weightNorm

<p>The weight vector from fitting an SVM, something like something like t(fit1$coefs) %*% fit1$SV, where fit comes from  &lt;- svm(m~B, nu=0.25, kernel="linear"))</p>

Augments existing or de-novo cell-type signature matrices to deconvolve bulk gene expression data.
Useful for building signature matrices from single cell RNAseq data, determine cell type deconvolution
spillover, and hierarchical deconvolution to use spillover to increase deconvolution accuracy. Please cite:
Danziger SA et al. (2019) ADAPTS: Automated Deconvolution Augmentation of Profiles for
Tissue Specific cells <doi:10.1101/633958>. This package expands on the techniques outlined in Newman AM,
Liu CL, Green MR, Gentles AJ, Feng W, Xu Y,
Hoang CD, Diehn M, Alizadeh, AA (2015) <doi:10.1038/nmeth.3337>'s Nature Methods paper:
'Robust enumeration of cell subsets from tissue expression profiles'  to allow a user to easily add
their own cell types (e.g. a tumor specific cell type) to Newman's LM22 or other signature matrix.

Samuel Danziger

weightNorm: Use weightNorm to normalize the SVM weights. Used for SVMDECONV

Description

Usage

Arguments

Value