scPred: Definition of 'scPred' class

In IMB-Computational-Genomics-Lab/scPred: scPred - Single cell prediction using singular value decomposition and machine learning classification

Description

An S4 class to contain principal component analysis of a gene expression matrix, metadata, training, and prediction information.

Slots

sva

Singular value decomposition performed with prcomp_irlba() function

metadata

A dataframe with:

• row names: ids matching the column names of the gene expression matrix

• columns: associated metadata such as cell type, conditions, sample, or batch.

trainData

Training gene expression data

expVar

Explained variance by each principoal component

pVar

Column name from metadata to use as the variable to predict using the informative principal components

features

A data frame with the following information:

• PC: Principal component

• Freq: Frequency of occurencxe of the principal component over a number of random samples from the PCA matrix

• expVar: Explained variance by the principal component

• cumExpVar: All principal components are ranked accoriding to their frequency of ocurrence and their variance explained. This column contains the cumulative variance explained across the ranked principal components

train

A list with all trained models using the caret package. Each model correspond to a cell type

projection

A matrix containing the prediction data projection

predictions

A data frame with the prediction results containing probabilities for each class

pseudo

TRUE if a log2(data + 1) transformation was performed before performing the PCA

IMB-Computational-Genomics-Lab/scPred documentation built on Jan. 11, 2020, 7:37 a.m.