2014
DOI: 10.1186/s12859-014-0401-3
|View full text |Cite
|
Sign up to set email alerts
|

MCMC implementation of the optimal Bayesian classifier for non-Gaussian models: model-based RNA-Seq classification

Abstract: BackgroundSequencing datasets consist of a finite number of reads which map to specific regions of a reference genome. Most effort in modeling these datasets focuses on the detection of univariate differentially expressed genes. However, for classification, we must consider multiple genes and their interactions.ResultsThus, we introduce a hierarchical multivariate Poisson model (MP) and the associated optimal Bayesian classifier (OBC) for classifying samples using sequencing data. Lacking closed-form solutions… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
24
0

Year Published

2015
2015
2022
2022

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 25 publications
(24 citation statements)
references
References 39 publications
0
24
0
Order By: Relevance
“…Following [4], we model the cellular mRNA concentrations using a log-normal distribution. The sequencing instrument is then assumed to sample the RNA concentrations through a Poisson process resulting in X i,j reads for sample i and gene j .…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…Following [4], we model the cellular mRNA concentrations using a log-normal distribution. The sequencing instrument is then assumed to sample the RNA concentrations through a Poisson process resulting in X i,j reads for sample i and gene j .…”
Section: Methodsmentioning
confidence: 99%
“…Justification for this choice and the values of hyperparameters ν, η, κ , and S are explained in [4]. …”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…In this section we consider robustness with respect to the hyperparameters. While prior construction is outside the domain of the present paper, it is important to note that this issue has been addressed for genomic classification in three settings: gene networks with Gaussian regulation [29], gene networks with discrete regulation [30], and gene sequencing where neither Gaussian nor multinomial modeling can be applied and MCMC methods are required [31].…”
Section: Robustness With Respect To Prior Distributionsmentioning
confidence: 99%
“…The hierarchical model is not as restrictive as the simple Poisson model and can be considered as a compromise between the Poisson and negative binomial models in the small-sample setting. 8 The simulated NGS data follow a conditionally Poisson distribution, and the marginal distribution of the data is a mixture of Poisson and Gaussian distributions.…”
Section: Cancer Informaticsmentioning
confidence: 99%