pre_model: Prediction of ENCODE cluster features based on scRNA-seq data

In WeiqiangZhou/SINTER: Single-cell genomic data integration

Description

This function is used for predicting ENCODE cluster features based on scRNA-seq data. The scRNA-seq data are first clustered into gene clusters and the cluster means are used as predictors.

Usage

pre_model(expr_select, DNase_train, RNA_train, num_predictor = 10,
  cluster_scale = 10, seed = 12345)

Arguments

expr_select	Input gene expression data from scRNA-seq.
DNase_train	ENCODE cluster features from DNase-seq data for building the regression model.
RNA_train	Gene expression from ENCODE RNA-seq data for building the regression model.
num_predictor	Number of predictors used in the prediction model.
cluster_scale	The scale to determine the number of gene clusters. The number of gene clusters is obtained by [the number of genes]/[cluster_scale].
seed	Set the seed in kmeans clustering for reproducible results.

Value

Y_pre

A matrix of predicted ENCODE cluster features.

Examples

## Not run: 
Y_pre <- pre_model(expr_select,DNase_train,RNA_train,num_predictor=10,cluster_scale=10,seed=12345)

## End(Not run)

WeiqiangZhou/SINTER documentation built on Sept. 11, 2019, 8:03 a.m.