Dataset Information

Empirical Bayesian models for analysing molecular serotyping microarrays.

ABSTRACT:

Background

Microarrays offer great potential as a platform for molecular diagnostics, testing clinical samples for the presence of numerous biomarkers in highly multiplexed assays. In this study applied to infectious diseases, data from a microarray designed for molecular serotyping of Streptococcus pneumoniae was used, identifying the presence of any one of 91 known pneumococcal serotypes from DNA extracts. This microarray incorporated oligonucleotide probes for all known capsular polysaccharide synthesis genes and required a statistical analysis of the microarray intensity data to determine which serotype, or combination of serotypes, were present within a sample based on the combination of genes detected.

Results

We propose an empirical Bayesian model for calculating the probabilities of combinations of serotypes from the microarray data. The model takes into consideration the dependencies between serotypes, induced by genes they have in common, and by homologous genes which, although not identical, are similar to each other in sequence. For serotypes which are very similar in capsular gene composition, extra probes are included on the microarray, providing additional information which is integrated into the Bayesian model. For each serotype combination with high probability, a second model, a Bayesian random effects model is applied to determine the relative abundance of each serotype.

Conclusions

To assess the accuracy of the proposed analysis we applied our methods to experimental data from samples containing individual serotypes and samples containing combinations of serotypes with known levels of abundance. All but two of the known serotypes of S. pneumoniae that were tested as individual samples could be uniquely determined by the Bayesian model. The model also enabled the presence of combinations of serotypes within samples to be determined. Serotypes with very low abundance within a combination of serotypes can be detected (down to 2% abundance in this study). As well as detecting the presence of serotype combinations, an approximate measure of the percentage abundance of the serotypes within the combination can be obtained.

SUBMITTER: Newton R

PROVIDER: S-EPMC3076268 | biostudies-literature | 2011 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Empirical Bayesian models for analysing molecular serotyping microarrays.

Newton Richard R Hinds Jason J Wernisch Lorenz L

BMC bioinformatics 20110331

<h4>Background</h4>Microarrays offer great potential as a platform for molecular diagnostics, testing clinical samples for the presence of numerous biomarkers in highly multiplexed assays. In this study applied to infectious diseases, data from a microarray designed for molecular serotyping of Streptococcus pneumoniae was used, identifying the presence of any one of 91 known pneumococcal serotypes from DNA extracts. This microarray incorporated oligonucleotide probes for all known capsular polys ...[more]

PMID: 21453458

Similar Datasets

Project description:Streptococcus pneumoniae is a human pathogen that is a major cause of infant mortality. Identifying the pneumococcal serotype is an important step in monitoring the impact of vaccines used to protect against disease. Genomic microarrays provide an effective method for molecular serotyping. Previously we developed an empirical Bayesian model for the classification of serotypes from a molecular serotyping array. With only few samples available, a model driven approach was the only option. In the meanwhile, several thousand samples have been made available to us, providing an opportunity to investigate serotype classification by machine learning methods, which could complement the Bayesian model.We compare the performance of the original Bayesian model with two machine learning algorithms: Gradient Boosting Machines and Random Forests. We present our results as an example of a generic strategy whereby a preliminary probabilistic model is complemented or replaced by a machine learning classifier once enough data are available. Despite the availability of thousands of serotyping arrays, a problem encountered when applying machine learning methods is the lack of training data containing mixtures of serotypes; due to the large number of possible combinations. Most of the available training data comprises samples with only a single serotype. To overcome the lack of training data we implemented an iterative analysis, creating artificial training data of serotype mixtures by combining raw data from single serotype arrays.With the enhanced training set the machine learning algorithms out perform the original Bayesian model. However, for serotypes currently lacking sufficient training data the best performing implementation was a combination of the results of the Bayesian Model and the Gradient Boosting Machine. As well as being an effective method for classifying biological data, machine learning can also be used as an efficient method for revealing subtle biological insights, which we illustrate with an example.

Project description:Ninety-two Streptococcus pneumoniae serotypes have been described so far, but the pneumococcal conjugate vaccine introduced in the Brazilian basic vaccination schedule in 2010 covers only the ten most prevalent in the country. Pneumococcal serotype-shifting after massive immunization is a major concern and monitoring this phenomenon requires efficient and accessible serotyping methods. Pneumococcal serotyping based on antisera produced in animals is laborious and restricted to a few reference laboratories. Alternatively, molecular serotyping methods assess polymorphisms in the cps gene cluster, which encodes key enzymes for capsular polysaccharides synthesis in pneumococci. In one such approach, cps-RFLP, the PCR amplified cps loci are digested with an endonuclease, generating serotype-specific fingerprints on agarose gel electrophoresis.In this work, in silico and in vitro approaches were combined to demonstrate that XhoII is the most discriminating endonuclease for cps-RFLP, and to build a database of serotype-specific fingerprints that accommodates the genetic diversity within the cps locus of 92 known pneumococci serotypes.The expected specificity of cps-RFLP using XhoII was 76% for serotyping and 100% for serogrouping. The database of cps-RFLP fingerprints was integrated to Molecular Serotyping Tool (MST), a previously published web-based software for molecular serotyping. In addition, 43 isolates representing 29 serotypes prevalent in the state of Minas Gerais, Brazil, from 2007 to 2013, were examined in vitro; 11 serotypes (nine serogroups) matched the respective in silico patterns calculated for reference strains. The remaining experimental patterns, despite their resemblance to their expected in silico patterns, did not reach the threshold of similarity score to be considered a match and were then added to the database.The cps-RFLP method with XhoII outperformed the antisera-based and other molecular serotyping methods in regard of the expected specificity. In order to accommodate the genetic variability of the pneumococci cps loci, the database of cps-RFLP patterns will be progressively expanded to include new variant in vitro patterns. The cps-RFLP method with endonuclease XhoII coupled with MST for computer-assisted interpretation of results may represent a relevant contribution to the real time detection of changes in regional pneumococci population diversity in response to mass immunization programs.

Dataset Information

Empirical Bayesian models for analysing molecular serotyping microarrays.

Background

Results

Conclusions

Publications

Empirical Bayesian models for analysing molecular serotyping microarrays.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets