Pumas version 0.12.0 (Alpha 12) released

A new release of Pumas is now available in the JuliaProRegistry. You can upgrade your current installation of Pumas by simply running ] up Pumas at the command prompt in JuliaPro.

Release Notes for Pumas v0.12.0


  • Sundials.jl is now supported when using steady-state dosing.
  • Information criteria functions aic and bic, as well as the shrinkage and npde functions, now have methods for FittedPumasModel.
  • The predict method now works for models fitted with NaivePooled.
  • Estimation of models with dose control parameters is now supported both for closed-form and ODE based models.
  • New concthreshold parameter in NCA.lambdaz to filter out tiny concentrations.
  • Support for passing obstimes in predict methods.
  • Many new docstrings.


  • PKPDAnalyticalProblem has been renamed to AnalyticalPKPDProblem.
  • ZeroSpline from DataInterpolations has been renamed to ConstantInterpolation.


  • Doses in NCA that are outside of observed time are now automatically removed.
  • Optional arguments used during the model fitting is now correctly pased to diagnostics functions. This ensures that e.g. ODE solver tolerances are identical between model fitting and diagnostics computations.
  • It is now possible to use random effects in the @vars block. That means that random effects can be applied to the solution of the dynamical system instead of just to the parameters of the dynamical system.
  • Bugfix for offset handling in DosageRegimen.
  • Fix printing of coefficient tables when the calculation of the covariance matrix has failed.
  • Fix printing of the number of successful bootstrap samples.


  • Pumas now supports Julia 1.4. Julia version 1.4.1 includes important compilation time fixes for Pumas relative to version 1.4.0.
  • StatsBase 0.33 is now supported.
  • RecipesBase 1.0 is now supported.
  • AdvancedHMC 0.2.12 is now required.
  • DataInterpolations 2.0 is now required.
  • StatsFuns 0.9 is now supported.