Ad
related to: duet bioinformatic toolNGS Data Analysis and Interpretation, Quickly and Securely – Ask for a Quote. Novel Scripts, Analysis Pipelines and Software Development– Find Out More
Search results
Here we present DUET, a web server for an integrated computational approach for studying missense mutations in proteins. DUET consolidates two complementary approaches (mCSM and SDM) in a consensus prediction, obtained by combining the results of the separate methods in an optimised predictor using Support Vector Machines (SVM).
- Introduction
- Materials and Methods
- Web Server
- Validation
- Results
- Conclusions
- Funding
In this era of high-throughput data generation, the ability to predict accurately the impacts of non-synonymous single nucleotide polymorphisms (nsSNPs) on protein stability is an essential tool for understanding the effects of human genome variation (1), particularly with respect to personalized medicine and the mechanisms of variable drug respons...
SDM
The method SDM, introduced in (7,14), relies on amino acid propensities derived from environment-specific substitution tables for homologous protein families that feed a statistical potential energy function and encompass an evolutionary view of the constraints from the immediate residue environment. The approach compares amino acid propensities for the wild-type and mutant proteins in the folded and unfolded states in order to estimate the free energy differences between wild type and mutant...
mCSM
mCSM is a machine learning method to predict the effects of missense mutations based on structural signatures (15). The mCSM signatures were derived from the graph-based concept of Cutoff Scanning Matrix (CSM) (19), originally proposed to represent network topology by distance patterns in the study of biological systems. mCSM uses a graph representation of the wild-type residue environment to extract geometric and physicochemical patterns (the last represented in terms of pharmacophores) that...
DUET-Integrated Computational Approach
Figure 1 shows the workflow of the developed methodology. Given a single point mutation in a protein structure, DUET calculates a combined/consensus prediction by combining the predictions from two methods (mCSM and SDM) in a non-linear way, using SVM regression with a Radial Basis Function kernel (22). In order to do so, complementary information regarding the mutation, such as secondary structure (used by SDM) and a pharmacophore vector that accounts for the changes between wild-type and mu...
Input
In order to run a prediction on the DUET server, the user submits a PDB structure or 4-letter code of the wild-type protein of interest, as well as the mutation information (residue position, wild-type and mutant residues codes in one-letter format) and chain identifier. Users also have the option to perform systematic mutations of a particular residue to all 19 possible mutants. DUET supports nuclear magnetic resonance structures but only the first model will be taken into account. Users are...
Output
As shown in Figure 2, the server displays in the output page the predictions from the individual methods, the combined/consensus prediction obtained by DUET and an interactive visualization of the uploaded PDB file via GLMol. This interface allows the user to visualize the protein with molecules represented in several ways, such as ‘cartoon’, ‘ball and stick’ and ‘spheres’ as well as to take snapshots. The predicted results are expressed as the variation in Gibbs Free Energy (ΔΔG) and negativ...
Mutation Data sets
DUET's regression model was trained on data for mutations derived from the ProTherm database (18) and used in a previous study (15). The training set is formed by 2297 randomly selected mutations drawn from the S2848 data set used by the PoPMuSiC method (13). To minimize the risk of overfitting, two blind test sets were devised to validate the method. The first data set was composed of 351 non-redundant mutations at position level, meaning that mutations in a given position are either in the...
Figure 3 shows regression analysis for the stability predictions generated by DUET in comparison with the experimentally measured variation in stability for the considered data sets. During training, DUET achieved a Pearson's correlation coefficient of r = 0.74 with a standard error of σ = 0.98 kcal/mol, significantly better than mCSM (r = 0.69, σ ...
DUET is an accurate, free and easy-to-use bioinformatics web server created for experts and non-experts alike who are interested in gaining insight into the effects of nsSNPs on protein stability. It integrates two complementary methods into a consensus/optimized prediction, as a way to leverage the best of SDM, a statistical potential energy funct...
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), Brazil (to D.E.V.P.); NHMRC CJ Martin Fellowship (GNT1072476), Victoria Fellowship from the Victorian Government and the Leslie (Les) J. Fleming Churchill Fellowship from the The Winston Churchill Memorial Trust (to D.B.A.); University of Cambridge and The Wellcome Trust for faci...
- Douglas E.V. Pires, David B. Ascher, Tom L. Blundell
- 2014
DUET predicts the change in protein stability (∆∆G) upon the introduction of a single mutation by combining two distinct previously published approaches: SDM : a statistical potential energy function developed by Topham et al. (1997) to predict the effect that single nucleotide polymorphisms will have on the stability of proteins.
If you want to add new tools please use the stable version avaliable at bio.tools. We're sorry but we couldn't find what you were looking for. You can try searching for the resource you need here .
Here we present DUET, a web server for an integrated computational approach to study missense mutations in proteins. DUET consolidates two complementary approaches (mCSM and SDM) in a consensus prediction, obtained by combining the results of the separate methods in an optimized predictor using Support Vector Machines (SVM).
- Douglas E.V. Pires, David B. Ascher, Tom L. Blundell
- 2014
DUET combines mCSM and SDM in a con-sensus prediction, by consolidating the results of the sepa-rate methods in an optimized predictor using Support Vec-tor Machines (SVMs) trained with Sequential Minimal Op-timization (17).
People also ask
What is duet – a web server?
How does duet predict protein stability?
What information is used in duet?
What are duet results?
May 14, 2014 · Here we present DUET, a web server for an integrated computational approach to study missense mutations in proteins. DUET consolidates two complementary approaches (mCSM and SDM) in a consensus...
