Description
Nonlinear Mixed Effects Models in Population PK/PD, Extra Support Functions.
Description
Fit and compare nonlinear mixed-effects models in differential equations with flexible dosing information commonly seen in pharmacokinetics and pharmacodynamics (Almquist, Leander, and Jirstrand 2015 <doi:10.1007/s10928-015-9409-1>). Differential equation solving is by compiled C code provided in the 'rxode2' package (Wang, Hallow, and James 2015 <doi:10.1002/psp4.12052>). This package is for support functions like preconditioned fits <doi:10.1208/s12248-016-9866-5>, boostrap and stepwise covariate selection.
README.md
nlmixr2extra
The goal of nlmixr2extra is to provide the tools to help with common pharmacometric tasks with nlmixr2 models like bootstrapping, covariate selection etc.
Installation
You can install the development version of nlmixr2extra from GitHub with:
# install.packages("remotes")
remotes::install_github("nlmixr2/nlmixr2data")
remotes::install_github("nlmixr2/lotri")
remotes::install_github("nlmixr2/rxode2")
remotes::install_github("nlmixr2/nlmixr2est")
remotes::install_github("nlmixr2/nlmixr2extra")
Example of a bootstrapFit()
This is a basic example of bootstrapping provided by this package
library(nlmixr2est)
#> Loading required package: nlmixr2data
library(nlmixr2extra)
# basic example code
# The basic model consists of an ini block that has initial estimates
one.compartment <- function() {
ini({
tka <- 0.45 # Log Ka
tcl <- 1 # Log Cl
tv <- 3.45 # Log V
eta.ka ~ 0.6
eta.cl ~ 0.3
eta.v ~ 0.1
add.sd <- 0.7
})
# and a model block with the error specification and model specification
model({
ka <- exp(tka + eta.ka)
cl <- exp(tcl + eta.cl)
v <- exp(tv + eta.v)
d/dt(depot) = -ka * depot
d/dt(center) = ka * depot - cl / v * center
cp = center / v
cp ~ add(add.sd)
})
}
# The fit is performed by the function nlmixr/nlmixr2 specifying the model, data
# and estimate (in a real estimate, nBurn and nEm would be much higher.)
fit <- nlmixr2(one.compartment, theo_sd, est="saem", saemControl(print=0, nBurn = 10, nEm = 20))
#> ℹ parameter labels from comments will be replaced by 'label()'
#> → loading into symengine environment...
#> → pruning branches (`if`/`else`) of saem model...
#> ✔ done
#> → finding duplicate expressions in saem model...
#> [====|====|====|====|====|====|====|====|====|====] 0:00:00
#> → optimizing duplicate expressions in saem model...
#> [====|====|====|====|====|====|====|====|====|====] 0:00:00
#> ✔ done
#> rxode2 2.0.11.9000 using 8 threads (see ?getRxThreads)
#> no cache: create with `rxCreateCache()`
#> Calculating covariance matrix
#> → loading into symengine environment...
#> → pruning branches (`if`/`else`) of saem model...
#> ✔ done
#> → finding duplicate expressions in saem predOnly model 0...
#> → finding duplicate expressions in saem predOnly model 1...
#> → optimizing duplicate expressions in saem predOnly model 1...
#> → finding duplicate expressions in saem predOnly model 2...
#> ✔ done
#> → Calculating residuals/tables
#> ✔ done
#> → compress origData in nlmixr2 object, save 5952
#> → compress phiM in nlmixr2 object, save 2832
#> → compress parHist in nlmixr2 object, save 1968
#> → compress saem0 in nlmixr2 object, save 24944
# In a real bootstrap, nboot would be much higher.
fit2 <- suppressMessages(bootstrapFit(fit, nboot = 5))
#> 001: 0.289754 0.955016 3.449185 0.381052 0.078862 0.016351 1.435990
#> 002: 0.341570 1.042356 3.475026 0.361999 0.074919 0.015533 0.968865
#> 003: 0.472750 1.038382 3.506706 0.343899 0.081378 0.014757 0.797063
#> 004: 0.496706 1.074803 3.510905 0.326704 0.077309 0.014019 0.722518
#> 005: 0.534589 1.100823 3.486683 0.310369 0.073930 0.013318 0.689762
#> 006: 0.536212 1.092222 3.496588 0.294850 0.070233 0.012652 0.646975
#> 007: 0.498232 1.116233 3.490177 0.296055 0.066722 0.012019 0.657194
#> 008: 0.472135 1.087746 3.486804 0.281253 0.063386 0.011418 0.665569
#> 009: 0.414591 1.093383 3.475219 0.275684 0.060216 0.011823 0.654913
#> 010: 0.463636 1.093226 3.468536 0.302019 0.060954 0.010231 0.644346
#> 011: 0.471632 1.094277 3.473210 0.300665 0.057946 0.010692 0.645369
#> 012: 0.487830 1.101393 3.474948 0.306205 0.054575 0.011432 0.636770
#> 013: 0.479627 1.106742 3.473516 0.303806 0.050805 0.012334 0.635296
#> 014: 0.488082 1.104715 3.475776 0.299002 0.052067 0.012733 0.636187
#> 015: 0.491629 1.105114 3.478241 0.293828 0.052474 0.013105 0.633431
#> 016: 0.496946 1.105220 3.481824 0.288786 0.052556 0.013002 0.633009
#> 017: 0.501182 1.104867 3.484359 0.291721 0.051772 0.013106 0.630237
#> 018: 0.504760 1.104384 3.485512 0.294660 0.051390 0.012882 0.628937
#> 019: 0.503525 1.106547 3.485744 0.294525 0.051059 0.012606 0.628119
#> 020: 0.504792 1.106269 3.487000 0.292017 0.051074 0.012392 0.628590
#> 021: 0.504680 1.105623 3.488382 0.289388 0.051105 0.012258 0.629262
#> 022: 0.506024 1.105160 3.490148 0.285219 0.051702 0.012195 0.629037
#> 023: 0.511997 1.105357 3.491865 0.290051 0.051408 0.012157 0.629789
#> 024: 0.515887 1.105808 3.492777 0.292475 0.050884 0.012147 0.630087
#> 025: 0.517210 1.105963 3.492826 0.295889 0.049986 0.012198 0.629288
#> 026: 0.516025 1.107520 3.492264 0.297170 0.049610 0.012291 0.628565
#> 027: 0.515202 1.108956 3.491510 0.296660 0.049518 0.012327 0.628714
#> 028: 0.516875 1.109118 3.491399 0.297858 0.048998 0.012389 0.628230
#> 029: 0.518964 1.109633 3.491344 0.299585 0.048763 0.012417 0.628187
#> 030: 0.520491 1.109555 3.491727 0.299411 0.048814 0.012561 0.627538
#> 001: 0.322787 0.951634 3.447451 0.381052 0.076738 0.016351 1.530345
#> 002: 0.427636 0.897920 3.465514 0.361999 0.072901 0.015533 1.087413
#> 003: 0.508253 0.828660 3.472124 0.343899 0.069256 0.014757 0.838074
#> 004: 0.509892 0.834282 3.468804 0.326704 0.066873 0.014019 0.673776
#> 005: 0.508392 0.823533 3.444179 0.310369 0.078466 0.013318 0.654094
#> 006: 0.461647 0.841721 3.438128 0.294850 0.074543 0.012652 0.607374
#> 007: 0.449577 0.846887 3.427116 0.328131 0.070816 0.012019 0.613524
#> 008: 0.452729 0.858913 3.420601 0.316657 0.086343 0.011418 0.600919
#> 009: 0.423963 0.842949 3.420380 0.329854 0.089491 0.010848 0.594947
#> 010: 0.428721 0.855938 3.425315 0.354540 0.091239 0.006169 0.606052
#> 011: 0.453442 0.853622 3.427827 0.351512 0.086620 0.006578 0.608115
#> 012: 0.462225 0.853917 3.425827 0.361433 0.082071 0.006803 0.605303
#> 013: 0.458003 0.859284 3.422302 0.375770 0.078209 0.006864 0.609796
#> 014: 0.463493 0.859918 3.421436 0.394293 0.077441 0.007209 0.612385
#> 015: 0.461922 0.861117 3.422084 0.391491 0.075832 0.007177 0.610504
#> 016: 0.463641 0.860191 3.423481 0.388623 0.072947 0.007093 0.610327
#> 017: 0.466608 0.861250 3.424922 0.387369 0.071245 0.007120 0.609212
#> 018: 0.467115 0.863905 3.424010 0.385711 0.070812 0.007068 0.607741
#> 019: 0.464636 0.865482 3.423091 0.384225 0.070733 0.006891 0.605629
#> 020: 0.466311 0.867835 3.422920 0.388178 0.071830 0.006899 0.603946
#> 021: 0.467791 0.867667 3.423117 0.388788 0.072470 0.006804 0.603274
#> 022: 0.467680 0.867848 3.423223 0.389921 0.072747 0.006679 0.601932
#> 023: 0.471964 0.867613 3.423780 0.392002 0.073413 0.006733 0.601413
#> 024: 0.471012 0.869247 3.423531 0.391023 0.074191 0.006624 0.600971
#> 025: 0.471592 0.868571 3.423338 0.394052 0.075357 0.006510 0.600329
#> 026: 0.470657 0.869562 3.423072 0.395694 0.076004 0.006495 0.600176
#> 027: 0.469108 0.870772 3.422378 0.395820 0.076448 0.006516 0.600126
#> 028: 0.467693 0.871474 3.422045 0.393456 0.075655 0.006647 0.599299
#> 029: 0.468393 0.872718 3.421465 0.391148 0.075150 0.006719 0.599974
#> 030: 0.468304 0.873833 3.420865 0.390229 0.075320 0.006836 0.599273
#> 001: 0.321454 0.971377 3.443146 0.381052 0.077198 0.016351 1.843240
#> 002: 0.404381 0.984655 3.454425 0.361999 0.073338 0.015533 1.327013
#> 003: 0.524777 0.923516 3.448166 0.343899 0.069671 0.014757 0.973899
#> 004: 0.464318 0.918715 3.444206 0.326704 0.066188 0.014019 0.899000
#> 005: 0.505866 0.944304 3.428324 0.369671 0.075402 0.013318 0.849983
#> 006: 0.463863 0.956021 3.409451 0.351188 0.087264 0.012652 0.825540
#> 007: 0.428948 0.950593 3.414305 0.333628 0.085637 0.012019 0.835024
#> 008: 0.421492 0.943008 3.403544 0.316947 0.086564 0.012203 0.836564
#> 009: 0.393406 0.940308 3.406897 0.301100 0.083656 0.014303 0.847300
#> 010: 0.441726 0.936843 3.412050 0.258291 0.089442 0.013228 0.846843
#> 011: 0.463308 0.937482 3.413063 0.248330 0.094996 0.012282 0.848071
#> 012: 0.453256 0.941789 3.410521 0.245399 0.103340 0.011370 0.838674
#> 013: 0.440268 0.949914 3.407022 0.233480 0.106164 0.010496 0.837572
#> 014: 0.443334 0.949030 3.408971 0.243138 0.108268 0.010403 0.840363
#> 015: 0.447580 0.948484 3.410579 0.244311 0.107791 0.010531 0.837262
#> 016: 0.446239 0.951883 3.411966 0.243853 0.107251 0.010434 0.835515
#> 017: 0.446532 0.954138 3.413003 0.246637 0.106016 0.010641 0.836453
#> 018: 0.446437 0.956413 3.411380 0.244549 0.106120 0.010611 0.836756
#> 019: 0.440359 0.957282 3.410359 0.246071 0.106063 0.010584 0.837482
#> 020: 0.438193 0.958720 3.410340 0.248115 0.108699 0.010520 0.836311
#> 021: 0.438664 0.958757 3.410299 0.247831 0.110066 0.010608 0.834780
#> 022: 0.438099 0.958202 3.411346 0.251382 0.111559 0.010467 0.834395
#> 023: 0.442660 0.957814 3.412045 0.250540 0.111833 0.010353 0.835423
#> 024: 0.445029 0.959311 3.412104 0.252011 0.112183 0.010420 0.836493
#> 025: 0.445302 0.957116 3.412285 0.252143 0.111216 0.010417 0.837473
#> 026: 0.445494 0.959271 3.411336 0.254985 0.111211 0.010295 0.836981
#> 027: 0.442450 0.961509 3.410295 0.255564 0.111479 0.010272 0.836688
#> 028: 0.442704 0.961873 3.410156 0.257600 0.110936 0.010306 0.835889
#> 029: 0.443796 0.962325 3.409781 0.257516 0.111795 0.010518 0.835939
#> 030: 0.444443 0.962669 3.409480 0.259052 0.111135 0.010623 0.836011
#> 001: 0.308790 0.955292 3.452306 0.381052 0.078745 0.016351 1.610290
#> 002: 0.320194 0.972929 3.441237 0.361999 0.074808 0.015533 1.052149
#> 003: 0.388375 0.903049 3.451275 0.343899 0.071067 0.014757 0.876051
#> 004: 0.352724 0.943163 3.446667 0.326704 0.067514 0.014019 0.848090
#> 005: 0.370729 0.942207 3.437666 0.310369 0.064138 0.013318 0.811039
#> 006: 0.340865 0.946849 3.433523 0.294850 0.067188 0.012652 0.778070
#> 007: 0.321317 0.929801 3.430701 0.280108 0.078825 0.012019 0.807483
#> 008: 0.297800 0.954520 3.419284 0.266103 0.074883 0.012974 0.812512
#> 009: 0.268345 0.941798 3.412954 0.252797 0.071139 0.012325 0.820797
#> 010: 0.284470 0.945655 3.410890 0.167484 0.058407 0.009044 0.819982
#> 011: 0.304119 0.956041 3.413440 0.160651 0.058828 0.009528 0.823598
#> 012: 0.310049 0.953562 3.414981 0.158940 0.058257 0.009152 0.821713
#> 013: 0.294795 0.958102 3.411723 0.154670 0.062969 0.009092 0.826275
#> 014: 0.295332 0.962803 3.410459 0.150207 0.064431 0.008887 0.830045
#> 015: 0.299234 0.965921 3.411482 0.147028 0.065119 0.008854 0.828014
#> 016: 0.296557 0.968780 3.412439 0.142049 0.062697 0.008819 0.829825
#> 017: 0.301181 0.968624 3.412841 0.141986 0.063694 0.008653 0.829478
#> 018: 0.302265 0.969492 3.411867 0.141653 0.063770 0.008469 0.831797
#> 019: 0.297096 0.971173 3.411014 0.139000 0.063844 0.008428 0.832478
#> 020: 0.295719 0.970786 3.411676 0.136934 0.062973 0.008331 0.832896
#> 021: 0.296313 0.970269 3.412745 0.133780 0.062369 0.008326 0.832039
#> 022: 0.295929 0.968986 3.413278 0.131895 0.062932 0.008154 0.831096
#> 023: 0.300475 0.969702 3.413923 0.132320 0.063767 0.007973 0.830692
#> 024: 0.305282 0.970974 3.414907 0.132679 0.064361 0.007801 0.829612
#> 025: 0.305960 0.970655 3.415266 0.134425 0.064468 0.007752 0.828770
#> 026: 0.305518 0.972429 3.414596 0.133795 0.064520 0.007710 0.829005
#> 027: 0.305864 0.972931 3.415149 0.133015 0.064204 0.007695 0.829063
#> 028: 0.305834 0.973216 3.414863 0.132775 0.064447 0.007567 0.828023
#> 029: 0.307110 0.972875 3.414641 0.134106 0.064937 0.007559 0.827898
#> 030: 0.308437 0.973293 3.414467 0.134239 0.065239 0.007624 0.827103
#> 001: 0.250224 0.973350 3.446505 0.381052 0.086079 0.016351 1.629574
#> 002: 0.238043 0.945447 3.463598 0.361999 0.081775 0.015533 1.148022
#> 003: 0.302269 0.841802 3.468763 0.343899 0.090469 0.014757 0.857538
#> 004: 0.243896 0.865882 3.459904 0.326704 0.111023 0.014019 0.756165
#> 005: 0.282010 0.882191 3.454090 0.310369 0.138965 0.013318 0.732686
#> 006: 0.222474 0.885134 3.439456 0.294850 0.137408 0.013019 0.659474
#> 007: 0.205525 0.892145 3.433143 0.280108 0.159956 0.013598 0.644376
#> 008: 0.196289 0.882056 3.422450 0.266103 0.151958 0.016950 0.625512
#> 009: 0.154722 0.867262 3.413034 0.252797 0.153009 0.016616 0.622420
#> 010: 0.161861 0.886435 3.409333 0.179466 0.147778 0.015684 0.616576
#> 011: 0.178851 0.885066 3.414862 0.190479 0.150189 0.016168 0.613058
#> 012: 0.192803 0.891881 3.415838 0.197485 0.142894 0.016087 0.612558
#> 013: 0.179534 0.903459 3.410968 0.187154 0.138015 0.016358 0.610325
#> 014: 0.186389 0.904350 3.413515 0.184616 0.140652 0.016013 0.611363
#> 015: 0.191013 0.904880 3.416840 0.180732 0.138288 0.016149 0.607843
#> 016: 0.194851 0.906830 3.417924 0.179089 0.136730 0.017363 0.605451
#> 017: 0.196487 0.907656 3.418840 0.179106 0.134246 0.017928 0.602876
#> 018: 0.199138 0.909915 3.418241 0.180375 0.132986 0.018225 0.601193
#> 019: 0.195281 0.910217 3.417478 0.181078 0.133218 0.018439 0.601077
#> 020: 0.193751 0.911645 3.417332 0.179321 0.132558 0.018496 0.600899
#> 021: 0.195542 0.912633 3.418240 0.178133 0.131680 0.018178 0.600791
#> 022: 0.196856 0.913167 3.419484 0.176285 0.131776 0.018081 0.600220
#> 023: 0.201760 0.912215 3.420795 0.178293 0.131133 0.018055 0.599618
#> 024: 0.206143 0.911332 3.421689 0.180024 0.130477 0.018251 0.598885
#> 025: 0.208976 0.909441 3.422674 0.181317 0.128259 0.018617 0.598188
#> 026: 0.209246 0.909773 3.422754 0.182192 0.127371 0.018828 0.597104
#> 027: 0.210086 0.911391 3.422127 0.185631 0.126914 0.019049 0.596365
#> 028: 0.210242 0.912131 3.422173 0.187723 0.125802 0.019472 0.595784
#> 029: 0.211096 0.912247 3.421602 0.191255 0.124943 0.019610 0.595855
#> 030: 0.211086 0.912450 3.421134 0.193390 0.125181 0.019772 0.595781
fit2
#> ── nlmixr² SAEM OBJF by FOCEi approximation ──
#>
#> Gaussian/Laplacian Likelihoods: AIC(fit) or fit$objf etc.
#> FOCEi CWRES & Likelihoods: addCwres(fit)
#>
#> ── Time (sec fit$time): ──
#>
#> setup covariance saem table compress other
#> elapsed 0.001 7.18 3.2 0.07 0.08 4.129
#>
#> ── Population Parameters (fit$parFixed or fit$parFixedDf): ──
#>
#> Parameter Est. SE %RSE Back-transformed(95%CI) BSV(CV%)
#> tka Log Ka 0.459 0.127 27.8 1.58 (1.23, 2.03) 70.2
#> tcl Log Cl 1.01 0.0895 8.85 2.75 (2.31, 3.28) 27.7
#> tv Log V 3.45 0.034 0.985 31.6 (29.6, 33.8) 13.2
#> add.sd 0.696 0.696
#> Shrink(SD)%
#> tka -5.46%
#> tcl 0.387%
#> tv 13.8%
#> add.sd
#>
#> Covariance Type (fit$covMethod): boot5
#> other calculated covs (setCov()): linFim
#> No correlations in between subject variability (BSV) matrix
#> Full BSV covariance (fit$omega) or correlation (fit$omegaR; diagonals=SDs)
#> Distribution stats (mean/skewness/kurtosis/p-value) available in fit$shrink
#> Censoring (fit$censInformation): No censoring
#>
#> ── Fit Data (object fit is a modified tibble): ──
#> # A tibble: 132 × 19
#> ID TIME DV PRED RES IPRED IRES IWRES eta.ka eta.cl eta.v cp
#> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 0 0.74 0 0.74 0 0.74 1.06 0.143 -0.439 -0.0982 0
#> 2 1 0.25 2.84 3.27 -0.430 4.06 -1.22 -1.75 0.143 -0.439 -0.0982 4.06
#> 3 1 0.57 6.57 5.85 0.721 7.08 -0.508 -0.731 0.143 -0.439 -0.0982 7.08
#> # … with 129 more rows, and 7 more variables: depot <dbl>, center <dbl>,
#> # ka <dbl>, cl <dbl>, v <dbl>, tad <dbl>, dosenum <dbl>