MAESTRO - multi agent stability prediction upon point mutations

Abstract

BackgroundPoint mutations can have a strong impact on protein stability. A change in stability may subsequently lead to dysfunction and finally cause diseases. Moreover, protein engineering approaches aim to deliberately modify protein properties, where stability is a major constraint. In order to support basic research and protein design tasks, several computational tools for predicting the change in stability upon mutations have been developed. Comparative studies have shown the usefulness but also limitations of such programs.ResultsWe aim to contribute a novel method for predicting changes in stability upon point mutation in proteins called MAESTRO. MAESTRO is structure based and distinguishes itself from similar approaches in the following points: (i) MAESTRO implements a multi-agent machine learning system. (ii) It also provides predicted free energy change (Δ ΔG) values and a corresponding prediction confidence estimation. (iii) It provides high throughput scanning for multi-point mutations where sites and types of mutation can be comprehensively controlled. (iv) Finally, the software provides a specific mode for the prediction of stabilizing disulfide bonds. The predictive power of MAESTRO for single point mutations and stabilizing disulfide bonds is comparable to similar methods.ConclusionsMAESTRO is a versatile tool in the field of stability change prediction upon point mutations. Executables for the Linux and Windows operating systems are freely available to non-commercial users from http://biwww.che.sbg.ac.at/MAESTRO.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0548-6) contains supplementary material, which is available to authorized users.

Variation Interpretation Predictors: Principles, Types, Performance, and Choice

“…The empirical potential methods combine and weigh physical and statistical energy components together with, for example, structure-related features [Guerois et al, 2002]. Some methods have also combined ML and energy function for stability prediction [Dehouck et al, 2009;Masso and Vaisman, 2010;Laimer et al, 2015].…”

“…It is evident that different features are important for tolerance and stability predictors. Some methods combine both ML algorithms as well as energy functions [Dehouck et al, 2009;Masso and Vaisman, 2010;Laimer et al, 2015]. While most of the methods predict the stability changes for individual variations, some predict the combined effect of variation pairs [Huang and Gromiha, 2009].…”

Allergens of <b><i>Blomia tropicalis</i></b>: An Overview of Recombinant Molecules

“…For the remaining allergens, models were calculated by comparative modeling using MODELLER software [51]. In case of nuclear magnetic resonance PDB entries, the model scoring function of MAESTRO was employed [112] to select a representative template structure. With MODELLER, 5 model variants were generated.…”

Structural effects of point mutations in proteins

“…( ) for a very interesting review on protein structural bioinformatics]. Many algorithms and web servers have been developed to provide estimation of the variation of the Gibbs‐free energy upon the effect of a given point mutation, such as FoldX, I‐Mutant, PoPMusic, Maestro, Cupsat, mCSM, NeEMO, Strum, Rosetta, or SPROUTS which is a web server combining the results of several methods. The Gibbs free energy estimations are scaled with experimental measures of the stability (ΔΔ G ) recorded in the Protherm database .…”