calibrate_model: tests and trains a model for a disease using a training and...

In biomedbigdata/SPONGE: Sparse Partial Correlations On Gene Expression

tests and trains a model for a disease using a training and test data set (e.g., TCGA-BRCA and METABRIC)

Description

tests and trains a model for a disease using a training and test data set (e.g., TCGA-BRCA and METABRIC)

Usage

calibrate_model(
  Input,
  modules_metadata,
  label,
  sampleIDs,
  Metric = "Exact_match",
  tunegrid_c = c(1:100),
  n_folds = 10,
  repetitions = 3
)

Arguments

Input	Features to use for model calibration.
modules_metadata	metadata table containing information about samples/patients
label	Column of metadata to use as label in classification model
sampleIDs	Column of metadata containing sample/patient IDs to be matched with column names of spongEffects scores
Metric	metric (Exact_match, Accuracy) (default: Exact_match)
tunegrid_c	defines the grid for the hyperparameter optimization during cross validation (caret package) (default: 1:100)
n_folds	number of folds (default: 10)
repetitions	number of k-fold cv iterations (default: 3)
modules	return from enrichment_modules() function

Value

returns a list with the trained model and the prediction results Calibrate classification RF classification model

returns a list with the trained model and the prediction results

biomedbigdata/SPONGE documentation built on Feb. 6, 2023, 10:19 p.m.