rhs_calc_mlx: Generate Right-hand side data (Monolix)

Description

This functions allows to generate right-hand side data, i.e., combined derivative data of multiple NNs and base-R operations.

rhs_calc_mlx(
  rhs,
  inputs,
  est_parms = NULL,
  mlx_file = NULL,
  time_nn = NULL,
  act = NULL,
  beta = 20
)

Dataframe with columns for the inputs and the combined right-hand side data.

rhs: (string) String of right-hand side, e.g., "NNc + WT * NNct"
inputs: (dataframe) Dataframe of inputs, with corresponding columns (including matching column names for each variable in rhs, e.g., NNc, WT, and NNct).
est_parms: (named vector; semi-optional) Named vector of estimated parameters from the NN extracted through the pre_fixef_extractor_mlx function. For optionality, see Details.
mlx_file: (string; semi-optional) (path)/name of the Monolix run. Must include ".mlxtran" and estimation bust have been run previously. For optionality, see Details.
time_nn: (boolean vector) Vector for each NN in rhs defining whether the neural network is a time-dependent neural network or not. Default value for all NN is FALSE.
act: (character vector) Vector for each NN in rhs defining the activation function used in the NN. Default value for all NN is "ReLU".
beta: (numeric) Beta value for the Softplus activation function, only applicable if any act is softplus; Default to 20.

Dominic Bräm

Either est_parms or mlx_file must be given. If both arguments are given, est_parms is prioritized.