scPredict: Predict cell classes from a new dataset using a trained model

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

Description

Predicts cell classes for a new dataset based on a training model, a reference eigenPred object

Usage

scPredict(object, newData = NULL, threshold = 0.9, returnProj = TRUE,
  returnData = FALSE, informative = TRUE, useProj = FALSE)

Arguments

object	An scPred object with metadata and informative features and trained model(s).
newData	A matrix object with cells as rows and genes (loci) as columns
threshold	Threshold used for probabilities to classify cells into classes
returnProj	Set to TRUE to return computed projection
returnData	Returns prediction data (newData)
informative	Set to TRUE to project only informative components
useProj	If a projection matrix is already stored in the scPred object, perform predictions using this matrix as input

Value

A data frame with prediction probabilities associated to each class and a predClass column, indicating the classification based on the provided threshold

Author(s)

Jos<c3><a9> Alquicira Hern<c3><a1>ndez

Examples

# Get class probabilities for cells in a new dataset. A 'predClass' columns with 
cell classes is returned depending on the threshold parameter.

prediction <- scPredict(object = object, newData = expTest, threshold = 0.9)

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