mutations for 131 globular proteins with experimentally resolved x-ray or NMR structure, for which mutation-induced change in protein stabil”
mCSM: predicting the effects of mutations in proteins using graph-based signatures (2013, methodology): “We have also applied our methodology to predict changes of stability resulting from mutations occurring in the tumour suppressor protein p53. mCSM outperforms other methods, demonstrating its applicability to understanding mutations that lead to disease.”
Predicting changes in protein thermodynamic stability upon point mutation with deep 3D convolutional neural networks (2020, methodology): “For example, a recent method used 167 randomly selected subsets of mutants from the widely used S2648 data set for training and 168 testing (34).”