Bioequivalence and Bioavailability Forum

Hi Weidson,

❝ When I use the option Install from Achive File (.zip; targ.gz) of Rstudio Panel and choose the file at save directory the following message appears on RStudio's console:

❝

❝ Installing package into ‘C:/Users/weidson.carlo/Documents/R/win-library/3.6’


❝ (as ‘lib’ is unspecified)


❝ Warning in install.packages :


❝   cannot open compressed file 'Metida.jl-master/DESCRIPTION', probable reason 'No such file or directory'


❝ Error in install.packages : cannot open the connection

As expected (see the subject line). It’s like presenting a Fortran-source to a C-compiler. Can’t work.
First you have to download and install Julia. Then start julia.exe (in the installation’s /bin-folder) and in its terminal:

julia> import Pkg; Pkg.add("Metida")

Looks on my machine like this:

               _
   _       _ _(_)_     |  Documentation: https://docs.julialang.org
  (_)     | (_) (_)    |
   _ _   _| |_  __ _   |  Type "?" for help, "]?" for Pkg help.
  | | | | | | |/ _` |  |
  | | |_| | | | (_| |  |  Version 1.7.1 (2021-12-22)
 _/ |\__'_|_|_|\__'_|  |  Official https://julialang.org/ release
|__/                   |

julia> import Pkg; Pkg.add("Metida")
    Updating registry at `C:\Users\HS\.julia\registries\General`
    Updating git-repo `https://github.com/JuliaRegistries/General.git`
  Downloaded artifact: Hwloc
    Updating `C:\Users\HS\.julia\environments\v1.7\Project.toml`
  [a1dec852] + Metida v0.12.4
    Updating `C:\Users\HS\.julia\environments\v1.7\Manifest.toml`
  [79e6a3ab] + Adapt v3.3.3
  [4fba245c] + ArrayInterface v3.2.2
  [2a0fbf3d] + CPUSummary v0.1.6
  [bbf7d656] + CommonSubexpressions v0.3.0
  [b429d917] + DensityInterface v0.4.0
  [85a47980] + Dictionaries v0.3.17
  [163ba53b] + DiffResults v1.0.3
  [b552c78f] + DiffRules v1.9.0
  [31c24e10] + Distributions v0.25.37
  [1a297f60] + FillArrays v0.12.7
  [6a86dc24] + FiniteDiff v2.9.0
  [f6369f11] + ForwardDiff v0.10.24
  [0e44f5e4] + Hwloc v2.0.0
  [615f187c] + IfElse v0.1.1
  [313cdc1a] + Indexing v1.1.1
  [d3d80556] + LineSearches v7.1.1
  [1914dd2f] + MacroTools v0.5.9
  [a1dec852] + Metida v0.12.4
  [075456b7] + MetidaBase v0.5.1
  [d41bc354] + NLSolversBase v7.8.2
  [77ba4419] + NaNMath v0.3.6
  [429524aa] + Optim v1.6.0
  [90014a1f] + PDMats v0.11.5
  [d96e819e] + Parameters v0.12.3
  [85a6dd25] + PositiveFactorizations v0.2.4
  [1fd47b50] + QuadGK v2.4.2
  [03a91e81] + SplitApplyCombine v1.2.0
  [aedffcd0] + Static v0.4.1
  [90137ffa] + StaticArrays v1.3.1
  [9d95f2ec] + TypedTables v1.4.0
  [3a884ed6] + UnPack v1.0.2
  [e33a78d0] + Hwloc_jll v2.7.0+0
  [4607b0f0] + SuiteSparse
Precompiling project...
  32 dependencies successfully precompiled in 26 seconds (51 already precompiled)

Before you can run PharmCat’s example in GitHub you have to install three other libraries.

julia> import Pkg; Pkg.add("CSV")
julia> import Pkg; Pkg.add("DataFrames")
julia> import Pkg; Pkg.add("CategoricalArrays")

Then with

julia> using Metida, CSV, DataFrames, CategoricalArrays
julia> df = CSV.File(joinpath(dirname(pathof(Metida)),"..","test","csv","df0.csv")) |> DataFrame
julia> transform!(df, :subject => categorical, renamecols=false)
julia> transform!(df, :period => categorical, renamecols=false)
julia> transform!(df, :sequence => categorical, renamecols=false)
julia> transform!(df, :formulation => categorical, renamecols=false)
julia> lmm = LMM(@formula(var~sequence+period+formulation), df;
       random = VarEffect(@covstr(formulation|subject), CSH),
       repeated = VarEffect(@covstr(formulation|subject), DIAG),
       )

You should get:

Linear Mixed Model: var ~ sequence
Random 1:
    Model: formulation|subject
    Type: CSH (3), Subjects: 5
Repeated:
    Model: formulation|subject
    Type: DIAG (2)
Blocks: 5, Maximum block size: 4
Not fitted.

Then:

julia> fit!(lmm)

You should get:

Linear Mixed Model: var ~ sequence + period + formulation
Random 1:
    Model: formulation|subject
    Type: CSH (3), Subjects: 5
Repeated:
    Model: formulation|subject
    Type: DIAG (2)
Blocks: 5, Maximum block size: 4
Status: converged See warnings in log.
    -2 logREML: 10.0652    BIC: 23.9282

    Fixed-effects parameters:
───────────────────────────────────────────────────────
                     Coef.  Std. Error      z  Pr(>|z|)
───────────────────────────────────────────────────────
(Intercept)      1.57749     0.334543    4.72    <1e-05
sequence: 2     -0.170833    0.384381   -0.44    0.6567
period: 2        0.195984    0.117228    1.67    0.0946
period: 3        0.145014    0.109171    1.33    0.1841
period: 4        0.157363    0.117228    1.34    0.1795
formulation: 2  -0.0791667   0.0903709  -0.88    0.3810
───────────────────────────────────────────────────────
    Variance components:
    θ vector: [0.455584, 0.367656, 1.0, 0.143682, 0.205657]
  Random 1   σ² formulation: 1   var   0.207557
  Random 1   σ² formulation: 2   var   0.135171
  Random 1   ρ                   rho   1.0
  Residual   σ² formulation: 1   var   0.0206445
  Residual   σ² formulation: 2   var   0.0422948

The terminal REPL (Read-Eval-Print-Loop) of Julia is pain in the back. I suggest Atom/Juno or Visual Studio Code.

Didn’t try package JuliaCall, except in very simple examples. According to the documentation one could install Julia with the function install_julia() and packages with julia_install_package(). Never tried that.