EASE-MM: Sequence-Based Prediction of Mutation-Induced Stability Changes with Feature-Based Multiple Models. Issue 6 (27th March 2016)

• Record Type: Journal Article
• Authors: Folkman, Lukas; Stantic, Bela; Sattar, Abdul; Zhou, Yaoqi
• Is Part Of: Journal of molecular biology. Volume 428:Issue 6(2016:Mar. 27)
• Page Start: 1394
• Page End: 1405
• Publication Date: 2016-03-27
• Subjects: missense mutation -- amino acid substitution -- non-synonymous SNV -- free energy change -- machine learning; AF allele frequency -- ASA accessible surface area -- PSSM position-specific scoring matrix -- rASA relative accessible surface area -- RMSE root-mean-square error -- SFFS sequential forward floating selection -- SNV single nucleotide variant -- SS secondary structure -- SVM support vector machine -- SVR support vector regression; Molecular biology -- Periodicals; Biology -- Periodicals; Biochemistry -- Periodicals; Bacteriology -- Periodicals; Molecular Biology -- Periodicals; Biochemistry -- Periodicals; Biologie moléculaire -- Périodiques; Biologie -- Périodiques; Biochimie -- Périodiques; Moleculaire biologie; Biochemistry; Biology; Molecular biology; Periodicals; 572.805
• DOI: 10.1016/j.jmb.2016.01.012
• Languages: English
• ISSNs: 0022-2836

Abstract

Abstract: Protein engineering and characterisation of non-synonymous single nucleotide variants (SNVs) require accurate prediction of protein stability changes (ΔΔ G u ) induced by single amino acid substitutions. Here, we have developed a new prediction method called Evolutionary, Amino acid, and Structural Encodings with Multiple Models (EASE-MM), which comprises five specialised support vector machine (SVM) models and makes the final prediction from a consensus of two models selected based on the predicted secondary structure and accessible surface area of the mutated residue. The new method is applicable to single-domain monomeric proteins and can predict ΔΔ G u with a protein sequence and mutation as the only inputs. EASE-MM yielded a Pearson correlation coefficient of 0.53–0.59 in 10-fold cross-validation and independent testing and was able to outperform other sequence-based methods. When compared to structure-based energy functions, EASE-MM achieved a comparable or better performance. The application to a large dataset of human germline non-synonymous SNVs showed that the disease-causing variants tend to be associated with larger magnitudes of ΔΔ G u predicted with EASE-MM. The EASE-MM web-server is available at http://sparks-lab.org/server/ease . Graphical abstract: Highlights: Prediction of protein stability changes (ΔΔ G u ) is essential for protein engineering as well as for improved prioritisation of non-synonymous single nucleotide variants (SNVs). We have developed a method (EASE-MM) which combines multiple specialised machine learning models to predict ΔΔ G u from the protein sequence alone. The new method yields higher prediction accuracy than other sequence-based methods and achieves a performance comparable to or better than structure-based energy functions. EASE-MM, being a sequence-based method, can be applied to most single-domain monomeric proteins encoded in the human or other genomes for improved characterisation of disease-causing mutations that are shown to associate with larger magnitudes of ΔΔ G u predicted with EASE-MM.