21
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Improving the prediction of disease-related variants using protein three-dimensional structure

      research-article
      1 , 3 , , 1 , 2
      BMC Bioinformatics
      BioMed Central
      ECCB 2010 Workshop: Annotation interpretation and management of mutations (AIMM)
      2692010

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Single Nucleotide Polymorphisms (SNPs) are an important source of human genome variability. Non-synonymous SNPs occurring in coding regions result in single amino acid polymorphisms (SAPs) that may affect protein function and lead to pathology. Several methods attempt to estimate the impact of SAPs using different sources of information. Although sequence-based predictors have shown good performance, the quality of these predictions can be further improved by introducing new features derived from three-dimensional protein structures.

          Results

          In this paper, we present a structure-based machine learning approach for predicting disease-related SAPs. We have trained a Support Vector Machine (SVM) on a set of 3,342 disease-related mutations and 1,644 neutral polymorphisms from 784 protein chains. We use SVM input features derived from the protein’s sequence, structure, and function. After dataset balancing, the structure-based method (SVM-3D) reaches an overall accuracy of 85%, a correlation coefficient of 0.70, and an area under the receiving operating characteristic curve (AUC) of 0.92. When compared with a similar sequence-based predictor, SVM-3D results in an increase of the overall accuracy and AUC by 3%, and correlation coefficient by 0.06. The robustness of this improvement has been tested on different datasets and in all the cases SVM-3D performs better than previously developed methods even when compared with PolyPhen2, which explicitly considers in input protein structure information.

          Conclusion

          This work demonstrates that structural information can increase the accuracy of disease-related SAPs identification. Our results also quantify the magnitude of improvement on a large dataset. This improvement is in agreement with previously observed results, where structure information enhanced the prediction of protein stability changes upon mutation. Although the structural information contained in the Protein Data Bank is limiting the application and the performance of our structure-based method, we expect that SVM-3D will result in higher accuracy when more structural date become available.

          Related collections

          Most cited references28

          • Record: found
          • Abstract: found
          • Article: not found

          Human non-synonymous SNPs: server and survey.

          Human single nucleotide polymorphisms (SNPs) represent the most frequent type of human population DNA variation. One of the main goals of SNP research is to understand the genetics of the human phenotype variation and especially the genetic basis of human complex diseases. Non-synonymous coding SNPs (nsSNPs) comprise a group of SNPs that, together with SNPs in regulatory regions, are believed to have the highest impact on phenotype. Here we present a World Wide Web server to predict the effect of an nsSNP on protein structure and function. The prediction method enabled analysis of the publicly available SNP database HGVbase, which gave rise to a dataset of nsSNPs with predicted functionality. The dataset was further used to compare the effect of various structural and functional characteristics of amino acid substitutions responsible for phenotypic display of nsSNPs. We also studied the dependence of selective pressure on the structural and functional properties of proteins. We found that in our dataset the selection pressure against deleterious SNPs depends on the molecular function of the protein, although it is insensitive to several other protein features considered. The strongest selective pressure was detected for proteins involved in transcription regulation.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            The worldwide Protein Data Bank (wwPDB): ensuring a single, uniform archive of PDB data

            The worldwide Protein Data Bank (wwPDB) is the international collaboration that manages the deposition, processing and distribution of the PDB archive. The online PDB archive is a repository for the coordinates and related information for more than 38 000 structures, including proteins, nucleic acids and large macromolecular complexes that have been determined using X-ray crystallography, NMR and electron microscopy techniques. The founding members of the wwPDB are RCSB PDB (USA), MSD-EBI (Europe) and PDBj (Japan) [H.M. Berman, K. Henrick and H. Nakamura (2003) Nature Struct. Biol., 10, 980]. The BMRB group (USA) joined the wwPDB in 2006. The mission of the wwPDB is to maintain a single archive of macromolecular structural data that are freely and publicly available to the global community. Additionally, the wwPDB provides a variety of services to a broad community of users. The wwPDB website at provides information about services provided by the individual member organizations and about projects undertaken by the wwPDB.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Automated inference of molecular mechanisms of disease from amino acid substitutions.

              Advances in high-throughput genotyping and next generation sequencing have generated a vast amount of human genetic variation data. Single nucleotide substitutions within protein coding regions are of particular importance owing to their potential to give rise to amino acid substitutions that affect protein structure and function which may ultimately lead to a disease state. Over the last decade, a number of computational methods have been developed to predict whether such amino acid substitutions result in an altered phenotype. Although these methods are useful in practice, and accurate for their intended purpose, they are not well suited for providing probabilistic estimates of the underlying disease mechanism. We have developed a new computational model, MutPred, that is based upon protein sequence, and which models changes of structural features and functional sites between wild-type and mutant sequences. These changes, expressed as probabilities of gain or loss of structure and function, can provide insight into the specific molecular mechanism responsible for the disease state. MutPred also builds on the established SIFT method but offers improved classification accuracy with respect to human disease mutations. Given conservative thresholds on the predicted disruption of molecular function, we propose that MutPred can generate accurate and reliable hypotheses on the molecular basis of disease for approximately 11% of known inherited disease-causing mutations. We also note that the proportion of changes of functionally relevant residues in the sets of cancer-associated somatic mutations is higher than for the inherited lesions in the Human Gene Mutation Database which are instead predicted to be characterized by disruptions of protein structure. http://mutdb.org/mutpred predrag@indiana.edu; smooney@buckinstitute.org.
                Bookmark

                Author and article information

                Conference
                BMC Bioinformatics
                BMC Bioinformatics
                BioMed Central
                1471-2105
                2011
                5 July 2011
                : 12
                : Suppl 4
                : S3
                Affiliations
                [1 ]Department of Bioengineering, Stanford University, Stanford CA, USA
                [2 ]Department Genetics, Stanford University, Stanford CA, USA
                [3 ]Department of Mathematics and Computer Science, University of Balearic Islands, Palma de Mallorca, Spain
                Article
                1471-2105-12-S4-S3
                10.1186/1471-2105-12-S4-S3
                3194195
                21992054
                0e90b3f5-1ed6-471a-bcf8-2f28af7f20fd
                Copyright ©2011 Capriotti; licensee BioMed Central Ltd.

                This is an open access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

                ECCB 2010 Workshop: Annotation interpretation and management of mutations (AIMM)
                Ghent, Belgium
                2692010
                History
                Categories
                Research

                Bioinformatics & Computational biology
                Bioinformatics & Computational biology

                Comments

                Comment on this article