Character specifying the name of the covariate.

A character specifying the type of the covariate. Possible values are:

• Continuous A covariate can take values on a continuous scale.

• Categorical A covariate can only take a finite number of values.

• Occasion The associated PK parameter may vary within an individual from one event to the next, called interoccasion variability.

A character specifying the corresponding structural parameter name.

A character string representing the presence of the covariate on the structural parameters. Possible values are:

• None The covariate does not have an effect on any structural parameter.

• Present The covariate has an effect on the structural parameters (the default).

• Searched The effect of the covariate on structural parameters is searched.

A character string representing the direction of the Covariate. Options are Forward, Backward, Interpolate. Default is Forward. Interpolate is only applicable to Type == "Continuous".

A character string (None, Mean or Median) or numeric value representing the center of the Covariate. Default is None. Valid only if Type == "Continuous".

A numeric vector representing the categories (at least two) of the covariate. Applicable only if Type is either Occasion or Categorical. The first category is set to the reference category for categorical covariate.

A list of Theta objects representing Thetas covariate effects. Only applicable if Type is either Categorical or Continuous. If Type == "Continuous", one Theta corresponding to current Covariate should be presented. If Type == "Categorical", thetas corresponding to each category (except the reference category) can be specified. If not given, theta(s) will be automatically generated with initial estimate set to 0.0.

A list of Omega objects representing the Omegas of the inter-occasion random effects. Applicable only if Type == "Occasion". The number of Omegas should be equal to the number of categories provided. If not given, Omegas will be created automatically with initial estimate set to 1.0.

PML structure current Covariate instance belongs to.

A character string giving the name of the Dosepoint.

A character string representing the state of the Dosepoint. Possible values are:

• None: current Dosepoint is not used.

• Present (the default): current Dosepoint is used as is.

• Searched: current Dosepoint is added as a token to be searched.

An optional structural parameter giving the time lag for the doses coming into current Dosepoint.

An optional structural parameter giving the bioavailability of the doses coming into current Dosepoint.

An optional structural parameter giving the duration of infusion for the doses coming into current Dosepoint.

An optional structural parameter giving the rate of infusion for the doses coming into current Dosepoint.

A character string that indicates bounded PML structure.

Numeric. Initial estimate for the model parameter.

Additional initial estimate(s) for the model parameter.

A character string giving the name of the Observation.

a Sigmas class instance or a list specifying the chosen sigma values for different error models. 0s are treated as no values. Inside Observation class it is transormed and kept as Sigmas class. The list could contain the following error models:

• Additive The additive error sigma value.

• LogAdditive The log-additive error sigma value.

• Proportional The proportional error sigma value.

• AdditiveMultiplicative A numeric vector specifying the additive and multiplicative parts for the additive-multiplicative error model. The vector should have names PropPart and AddPart.

• MixRatio A numeric vector specifying the proportional and additive parts for the mix-ratio error model. The vector should have names PropPart and AddPart.

• Power A numeric vector specifying the standard deviation and power parts for the power error model. The vector should have names StdevPart and PowerPart.

A logical value indicating whether the dataset contains BQL values and they should be taken into account (M3 method).

An optional numeric positive value of static LLOQ. Applicable only when BQL argument is TRUE. Any observed value less than or equal to that LLOQ value is treated as censored.

A logical value indicating if the standard deviation (Stdev) is frozen.

A logical value indicating if the Observation variable should be reset to 0 after observation (doafter={A0=0;}). Applicable for elimination compartment.

A list of covariates (Covariate instances) that should be included in the model, but not linked to any of structural parameters. Used with "Emax" PD models ('C' covariate is added automatically when creating a new model, but should be added manually when modifying the model).

Character specifying the name of PML structure in which the observation should be added. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

A character string giving the name of the Observation.

One of the following: observe, multi, LL, event, count, ordinal

A character string giving the RHS of response statement without Type.

A character vector giving the names of variables used in the Statement.

a list specifying the chosen sigma value Should be given only if Type == "observe"

A character string specifying the sequence of operations to be performed before current observation event.

A character string specifying the sequence of operations to be performed after current observation event.

A logical value indicating whether the dataset contains BQL values and they should be taken into account (M3 method).

An optional numeric positive value of static LLOQ. Applicable only when BQL argument is TRUE. Any observed value less than or equal to that LLOQ value is treated as censored.

Character specifying the name of PML structure in which the observation should be added. For the naming convention of PMLStructures, see Details section of create_ModelPK().

A character string specifying the name of the Omega.

Numeric specifying the initial value of the Omega. Default value is 1.

Character specifying the presence of the Omega. Possible values are:

• None The Omega does not exist in the specified PMLStructures.

• Present The Omega exists in the specified PMLStructures (the default).

• Searched The presence of the Omega is searched.

A logical value indicating whether the Omega is frozen or not.

A character string specifying the corresponding structural parameter name.

PML structure current omega belongs to.

The additive error sigma value.

The log-additive error sigma value.

The proportional error sigma value.

A list specifying the additive and multiplicative parts for the additive-multiplicative error model. The list should have elements PropPart and AddPart. Alternatively the proportional part (PropPart) could be presented as StParm, see StParm().

A list specifying the proportional and additive parts for the mix-ratio error model. The list should have elements PropPart and AddPart. Alternatively the proportional part (PropPart) could be presented as StParm, see StParm().

A numeric vector specifying the standard deviation and power parts for the power error model. The vector should have names StdevPart and PowerPart.

A character string giving the name of the Observation.

Character specifying the name of the structural parameter.

Character specifying the type of the structural parameter. Options are

• LogNormal The PML statement of the structural parameter will look like the following:

stparm(V = tvV * wt^dVdwt * exp(nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• LogNormal1 The PML statement of the structural parameter will look like the following:

stparm(V = (tvV + wt*dVdwt) * exp(nV + nVx0*( Occasion==0) + nVx1*( Occasion==1)))

• LogNormal2 The PML statement of the structural parameter will look like the following:

stparm(V = exp(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occason==1)))

• LogitNormal The PML statement of the structural parameter will look like the following:

stparm(V = ilogit(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• Normal The PML statement of the structural parameter will look like the following:

stparm(V = tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1))

character string that indicates the presence of the structural parameter. Options are:

• None The structural parameter does not exist in the specified PMLStructures.

• Present The structural parameter exists in the specified PMLStructures (the default).

• Searched The presence of the structural parameter is searched.

A Theta class instance inside the structural parameter. If not given, the associated Theta will be automatically created with its name set to "tv" + StParmName.

An Omega class instance inside the structural parameter. If not given, the associated Omega will be automatically created with its name set to "n" + StParmName

A list of covariates (Covariate instances) that should be included in the structural parameter statement.

Character specifying the name of PML structure for which current parameter should be attributed. For the naming convention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models.

Character; Name of the generated table.

Numeric; Time values for simulation. Applicable for time-based models only. Ignored when keepSource=TRUE.

Character; Vector of covariate names. Simulation point is added when the covariate value is set.

Character or logical; Vector of dosing compartment names. Alternatively if WhenDose == TRUE, triggers are added for all dosepoints for each PMLParametersSet separately; that approach is useful when different models in the set have different dosing compartments. Simulation point is added when the dose value is set.

Character; String of observed variables names. Simulation point is added when the observation value is set.

Character; List of variables from the model for simulation.

Logical; Set to TRUE to keep the number of rows appearing in the table the same as the number of rows in the input dataset.

Set to TRUE to output time after dose.

Logical; Set to TRUE to output individual residuals. Valid only if WhenObs is specified and ForSimulation==FALSE.

Logical; Set to TRUE to output the weight of current observation. Valid only if WhenObs is specified and ForSimulation==FALSE.

Logical; Set to TRUE to output individual weighted residuals. Valid only if WhenObs is specified and ForSimulation==FALSE.

Character; The mode of output. Options are all (default), unique, first. Only applicable to non time-based models for the case where only CovrSet is defined or the case where only CovrSet and VariablesList are defined. Since current version supports time-based models only, this argument is not applicable and won't change the output.

Logical; Set to TRUE if the table should be generated during simulation, otherwise the table will be generated after fitting.

A character string representing the name of the Theta instance.

An InitialEstimate() class instance or a numerical value for the initial estimate of the Theta or a numeric vector length three with its elements representing the lower bound, initial estimate.

Character specifying the presence of the Theta. Possible values are:

• None The Theta does not exist in the specified PMLStructure.

• Present The Theta exists in the specified PMLStructure (the default)

• Searched The presence of the Theta is searched.

A logical value indicating whether the Theta will be estimated or not.

A character specifying the corresponding structural parameter name. Used for the Name of current Theta construction if it is not specified as 'tv' + StParmName.

PML structure current theta belongs to

A list of PML parameters sets (PMLModels class instance).

A character string representing the name of the covariate to be added.

A character specifying the type of the covariate. Possible values are:

• Continuous A covariate can take values on a continuous scale.

• Categorical A covariate can only take a finite number of values.

• Occasion The associated PK parameter may vary within an individual from one event to the next, called interoccasion variability.

Character or character vector specifying names of structural parameters to which covariates should be added. Can be set to NULL or not specified, for such case, covariate will be added to all structural parameters.

A character string representing the presence of the covariate on the structural parameters. Possible values are:

• None The covariate does not have an effect on any structural parameter.

• Present The covariate has an effect on the structural parameters (the default).

• Searched The effect of the covariate on structural parameters is searched.

A character string representing the direction of the Covariate. Options are Forward, Backward, Interpolate. Default is Forward. Interpolate is only applicable to Type == "Continuous".

A character string (None, Mean or Median) or numeric value representing the center of the Covariate. Default is None. Valid only if Type == "Continuous".

A numeric vector representing the categories (at least two) of the covariate. Applicable only if Type is either Occasion or Categorical. The first category is set to the reference category for categorical covariate.

Character or character vector specifying names of PML structures to which the covariate will be added. For the naming covention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models.

A list of existing spaces.

A character string containing the custom code for the new space.

A list of PML parameters sets (PMLModels class instance).

Character specifying the name of the structural parameter to be added.

Character specifying the type of the structural parameter. Options are

• LogNormal The PML statement of the structural parameter will look like the following:

stparm(V = tvV * wt^dVdwt * exp(nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• LogNormal1 The PML statement of the structural parameter will look like the following:

stparm(V = (tvV + wt*dVdwt) * exp(nV + nVx0*( Occasion==0) + nVx1*( Occasion==1)))

• LogNormal2 The PML statement of the structural parameter will look like the following:

stparm(V = exp(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occason==1)))

• LogitNormal The PML statement of the structural parameter will look like the following:

stparm(V = ilogit(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• Normal The PML statement of the structural parameter will look like the following:

stparm(V = tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1))

character string that indicates the presence of the structural parameter. Options are:

• None The structural parameter does not exist in the specified PMLStructures.

• Present The structural parameter exists in the specified PMLStructures (the default).

• Searched The presence of the structural parameter is searched.

A Theta class instance inside the structural parameter. If not given, the associated Theta will be automatically created with its name set to "tv" + StParmName.

An Omega class instance inside the structural parameter. If not given, the associated Omega will be automatically created with its name set to "n" + StParmName

A list of covariates (Covariate instances) that should be included in the structural parameter statement.

Character or character vector specifying names of PML structures to whichthe structural parameter will be added. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

Character specifying the name of the argument in the Dosepoint() instance to add/update the associated structural parameter. Options are bioavail, rate, duration, tlag. Not applicable for custom models

A character string containing the custom code.

Logical indicating whether the Emax model contains a baseline response. If it is set to TRUE, the new parameter, E0, for baseline response is added to the model. Default is FALSE.

Logical indicating whether the Emax model with baseline response is fractional. Applicable only for the Emax models with baseline response, otherwise a warning is given and current parameter is ignored. Default is FALSE.

Logical indicating whether the model is inhibitory. If it is set to TRUE, the structural parameters 'EC50' and 'Emax' change to 'IC50' (concentration producing 50% of maximal inhibition) and 'Imax'. Default is FALSE.

Logical indicating whether the model is sigmoidal. If it is set to TRUE, the Hill coefficient, 'Gam', is added to the model. Default is FALSE.

Logical indicating whether each element in vectorized argument should be treated as a separate PML structure (i.e. treated as data.frame vectors), TRUE, or as parameters to obtain a pool (i.e. expanded) of PML structures, FALSE. Default is FALSE (one value for a function call).

Additional named arguments, including Structural parameters (StParm), Covariates, Dosepoints (for PK models), Thetas and Omegas. See 'Additional arguments' section.

Pharmacodynamic model type. Currently, only Emax is supported.

Logical indicating whether the Emax model contains a baseline response. If it is set to TRUE, the new parameter, E0, for baseline response is added to the model. Default is FALSE.

Logical indicating whether the Emax model with baseline response is fractional. Applicable only for the Emax models with baseline response, otherwise a warning is given and current parameter is ignored. Default is FALSE.

Logical indicating whether the model is inhibitory. If it is set to TRUE, the structural parameters 'EC50' and 'Emax' change to 'IC50' (concentration producing 50% of maximal inhibition) and 'Imax'. Default is FALSE.

Logical indicating whether the model is sigmoidal. If it is set to TRUE, the Hill coefficient, 'Gam', is added to the model. Default is FALSE.

Logical indicating whether each element in vectorized argument should be treated as a separate PML structure (i.e. treated as data.frame vectors), TRUE, or as parameters to obtain a pool (i.e. expanded) of PML structures, FALSE. Default is FALSE (one value for a function call).

Additional named arguments, including Structural parameters (StParm), Covariates, Dosepoints (for PK models), Thetas and Omegas. See 'Additional arguments' section.

The number of compartments in the model. Supported embedded models are 1-, 2-, 3-compartments. Default is 1.

The absorption type of the model. Supported types are:

• Intravenous (Default) - Dose is given in the main compartment (A1) directly.

• First-Order - Dose is absorbed to the main compartment (A1) from the absorption compartment (Aa) by first-order kinetic.

• Gamma - Dose is absorbed to A1 by Gamma Distributed delay kinetic.

• ⁠Inverse Gaussian⁠ - Dose is absorbed to A1 by Inverse Gaussian Distributed delay kinetic.

• Weibull - Dose is absorbed to A1 by Weibull Distributed delay kinetic.

The parameterization type. Possible options are Clearance - Clearance parameters: Cl, Cl2 to be used and Micro - Micro parameters: Ke, K12, K21 to be used. Default is Clearance.

Logical indicating whether saturation should be considered. Default is FALSE.

Logical indicating whether elimination compartment should be included. Default is FALSE.

Logical indicating whether fraction excreted structural parameter should be included in urinecpt statement: urinecpt(A0 = Cl * C, fe=Fe). Valid only if EliminationCpt == TRUE. Default is FALSE.

Logical indicating whether each element in vectorized argument should be treated as a separate PML structure (i.e. treated as data.frame vectors), TRUE, or as parameters to obtain a pool (i.e. expanded) of PML structures, FALSE. Default is FALSE (one value for a function call).

Logical indicating whether closed forms (cfMicro) should be used when possible. Note that closed forms are not available for the models with elimination compartment, models with saturation or absorption types other than Intravenous or First-Order. The models with interpolated covariates must use ClosedForm == FALSE. Default is TRUE (one value for a function call).

Additional named arguments, including Structural parameters (StParm), Covariates, Dosepoints (for PK models), Thetas and Omegas. See 'Additional arguments' section.

Character string: The name of the author.

Character string (optional): The name of the project. If not specified, pyDarwin will set its value to the name of the parent folder of the options file.

Character string: One of EX, GA, GP, RF, GBRT, PSO. See section Details below for more information.

List: Options specific to the Genetic Algorithm (GA). See pyDarwinOptionsGA().

List: Options specific to the Particle Swarm Optimization (PSO). See pyDarwinOptionsPSO().

Positive integer: Seed for random number generation.

Positive integer: Number of models to execute in parallel, i.e., how many threads to create to handle model runs.

Positive integer: Number of iterations or generations of the search algorithm to run. Not used/required for EX.

Positive integer: Number of models to create in every generation. Not used/required for EX.

Positive integer: Number of parallel processes to perform the "ask" step (to increase performance). Required only for GP, RF, and GBRT.

Positive integer: Batch size for the EX (Exhaustive Search) algorithm.

Positive real: Value of fitness or reward assigned when model output is not generated. Should be set larger than any anticipated completed model fitness.

List: Options specific to the penalty calculation. See pyDarwinOptionsPenalty().

Integer: How often to run the downhill step. If < 1, no periodic downhill search will be performed.

Integer: Used for GA and downhill. A penalty is assigned for each model based on the number of similar models within a niche radius. This penalty is applied only to the selection process (not to the fitness of the model). The purpose is to ensure maintaining a degree of diversity in the population (integer). num_niches is also used to select the number of models that are entered into the downhill step for all algorithms, except EX.

Positive real: The radius of the niches. The niche radius is used to define how similar pairs of models are. This is used to select models for the Local search, as requested, and to calculate the sharing penalty for Genetic Algorithm.

Logical: Whether to perform the two-bit local search. The two-bit local search substantially increases the robustness of the search. All downhill local searches are done starting from num_niches models.

Logical: Whether to perform a local search (1-bit and 2-bit) at the end of the global search.

Logical: whether to perform search for block omegas. Used only when engine_adapter == 'nlme'.

Logical: whether to perform search for band omegas. Used only when engine_adapter == 'nonmem'.

Logical: If set, every search block will be handled individually: each block will have a separate gene and max omega search length (either calculated or set explicitly in the options). If set to FALSE, all search blocks will have the same pattern of block omegas. Default is TRUE.

Logical: set to true to search omega submatrix. Default is FALSE.

Integer: Maximum size of sub matrix to use in search. Default is 4.

Positive real: Time (seconds) after which the execution will be terminated, and the crash value assigned.

Character string (Windows only): Priority class for child processes that build and run models, as well as run the R postprocess script. Options are below_normal and normal. below_normal is recommended to maintain user interface responsiveness.

List: Options specific to postprocessing. See pyDarwinOptionsPostprocess()

Logical: Key model is the best model in population (generation). Such models may be a subject of interest when the search is analyzed, so they should be saved separately with all their output. Default is TRUE

Logical: Whether to restore saved Model Cache from file. Default is FALSE.

Character string: The file from which to restore Model Cache. Will only have an effect if use_saved_models is set to true. By default, the cache is saved in {working_dir}/models.json and cleared every time the search is started. To use saved runs, rename models.json or copy it to a different location.

Logical: Do not overwrite the saved_models_file content. Default is FALSE.

Logical: If TRUE, will delete the entire model run directory, otherwise - only unnecessary files inside it. Default is FALSE.

Logical: Whether to delete the entire temp_dir after the search is finished or stopped. Doesn't have any effect when the search is run on a grid. Default is TRUE.

Logical: Whether to override options with environment-specific values. Default is TRUE.

Character string: ModelCache subclass to be used. Currently, there are only darwin.MemoryModelCache and darwin.AsyncMemoryModelCache. You can create your own and use it (e.g., a cache that stores model runs in a database). The name is quite arbitrary and doesn't have any convention/constraints.

Character string: ModelRunManager subclass to be used. Currently, there are only darwin.LocalRunManager and darwin.GridRunManager.

Character string: ModelEngineAdapter subclass to be used. Currently only nlme (default) and nonmem are available.

Character string: The project's working directory, where all the necessary files and folders are created. By default, it is set to ⁠<pyDarwin home>/{project_stem}⁠, where {project_stem} is a file system friendly representation of the project name in a way that it will be easy to manage as a folder name where all non-letters and non-digits are replaced with underscores.

Character string: Directory where datasets are located. Must be available for individual model runs. Default in pyDarwin if not given: {project_dir}.

Character string: Directory where pyDarwin output will be placed. Default is {working_dir}/output.

Character string: Parent directory for all model runs' run directories, i.e., where all folders for every iteration are located. Default in pyDarwin if not given: {working_dir}/temp.

Character string: Directory where the NLME Engine is installed/unzipped. Default: ⁠C:/Program Files/Certara/NLME_Engine⁠. Used only when engine_adapter == 'nlme'.

Character string: Directory where the Mingw-w64 compiler (gcc) is installed. Default: ⁠C:/Program Files/Certara/mingw64⁠ for Windows and gcc version found by ⁠which gcc⁠ on Linux. Used only when engine_adapter == 'nlme'.

Character string: Directory where NONMEM is installed. Used only when engine_adapter == 'nonmem'.

Character string: Path to the Rscript executable. By default, it is obtained with R.home("bin").

Character string (optional): Path to the license file. If not provided, pyDarwin will set its value to PhoenixLicenseFile (only for current Python session).

List: Options specific to the grids. See pyDarwinOptionsGridAdapter()

Additional parameters: Other arguments not explicitly defined in the function's signature are allowed and will be stored in the options list. See pyDarwin documentation.

An object of class "PMLModels" containing PML model parameters.

A list of PML parameters sets (PMLModels class instance).

Logical. Should the names of covariates with None state or covariates inside structural parameters with None state be included or not.

Logical. Should the names of covariate, fcovariate and interpolate statements (from the PML code of custom spaces) be included or not. Default is TRUE.

A list of PML parameters sets (PMLModels class instance).

Logical. Should the names of dosepoints with None state be included or not. Default is FALSE.

Logical. Should the names of custom dosepoint and dosepoint2 statements (from the PML code of custom spaces) be included or not. Default is TRUE.

A list of PML parameters sets (PMLModels class instance).

Logical. Should the names of responses (observe, multi, ordinal, count, event and LL) from the PML code of custom spaces be included or not. Default is TRUE.

Logical. If TRUE (default), only the names of observe responses are included in the PML code generated for custom spaces. Non-observed response names (such as multi, ordinal, count, event, and LL) are not included. Ignored if IncludeCustom == FALSE.

PMLModels class instance or an element (one PML structure) of this class or StParm class.

Logical. Whether should the omega names to be inlcuded from structural parameters, covariates or omegas with a State == 'None'.

Logical. Should the names of custom ranef statements (from the PML code of custom spaces) be included or not. Default is TRUE.

A list of PML parameters sets (PMLModels class instance).

Logical. Should the names of structural parameters with None state be included or not. Default is FALSE.

Logical. Should the names of custom stparm statements (from the PML code of custom spaces) be included or not. Default is TRUE.

PMLModels class instance or an element (one PML structure) of this class or StParm class.

Logical. Whether should the Theta names to be inlcuded from structural parameters, covariates or thetas with a State == 'None'.

Logical. Should the names of custom theta statements (from the PML code of custom spaces) be included or not. Default is TRUE.

A list of PML parameters sets (PMLModels class instance).

A character string giving the name of the Dosepoint.

An optional structural parameter giving the time lag for the doses coming into current Dosepoint.

An optional structural parameter giving the bioavailability of the doses coming into current Dosepoint.

An optional structural parameter giving the duration of infusion for the doses coming into current Dosepoint.

An optional structural parameter giving the rate of infusion for the doses coming into current Dosepoint.

Character or character vector specifying names of PML structures in which the dosepoint statement will be modified. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

A list of PML parameters sets (PMLModels class instance).

A character string giving the name of the Observation.

a Sigmas class instance or a list specifying the chosen sigma values for different error models. 0s are treated as no values. Inside Observation class it is transormed and kept as Sigmas class. The list could contain the following error models:

• Additive The additive error sigma value.

• LogAdditive The log-additive error sigma value.

• Proportional The proportional error sigma value.

• AdditiveMultiplicative A numeric vector specifying the additive and multiplicative parts for the additive-multiplicative error model. The vector should have names PropPart and AddPart.

• MixRatio A numeric vector specifying the proportional and additive parts for the mix-ratio error model. The vector should have names PropPart and AddPart.

• Power A numeric vector specifying the standard deviation and power parts for the power error model. The vector should have names StdevPart and PowerPart.

A logical value indicating whether the dataset contains BQL values and they should be taken into account (M3 method).

An optional numeric positive value of static LLOQ. Applicable only when BQL argument is TRUE. Any observed value less than or equal to that LLOQ value is treated as censored.

A logical value indicating if the standard deviation (Stdev) is frozen.

A logical value indicating if the Observation variable should be reset to 0 after observation (doafter={A0=0;}). Applicable for elimination compartment.

A list of covariates (Covariate instances) that should be included in the model, but not linked to any of structural parameters. Used with "Emax" PD models ('C' covariate is added automatically when creating a new model, but should be added manually when modifying the model).

Character or character vector specifying names of PML structures in which the observation will be modified. For the naming convention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models.

A list of PML parameters sets (PMLModels class instance).

A character string specifying the name of the Omega.

Numeric specifying the initial value of the Omega. Default value is 1.

Character specifying the presence of the Omega. Possible values are:

• None The Omega does not exist in the specified PMLStructures.

• Present The Omega exists in the specified PMLStructures (the default).

• Searched The presence of the Omega is searched.

A logical value indicating whether the Omega is frozen or not.

Character or character vector specifying names of PML structures in which the Omega will be modified. For the naming convention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models.

A list of PML parameters sets (PMLModels class instance).

Character specifying the name of the structural parameter to be modified.

Character specifying the type of the structural parameter. Options are

• LogNormal The PML statement of the structural parameter will look like the following:

stparm(V = tvV * wt^dVdwt * exp(nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• LogNormal1 The PML statement of the structural parameter will look like the following:

stparm(V = (tvV + wt*dVdwt) * exp(nV + nVx0*( Occasion==0) + nVx1*( Occasion==1)))

• LogNormal2 The PML statement of the structural parameter will look like the following:

stparm(V = exp(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occason==1)))

• LogitNormal The PML statement of the structural parameter will look like the following:

stparm(V = ilogit(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• Normal The PML statement of the structural parameter will look like the following:

stparm(V = tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1))

character string that indicates the presence of the structural parameter. Options are:

• None The structural parameter does not exist in the specified PMLStructures.

• Present The structural parameter exists in the specified PMLStructures (the default).

• Searched The presence of the structural parameter is searched.

A Theta class instance inside the structural parameter. If not given, the associated Theta will be automatically created with its name set to "tv" + StParmName.

An Omega class instance inside the structural parameter. If not given, the associated Omega will be automatically created with its name set to "n" + StParmName

A list of covariates (Covariate instances) that should be included in the structural parameter statement.

Character or character vector specifying names of PML structures to whichthe structural parameter will be added. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

A list of PML parameters sets (PMLModels class instance).

Character specifying the name of the structural parameter to be added.

Character specifying the type of the structural parameter. Options are

• LogNormal The PML statement of the structural parameter will look like the following:

stparm(V = tvV * wt^dVdwt * exp(nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• LogNormal1 The PML statement of the structural parameter will look like the following:

stparm(V = (tvV + wt*dVdwt) * exp(nV + nVx0*( Occasion==0) + nVx1*( Occasion==1)))

• LogNormal2 The PML statement of the structural parameter will look like the following:

stparm(V = exp(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occason==1)))

• LogitNormal The PML statement of the structural parameter will look like the following:

stparm(V = ilogit(tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1)))

• Normal The PML statement of the structural parameter will look like the following:

stparm(V = tvV + wt*dVdwt + nV + nVx0*(Occasion==0) + nVx1*(Occasion==1))

character string that indicates the presence of the structural parameter. Options are:

• None The structural parameter does not exist in the specified PMLStructures.

• Present The structural parameter exists in the specified PMLStructures (the default).

• Searched The presence of the structural parameter is searched.

A Theta class instance inside the structural parameter. If not given, the associated Theta will be automatically created with its name set to "tv" + StParmName.

An Omega class instance inside the structural parameter. If not given, the associated Omega will be automatically created with its name set to "n" + StParmName

A list of covariates (Covariate instances) that should be included in the structural parameter statement.

Character or character vector specifying names of PML structures to whichthe structural parameter will be added. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

A list of PML parameters sets (PMLModels class instance).

Character specifying the name of the Theta to be modified.

An InitialEstimate() class instance or a numerical value for the initial estimate of the Theta or a numeric vector length three with its elements representing the lower bound, initial estimate.

A logical value indicating whether the Theta will be estimated or not.

Character or character vector specifying names of PML structures in which the Theta parameter will be modified. For the naming convention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models..

A CustomSpace object.

Additional arguments (not used).

A positive integer specifying the number of best models from any generation to carry over, unchanged, to the next generation. Functions like the Hall of Fame in DEAP. Default: 2

A real value (between 0.0 and 1.0) specifying the fraction of mating pairs that will undergo crossover. Default: 0.95

A real value (between 0.0 and 1.0) specifying the probability that at least one bit in the genome will be “flipped”, 0 to 1, or 1 to 0. Default: 0.95

A real value specifying the parameter of the niche penalty calculation. Default: 0.1

A string specifying the selection algorithm for the GA. Currently, only "tournament" is available. Default: "tournament"

A positive integer specifying the number of “parents” to enter in the selection. 2 is highly recommended, experience with other values is very limited. Default: 2

A string specifying the algorithm for crossover. Only "cxOnePoint" (single-point crossover) is available. Default: "cxOnePoint"

A string specifying the algorithm for mutation. Currently, only "flipBit" is available. Default: "flipBit"

A real value specifying the probability of any bit being mutated (real value between 0.0 and 1.0). Default: 0.1

A positive real value used for the calculation of the crowding penalty. The niche penalty is calculated by first finding the “distance matrix”, the pair-wise Mikowski distance from the present model to all other models. The “crowding” quantity is then calculated as the sum of: (distance/niche_radius)^sharing_alpha for all other models in the generation for which the Mikowski distance is less than the niche radius. Finally, the penalty is calculated as: exp((crowding-1)*niche_penalty)-1. The objective of using a niche penalty is to maintain diversity of models, to avoid premature convergence of the search by penalizing when models are too similar to other models in the current generation. Default: 20

Required. Path to Python interpreter, preferably to the instance of the interpreter located in the virtual environment where pyDarwin is deployed. The path must be available to all grid nodes that run jobs.

Required. A command that submits a search job to the grid queue. This command is used for the entire search.

Required. A command that submits individual runs to the grid queue. The actual command submitted to the queue is constructed by pyDarwin. It should not include ⁠<python_path> -m darwin.run_model⁠.

Required. A regular expression pattern to extract the job ID after submission. The job ID must be captured with the first capturing group.

Required. A command that retrieves finished jobs from the grid controller. If the controller/setup allows to specify ids/patterns in polling commands, do it. Otherwise, all finished jobs should be polled using commands ⁠qstat -s z⁠.

Required. A regular expression pattern to find a job ID in every line of the poll_command output. Similar to submit_job_id_re.

Optional. How often to poll jobs (in seconds). Default is 10 seconds.

Optional. A command that deletes all unfinished jobs related to the search when you stop it. It may delete all of them by ID (e.g., ⁠qdel {job_ids}⁠) or by mask (e.g., ⁠qdel {project_stem}-*⁠)..

A real value specifying the particle coordination movement as it relates to the previous velocity (commonly denoted as w). Default: 0.4

A real value specifying the particle coordination movement as it relates to its own best known position (commonly denoted as c1). Default: 0.5

A real value specifying the particle coordination movement as it relates to the current best known position across all particles (commonly denoted as c2). Default: 0.5

A positive integer specifying the number of neighbors that any particle interacts with to determine the social component of the velocity of the next step. A smaller number of neighbors results in a more thorough search (as the neighborhoods tend to move more independently, allowing the swarm to cover a larger section of the total search space) but will converge more slowly. Default: 20

A positive integer specifying the Minkowski p-norm to use. A value of 1 is the sum-of-absolute values (or L1 distance) while 2 is the Euclidean (or L2) distance. Default: 2

A positive integer specifying the number of iterations used to determine whether the optimization has converged. Default: 5

numeric: Penalty added to fitness/reward for each estimated THETA. A value of 3.84 corresponds to a hypothesis test with 1 df and p < 0.05 (for nested models), and a value of 2 for 1 df corresponds to the Akaike information criterion. Default: 10

numeric: Penalty added to fitness/reward for each estimated OMEGA element. Default: 10

numeric: Penalty added to fitness/reward for each estimated SIGMA element. Default: 10

numeric: Penalty added to fitness/reward for failing to converge. Default: 100

numeric: Penalty added to fitness/reward for failing the covariance step (real number). If a successful covariance step is important, this can be set to a large value (e.g., 100), otherwise, set to 0. Default: 100

numeric: Penalty added to fitness/reward if any off-diagonal element of the correlation matrix of estimates has an absolute value > 0.95 (real number). This penalty will be added if the covariance step fails or is not requested. Default: 100

numeric: Penalty added if the covariance step fails or is not requested, e.g., PRINT=E is not included in $COV. Additionally, if the covariance is successful and the condition number of the covariance matrix is > 1000, then this penalty is added to the fitness/reward. Default: 100

numeric: Penalty added to fitness/reward if any tokens do not influence the control file (relevant for nested tokens). Should be very small (e.g., 0.0001), as the purpose is only for the model with non-influential tokens to be slightly worse than the same model without the non-influential token(s) to break a tie. Default: 0.00001

Logical: Whether to use R for postprocessing. If set to TRUE, R will be used to execute the post-processing script specified in post_run_r_code. Default: FALSE.

Character: The file path to the R script that contains post-processing code. This script will be executed after the pyDarwin optimization process finishes. It can perform additional analysis or manipulations on the generated results.

Numeric: The time limit (in seconds) for the execution of the post-processing R script. If the R script takes longer to execute than this timeout value, it will be terminated. Default: 30

Logical: Whether to use Python for postprocessing. If set to TRUE, Python will be used to execute the post-processing script specified in post_run_python_code. Default: FALSE

Character: The file path to the Python script that contains post-processing code. This script will be executed after the pyDarwin optimization process finishes. It can perform additional analysis or manipulations on the generated results. Default: {project_dir}/simplefunc.py

A list of PML parameters sets (PMLModels class instance).

Character specifying the name of the covariate to be removed.

Character or character vector specifying names of structural parameters from which the covariate will be removed. Can be set to NULL or not specified, for such case the covariate will be removed from all structural parameters.

Character or character vector specifying names of PML structures from which the covariate will be removed. For the naming convention of PMLStructures, see Details section of see details section of get_PMLParametersSets().

A list of PML parameters sets (PMLModels class instance).

A character string giving the name of the Observation.

Character or character vector specifying names of PML structures from which the observation will be removed. For the naming convention of PMLStructures, see Details section of create_ModelPK() for PK models and create_ModelPD() for PD models.

A list of PML parameters sets (PMLModels class instance).

character specifying the name for the structural parameter to be removed.

Character or character vector specifying names of PML structures from which the structural parameter will be removed. For the naming convention of PMLStructures, see Details section of get_PMLParametersSets().

Path to the Python interpreter executable.

Flags to pass to the Python interpreter. Refer to Python documentation for details. Note that -m is essential (runs library module as a script and terminates option list).

Optional path to the directory containing template file, tokens file and options file. If that argument is given, it overrides the paths of TemplatePath, TokensPath, OptionsPath with warning. Default is current working directory.

Path to the template file.

Path to the tokens JSON file.

Path to the options JSON file.

Logical. If TRUE, the function waits for the search process to complete and returns the results. If FALSE, the process is launched and exits immediately.

Logical; Specifying whether or not to sort the input data by subject and time values. Default is TRUE.

Character; Specifying the solver used to numerically solve Ordinary Differential Equations (ODEs). Options are

• MatrixExponent (the default),

• DVERK,

• DOPRI5,

• AutoDetect,

• Stiff.

Note: both DVERK and DOPRI5 are non-stiff solvers. NLME will automatically switches to DVERK if ODEs are nonlinear.

Numeric; Specifying relative tolerance for the ODE solver. Not applicable when ODE == MatrixExponent.

Numeric; Specifying absolute tolerance for the ODE solver.

Numeric; Specifying maximum number of allowable steps or function evaluations for the ODE solver.

Numeric; Specifying maximum number of iterations for estimation.

Character; Specifying engine method for estimation. Options are:

• FOCE-ELS (the default),

• QRPEM,

• Laplacian,

• Naive-Pooled,

• FOCE-LB,

• IT2S-EM,

• FO.

Note: if model involves any discontinuous observed variable (e.g., count data) or BQL data, NLME will switch from default method FOCE-ELS to Laplacian.

Character; Specifying method for standard error computations. Options are:

• Auto-Detect (the default),

• Sandwich,

• Hessian,

• Fisher-Score,

• None.

Here None means that standard error calculations are not performed. Since when method = QRPEM only Fisher-Score standard error type is available in NLME, any selected option except None will reset to stdErr = "Fisher-Score".

Logical; Default TRUE uses central difference for stdErr calculations. Set to FALSE for forward difference method.

Numeric; Specifying the step size used for stdErr calculations.

Numeric; Specifying the number of integration points for adaptive Gaussian quadrature (AGQ) algorithm. Only applicable to models with method set to either FOCE-ELS or Laplacian.

Numeric; Specifying the number of iterations to perform non-parametric estimation. Only applicable when method is not set to Naive-Pooled (otherwise ignored).

Logical, Set to TRUE to use synthetic gradient during the estimation process. Only applicable to population models when method is not set to Naive-Pooled (otherwise ignored).

Numeric; Specifying the number of iterations to perform Maximum A Posterior (MAP) initial Naive Pooling (NP) run before estimation. Only applicable to population models when method is not set to Naive-Pooled (otherwise ignored).

Numeric; Specifying the number of replicates to generate the PCWRES after the simple estimation. Only applicable to population models when method is not set to Naive-Pooled (otherwise ignored).

Numeric; Specifying the step size used for numerical differentiation when linearizing the model function during the estimation process.

Numeric; Specifying the number of significant decimal digits for the Laplacian/ELS algorithm to use to reach convergence.

Numeric; Specifying the number of significant decimal digits for the individual estimation to use to reach convergence.

Numeric; Specifying the period used to perform MAP assistance (mapAssist = 0 means that MAP assistance is not performed). Only applicable when method == "QRPEM".

Numeric; Specifying the number of samples. Only applicable when method == "QRPEM".

Numeric; Specifying the acceptance ratio. Only applicable when method == "QRPEM".

Character; Specifying the distribution used for important sampling, and options are

• Normal (the default),

• DoubleExponential,

• Direct,

• T,

• Mixture-2,

• Mixture-3.

Only applicable to the model with method = "QRPEM".

Numeric; Specifying the degree of freedom (allowed value is between 3 and 30) for T distribution. Only applicable when method =="QRPEM" and impDist == "T".

Numeric; Specifying the number of samples per subject used in the Sampling Importance Re-Sampling (SIR) algorithm to determine the number of SIR samples taken from the empirical discrete distribution that approximates the target conditional distribution. Only applicable to population models with method = "QRPEM".

Numeric; Specifying the number of burn-in iterations to perform at startup to adjust certain internal parameters. Only applicable to population models with method = "QRPEM".

Logical; Set to TRUE to freeze Omega but not Theta for the number of iterations specified in the numBurnIn. Only applicable to population models with method = "QRPEM".

Logical; Set to TRUE to use Monte-Carlo sampling instead of Quasi-Random. Only applicable to population models with method = "QRPEM".

Logical; Set to TRUE to execute all requested iterations specified in numIterations. Only applicable to population models with method = "QRPEM".

Character; Specifying the quasi-random scrambling method to use, and options are

• Owen (the default),

• Tezuka-Faur,

• None.

Only applicable to population models with method = "QRPEM".

Integer; Number of replicates to simulate the model

Integer; Random number generator seed

Logical; Specifying whether or not to sort the input data by subject and time values. Default is TRUE.

Character; Specifying the solver used to numerically solve Ordinary Differential Equations (ODEs). Options are

• MatrixExponent (the default),

• DVERK,

• DOPRI5,

• AutoDetect,

• Stiff.

Note: both DVERK and DOPRI5 are non-stiff solvers. NLME will automatically switches to DVERK if ODEs are nonlinear.

Numeric; Specifying relative tolerance for the ODE solver. Not applicable when ODE == MatrixExponent.

Numeric; Specifying absolute tolerance for the ODE solver.

Numeric; Specifying maximum number of allowable steps or function evaluations for the ODE solver.

Path to the Python interpreter executable.

Flags to pass to the Python interpreter. Refer to Python documentation for details. Note that -m is essential (runs library module as a script and terminates option list).

Logical. If TRUE, -f flag is added to force stop search immediately.- Default is FALSE.

the DirectoryPath argument of run_pyDarwin() or the parent folder of options file passed to that function. Default is current working directory.

TemplateFilePath NLME template file path to be written (usually txt).

json file path to be written (usually json).

A problem name to be outputted in Description section.

The author information for the model to be outputted in Author section.

A data file path used by NLME.

A named vector ModelTerm = DataTerm for the used data file.

A character string specifying additional column definitions in NLME column definition format. See https://onlinehelp.certara.com/phoenix/8.4/index.html#t=Phoenix_UserDocs%2FPML%2FColumn_mappings.htm

A list of PML parameters sets (PMLModels class instance).

Estimation arguments for the model template. Please use specify_EngineParams to specify the arguments passed to NLME.

Simulation arguments for the model template. Please use specify_SimParams to specify the arguments passed to NLME.

A list of Table class instances specifying properties of the tables to be generated after fitting or during simulation.

Additional rows to include in the model template appendix in NLME column definition format. See https://onlinehelp.certara.com/phoenix/8.4/index.html#t=Phoenix_UserDocs%2FPML%2FColumn_mappings.htm

A list of character vectors representing omega names to try to build block omegas.

A list containing the pyDarwin options to be written to the JSON file. Default is the result of calling create_pyDarwinOptions() with default arguments.

Character: The path to the JSON file where the options will be written. Default is a file named "options.json" in the current working directory.

adds indentation whitespace to JSON output. Can be TRUE/FALSE or a number specifying the number of spaces to indent. See prettify()

max number of decimal digits to print for numeric values. Use I() to specify significant digits. Use NA for max precision.

automatically unbox() all atomic vectors of length 1. It is usually safer to avoid this and instead use the unbox() function to unbox individual elements. An exception is that objects of class AsIs (i.e. wrapped in I()) are not automatically unboxed. This is a way to mark single values as length-1 arrays.