processProposalWindows

Internal function to check that the proposal windows passed to
MDI are of the expected type. If the default is used then the GP
hyper-parameters have proposal windows 0.125 (ampltidue), 0.15 (length-scale),
and 0.1 (noise).

Integrative clustering and semi-supervised prediction.
This package includes a 'C++' implementation of both semi-supervised and
unsupervised Multiple Dataset Integration (MDI; Kirk et al., 2012
<https://doi-org.ezp.lib.cam.ac.uk/10.1093/bioinformatics/bts595>), an
extension of Bayesian mixture models to the integrative (multiple dataset or
multi-modal) setting such as multi-omics analysis. The package also includes
Bayesian mixture models. Densities allowed within MDI and the mixture model
are Gaussian with full and diagonal covariance matrices, categorical, Gaussian
with a Gaussian process (GP) prior on the mean parameter. The GP model
implemented canonly handle data with common time points of equal separation.
The Gaussian and GP models can be augmented with a global multivariate t
distribution to handle outliers.

Stephen Coleman

mdir

Bayesian Model-Based Clustering of Multi-Modal Data

Paul Kirk

Chris Wallace

Oliver Crook

processProposalWindows function

<dl><dt>proposal_windows</dt>
<dd>List of the proposal windows for the Metropolis-Hastings
sampling of Gaussian process hyperparameters. Each entry corresponds to a
view. For views modelled using a Gaussian process, the first entry is the
proposal window for the ampltiude, the second is for the length-scale and the
third is for the noise. These are not used in other mixture types.</dd>
<dt>types</dt>
<dd>Character vector indicating density types to use. 'G' (Gaussian
with diagonal covariance matrix) 'MVN' (multivariate normal), 'TAGM'
(t-adjust Gaussian mixture), 'GP' (MVN with Gaussian process prior on the
mean), 'TAGPM' (TAGM with GP prior on the mean), 'C' (categorical).</dd></dl>

Arguments

Process proposal windows — processProposalWindows

<dl>

<dt>proposal_windows</dt>
<dd>List of the proposal windows for the Metropolis-Hastings
sampling of Gaussian process hyperparameters. Each entry corresponds to a
view. For views modelled using a Gaussian process, the first entry is the
proposal window for the ampltiude, the second is for the length-scale and the
third is for the noise. These are not used in other mixture types.</dd>


<dt>types</dt>
<dd>Character vector indicating density types to use. 'G' (Gaussian
with diagonal covariance matrix) 'MVN' (multivariate normal), 'TAGM'
(t-adjust Gaussian mixture), 'GP' (MVN with Gaussian process prior on the
mean), 'TAGPM' (TAGM with GP prior on the mean), 'C' (categorical).</dd>

</dl>

processProposalWindows: Process proposal windows

Description

Usage

Value

Arguments

Examples