run_deconvolution

Perform deconvolution on a new set of samples, based on the CimpleG models trained

DNA methylation signatures are usually based on multivariate
approaches that require hundreds of sites for predictions. 'CimpleG'
is a method for the detection of small CpG methylation signatures used
for cell-type classification and deconvolution. 'CimpleG' is time
efficient and performs as well as top performing methods for cell-type
classification of blood cells and other somatic cells, while basing
its prediction on a single DNA methylation site per cell type (but
users can also select more sites if they so wish). Users can train
cell type classifiers ('CimpleG' based, and others) and directly apply
these in a deconvolution of cell mixes context. Altogether, 'CimpleG'
provides a complete computational framework for the delineation of
DNAm signatures and cellular deconvolution. For more details see Maié
et al. (2023) <doi:10.1186/s13059-023-03000-0>.

Tiago F.V. Maié

CimpleG

A Method to Identify Single CpG Sites for Classification and
Deconvolution

run_deconvolution function

<dl><dt>cpg_obj</dt>
<dd>A CimpleG object. When creating/training CimpleG the parameter `deconvolution_reference` should be set to `TRUE`.</dd>
<dt>new_data</dt>
<dd>Matrix or data.frame that should have the samples you want to perform deconvolution on.
Samples should be in rows and probes/CpGs in columns.</dd>
<dt>ref_mat</dt>
<dd>If the CimpleG object does not have the reference matrix, you can provide it here instead. See `make_deconv_ref_matrix`</dd>
<dt>deconvolution_method</dt>
<dd>Deconvolution method to be used. One of #TODO</dd>
<dt>...</dt>
<dd>Extra parameters only used when deconvolution_method is set to `NMF`. The most relevant parameter are probably `method` and `beta`.</dd></dl>

Arguments

Perform deconvolution on a new set of samples, based on the CimpleG models trained — run_deconvolution

<dl>

<dt>cpg_obj</dt>
<dd>A CimpleG object. When creating/training CimpleG the parameter `deconvolution_reference` should be set to `TRUE`.</dd>


<dt>new_data</dt>
<dd>Matrix or data.frame that should have the samples you want to perform deconvolution on.
Samples should be in rows and probes/CpGs in columns.</dd>


<dt>ref_mat</dt>
<dd>If the CimpleG object does not have the reference matrix, you can provide it here instead. See `make_deconv_ref_matrix`</dd>


<dt>deconvolution_method</dt>
<dd>Deconvolution method to be used. One of #TODO</dd>


<dt>...</dt>
<dd>Extra parameters only used when deconvolution_method is set to `NMF`. The most relevant parameter are probably `method` and `beta`.</dd>

</dl>

run_deconvolution: Perform deconvolution on a new set of samples, based on the CimpleG models trained

Description

Usage

Value

Arguments