run_omics_evaluation: Perform omics datasets evaluation
In bzhanglab/OmicsEV: A tool for large scale omics datasets evaluation

View source: R/tool.R

run_omics_evaluation

R Documentation

Perform omics datasets evaluation

Description

Perform omics datasets evaluation

Usage

run_omics_evaluation(data_dir = NULL, x2 = NULL, sample_list = NULL,
  data_type = "protein", class_for_cor = NULL, class_for_fun = NULL,
  class_for_ml = NULL, use_common_features_for_func_pred = TRUE,
  class_color = NULL, out_dir = "./", cpu = 0,
  missing_value_cutoff = 0.5, species = "human")

Arguments

`data_dir`	A folder contains multiple omics datasets in tsv format. Row: genes/proteins, column: samples.
`x2`	A tsv format file which contains protein or gene expression data. When the value of parameter is not NULL, the data in this file will be used to perform correlation analysis between this dataset and the dataset in data_dir
`sample_list`	A file in tsv format contains sample class, batch and order information.
`data_type`	The quantification data type in folder data_dir: protein, gene. Default is protein.
`class_for_cor`	The class of samples which will be used to perform correlation analysis. A charactar vector.
`class_for_fun`	The class of samples which will be used for function prediction. A charactar vector.
`class_for_ml`	The classes of samples (two classes) which will be used for phenotype prediction. A sample list file or a charactar vector.
`use_common_features_for_func_pred`	whether or not to use common protien/genes for function prediction. Default is TRUE.
`class_color`	The color for class.
`out_dir`	Output folder
`cpu`	The number of CPUs. Default is 0 and all available CPUs will be used.
`missing_value_cutoff`	The cutoff of missing value filtering. Default is 0.5.
`species`	Default is human.