Predict: Run a prediction on new data using the graph learning model.

In ncats/MultiOmicsGraphPrediction: Network-Based Ensemble Prediction from IntLIM Predictors

Run a prediction on new data using the graph learning model.

Description

Run a prediction on new data using the graph learning model.

Usage

Predict(
  pairs,
  targets,
  sources,
  inputData,
  weights,
  model,
  minCutoff,
  maxCutoff,
  useCutoff = FALSE,
  useActivation = TRUE,
  independentVarType,
  outcomeType,
  averaging = FALSE,
  individualPredictors = NULL,
  zeroOut = FALSE
)

Arguments

pairs	A list of pairs to include in the composite model.
targets	Target analytes for all pairs
sources	Source analytes for all pairs
inputData	The input testing data, which should be of an IntLimData class type.
weights	The weight of each predictor.
model	The learned model, an object of the modelResults class.
minCutoff	Mininum cutoff for the prediction.
maxCutoff	Maximum cutoff for the prediction.
useCutoff	Whether or not to use the cutoff for prediction. Default is FALSE.
useActivation	Whether or not to use the activation function if the phenotype to predict is a factor. Default is TRUE. We set to FALSE during training.
independentVarType	The independent variable type (1 or 2)
outcomeType	The outcome type (1 or 2)
averaging	If TRUE, then averaging is used to combine predictors rather than retaining the same functional form for both the input and the output.
individualPredictors	The values of the individual predictors. If set to NULL (default), the edge wise predictions in the model input are used. This variable only needs to be set when inputting test data.
zeroOut	This parameter zeros out predictors outside of the allowed range.

Value

A vector of predictions

ncats/MultiOmicsGraphPrediction documentation built on Aug. 23, 2023, 9:19 a.m.