A Method to Identify Single CpG Sites for Classification and Deconvolution
CimpleG: A Method to Identify Single CpG Sites for Classification and ...
Find simple CpG (CimpleG) signatures.
Feature selection function used in the sigma delta space
Compute diff mean sum var dataframe
Helper function to darken down a given color.
Scatter plots of observed (true) vs predicted values for deconvolution...
Boxplot and rankings of deconvolution metrics for deconvolution result...
Stacked barplot of deconvolution results
EpiDISH deconvolution
NMF deconvolution
NNLS deconvolution
Creates the old version of the difference in means by sum of variances...
Creates the old version of the difference in means by sum of variances...
Evaluation of produced models on test data
Get CpG annotation from Illumina
Helper function to lighten up a given color.
Load an R object saved with CimpleG or an RDS file.
Make color palette data frame
Make tidy data for use in deconvolution plots
Build deconvolution reference matrix
Predict outcome from a CimpleG signatures on new data
Perform deconvolution on a new set of samples, based on the CimpleG mo...
Save an R object to disk with fast and efficient compression algorithm...
Feature selection function used in the diffmeans, sumvariance space
CpG signature plot
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>.
Useful links