Dataset Information

A hierarchical Naive Bayes Model for handling sample heterogeneity in classification problems: an application to tissue microarrays.

ABSTRACT:

Background

Uncertainty often affects molecular biology experiments and data for different reasons. Heterogeneity of gene or protein expression within the same tumor tissue is an example of biological uncertainty which should be taken into account when molecular markers are used in decision making. Tissue Microarray (TMA) experiments allow for large scale profiling of tissue biopsies, investigating protein patterns characterizing specific disease states. TMA studies deal with multiple sampling of the same patient, and therefore with multiple measurements of same protein target, to account for possible biological heterogeneity. The aim of this paper is to provide and validate a classification model taking into consideration the uncertainty associated with measuring replicate samples.

Results

We propose an extension of the well-known Naïve Bayes classifier, which accounts for biological heterogeneity in a probabilistic framework, relying on Bayesian hierarchical models. The model, which can be efficiently learned from the training dataset, exploits a closed-form of classification equation, thus providing no additional computational cost with respect to the standard Naïve Bayes classifier. We validated the approach on several simulated datasets comparing its performances with the Naïve Bayes classifier. Moreover, we demonstrated that explicitly dealing with heterogeneity can improve classification accuracy on a TMA prostate cancer dataset.

Conclusion

The proposed Hierarchical Naïve Bayes classifier can be conveniently applied in problems where within sample heterogeneity must be taken into account, such as TMA experiments and biological contexts where several measurements (replicates) are available for the same biological sample. The performance of the new approach is better than the standard Naïve Bayes model, in particular when the within sample heterogeneity is different in the different classes.

SUBMITTER: Demichelis F

PROVIDER: S-EPMC1698579 | biostudies-literature | 2006 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A hierarchical Naïve Bayes Model for handling sample heterogeneity in classification problems: an application to tissue microarrays.

Demichelis Francesca F Magni Paolo P Piergiorgi Paolo P Rubin Mark A MA Bellazzi Riccardo R

BMC bioinformatics 20061124

<h4>Background</h4>Uncertainty often affects molecular biology experiments and data for different reasons. Heterogeneity of gene or protein expression within the same tumor tissue is an example of biological uncertainty which should be taken into account when molecular markers are used in decision making. Tissue Microarray (TMA) experiments allow for large scale profiling of tissue biopsies, investigating protein patterns characterizing specific disease states. TMA studies deal with multiple sam ...[more]

PMID: 17125514

Similar Datasets

Project description:Verbal autopsy (VA) deals with post-mortem surveys about deaths, mostly in low and middle income countries, where the majority of deaths occur at home rather than a hospital, for retrospective assignment of causes of death (COD) and subsequently evidence-based health system strengthening. Automated algorithms for VA COD assignment have been developed and their performance has been assessed against physician and clinical diagnoses. Since the performance of automated classification methods remains low, we aimed to enhance the Naïve Bayes Classifier (NBC) algorithm to produce better ranked COD classifications on 26,766 deaths from four globally diverse VA datasets compared to some of the leading VA classification methods, namely Tariff, InterVA-4, InSilicoVA and NBC. We used a different strategy, by training multiple NBC algorithms using the one-against-all approach (OAA-NBC). To compare performance, we computed the cumulative cause-specific mortality fraction (CSMF) accuracies for population-level agreement from rank one to five COD classifications. To assess individual-level COD assignments, cumulative partially-chance corrected concordance (PCCC) and sensitivity was measured for up to five ranked classifications. Overall results show that OAA-NBC consistently assigns CODs that are the most alike physician and clinical COD assignments compared to some of the leading algorithms based on the cumulative CSMF accuracy, PCCC and sensitivity scores. The results demonstrate that our approach improves the performance of classification (sensitivity) by between 6% and 8% compared with other VA algorithms. Population-level agreements for OAA-NBC and NBC were found to be similar or higher than the other algorithms used in the experiments. Although OAA-NBC still requires improvement for individual-level COD assignment, the one-against-all approach improved its ability to assign CODs that more closely resemble physician or clinical COD classifications compared to some of the other leading VA classifiers.

Project description:MotivationIntrinsically disordered regions of proteins play an essential role in the regulation of various biological processes. Key to their regulatory function is often the binding to globular protein domains via sequence elements known as molecular recognition features (MoRFs). Development of computational tools for the identification of candidate MoRF locations in amino acid sequences is an important task and an area of growing interest. Given the relative sparseness of MoRFs in protein sequences, the accuracy of the available MoRF predictors is often inadequate for practical usage, which leaves a significant need and room for improvement. In this work, we introduce MoRFCHiBi_Web, which predicts MoRF locations in protein sequences with higher accuracy compared to current MoRF predictors.MethodsThree distinct and largely independent property scores are computed with component predictors and then combined to generate the final MoRF propensity scores. The first score reflects the likelihood of sequence windows to harbour MoRFs and is based on amino acid composition and sequence similarity information. It is generated by MoRFCHiBi using small windows of up to 40 residues in size. The second score identifies long stretches of protein disorder and is generated by ESpritz with the DisProt option. Lastly, the third score reflects residue conservation and is assembled from PSSM files generated by PSI-BLAST. These propensity scores are processed and then hierarchically combined using Bayes rule to generate the final MoRFCHiBi_Web predictions.ResultsMoRFCHiBi_Web was tested on three datasets. Results show that MoRFCHiBi_Web outperforms previously developed predictors by generating less than half the false positive rate for the same true positive rate at practical threshold values. This level of accuracy paired with its relatively high processing speed makes MoRFCHiBi_Web a practical tool for MoRF prediction.Availabilityhttp://morf.chibi.ubc.ca:8080/morf/.