ADPPK

The Population PK Analysis Data (ADPPK) follows the CDISC Implementation Guide (https://www.cdisc.org/standards/foundational/adam/basic-data-structure-adam-poppk-implementation-guide-v1-0). Population PK models generally make use of nonlinear mixed effects models that require numeric variables. The data used in the models will include both dosing and concentration records, relative time variables, and numeric covariate variables. A DV or dependent variable is often expected. For more details see the {admiral} vignette.

First Load Packages

First we will load the packages required for our project. We will use {admiral} for the creation of analysis data. {admiral} requires {dplyr}, {lubridate} and {stringr}. Find other {admiral} functions and related variables by searching admiraldiscovery. We will use {metacore} and {metatools} to store and manipulate metadata from our specifications. We will use {xportr} to perform checks on the final data and export to a transport file.

The source SDTM data will come from the CDISC pilot study data stored in {pharmaversesdtm}.

# Load Packages
library(admiral)
library(dplyr)
library(lubridate)
library(stringr)
library(metacore)
library(metatools)
library(xportr)
library(readr)
library(pharmaversesdtm)
library(pharmaverseadam)

Next Load Specifications for Metacore

We have saved our specifications in an Excel file and will load them into {metacore} with the metacore::spec_to_metacore() function.

# ---- Load Specs for Metacore ----
metacore <- spec_to_metacore("./metadata/pk_spec.xlsx") %>%
  select_dataset("ADPPK")

Load Source Datasets

We will load are SDTM data from {pharmaversesdtm}. The main components of this will be exposure data from EX and pharmacokinetic concentration data from PC. We will use ADSL for baseline characteristics and we will derive additional baselines from vital signs VS and laboratory data LB.

# ---- Load source datasets ----
# Load PC, EX, VS, LB and ADSL

ex <- pharmaversesdtm::ex
pc <- pharmaversesdtm::pc
vs <- pharmaversesdtm::vs
lb <- pharmaversesdtm::lb

adsl <- pharmaverseadam::adsl

ex <- convert_blanks_to_na(ex)
pc <- convert_blanks_to_na(pc)
vs <- convert_blanks_to_na(vs)
lb <- convert_blanks_to_na(lb)

Derivations

Derive PC Dates

Here we use {admiral} functions for working with dates and we will also create a nominal time from first dose NFRLT for PC data based on PCTPTNUM.

# ---- Derivations ----

# Get list of ADSL vars required for derivations
adsl_vars <- exprs(TRTSDT, TRTSDTM, TRT01P, TRT01A)

pc_dates <- pc %>%
  # Join ADSL with PC (need TRTSDT for ADY derivation)
  derive_vars_merged(
    dataset_add = adsl,
    new_vars = adsl_vars,
    by_vars = exprs(STUDYID, USUBJID)
  ) %>%
  # Derive analysis date/time
  # Impute missing time to 00:00:00
  derive_vars_dtm(
    new_vars_prefix = "A",
    dtc = PCDTC,
    time_imputation = "00:00:00"
  ) %>%
  # Derive dates and times from date/times
  derive_vars_dtm_to_dt(exprs(ADTM)) %>%
  derive_vars_dtm_to_tm(exprs(ADTM)) %>%
  # Derive event ID and nominal relative time from first dose (NFRLT)
  mutate(
    EVID = 0,
    DRUG = PCTEST,
    NFRLT = if_else(PCTPTNUM < 0, 0, PCTPTNUM), .after = USUBJID
  )

Sample of Data

Get Dosing Information

Here we also create nominal time from first dose NFRLT for EX data based on VISITDY.

# ---- Get dosing information ----

ex_dates <- ex %>%
  derive_vars_merged(
    dataset_add = adsl,
    new_vars = adsl_vars,
    by_vars = exprs(STUDYID, USUBJID)
  ) %>%
  # Keep records with nonzero dose
  filter(EXDOSE > 0) %>%
  # Add time and set missing end date to start date
  # Impute missing time to 00:00:00
  # Note all times are missing for dosing records in this example data
  # Derive Analysis Start and End Dates
  derive_vars_dtm(
    new_vars_prefix = "AST",
    dtc = EXSTDTC,
    time_imputation = "00:00:00"
  ) %>%
  derive_vars_dtm(
    new_vars_prefix = "AEN",
    dtc = EXENDTC,
    time_imputation = "00:00:00"
  ) %>%
  # Derive event ID and nominal relative time from first dose (NFRLT)
  mutate(
    EVID = 1,
    NFRLT = case_when(
      VISITDY == 1 ~ 0,
      TRUE ~ 24 * VISITDY
    )
  ) %>%
  # Set missing end dates to start date
  mutate(AENDTM = case_when(
    is.na(AENDTM) ~ ASTDTM,
    TRUE ~ AENDTM
  )) %>%
  # Derive dates from date/times
  derive_vars_dtm_to_dt(exprs(ASTDTM)) %>%
  derive_vars_dtm_to_dt(exprs(AENDTM))

Sample of Data

Expand Dosing Records

Since there is a start date and end date for dosing records we need to expand the dosing records between the start date and end date using the function admiral::create_single_dose_dataset().

ex_exp <- ex_dates %>%
  create_single_dose_dataset(
    dose_freq = EXDOSFRQ,
    start_date = ASTDT,
    start_datetime = ASTDTM,
    end_date = AENDT,
    end_datetime = AENDTM,
    nominal_time = NFRLT,
    lookup_table = dose_freq_lookup,
    lookup_column = CDISC_VALUE,
    keep_source_vars = exprs(
      STUDYID, USUBJID, EVID, EXDOSFRQ, EXDOSFRM,
      NFRLT, EXDOSE, EXDOSU, EXTRT, ASTDT, ASTDTM, AENDT, AENDTM,
      VISIT, VISITNUM, VISITDY,
      TRT01A, TRT01P, DOMAIN, EXSEQ, !!!adsl_vars
    )
  ) %>%
  # Derive AVISIT based on nominal relative time
  # Derive AVISITN to nominal time in whole days using integer division
  # Define AVISIT based on nominal day
  mutate(
    AVISITN = NFRLT %/% 24 + 1,
    AVISIT = paste("Day", AVISITN),
    ADTM = ASTDTM,
    DRUG = EXTRT
  ) %>%
  # Derive dates and times from datetimes
  derive_vars_dtm_to_dt(exprs(ADTM)) %>%
  derive_vars_dtm_to_tm(exprs(ADTM)) %>%
  derive_vars_dtm_to_tm(exprs(ASTDTM)) %>%
  derive_vars_dtm_to_tm(exprs(AENDTM))

Sample of Data

Find First Dose

In this section we will find the first dose for each subject and drug.

# ---- Find first dose per treatment per subject ----
# ---- Join with ADPPK data and keep only subjects with dosing ----

adppk_first_dose <- pc_dates %>%
  derive_vars_merged(
    dataset_add = ex_exp,
    filter_add = (!is.na(ADTM)),
    new_vars = exprs(FANLDTM = ADTM, EXDOSE_first = EXDOSE),
    order = exprs(ADTM, EXSEQ),
    mode = "first",
    by_vars = exprs(STUDYID, USUBJID, DRUG)
  ) %>%
  filter(!is.na(FANLDTM)) %>%
  # Derive AVISIT based on nominal relative time
  # Derive AVISITN to nominal time in whole days using integer division
  # Define AVISIT based on nominal day
  mutate(
    AVISITN = NFRLT %/% 24 + 1,
    AVISIT = paste("Day", AVISITN),
  )

Sample of Data

Find Previous Dose

For ADPPK we will find the previous dose with respect to actual time and nominal time.

# ---- Find previous dose  ----

adppk_prev <- adppk_first_dose %>%
  derive_vars_joined(
    dataset_add = ex_exp,
    by_vars = exprs(USUBJID),
    order = exprs(ADTM),
    new_vars = exprs(
      ADTM_prev = ADTM, EXDOSE_prev = EXDOSE, AVISIT_prev = AVISIT,
      AENDTM_prev = AENDTM
    ),
    join_vars = exprs(ADTM),
    join_type = "all",
    filter_add = NULL,
    filter_join = ADTM > ADTM.join,
    mode = "last",
    check_type = "none"
  )

Sample of Data

Find Previous Nominal Dose

adppk_nom_prev <- adppk_prev %>%
  derive_vars_joined(
    dataset_add = ex_exp,
    by_vars = exprs(USUBJID),
    order = exprs(NFRLT),
    new_vars = exprs(NFRLT_prev = NFRLT),
    join_vars = exprs(NFRLT),
    join_type = "all",
    filter_add = NULL,
    filter_join = NFRLT > NFRLT.join,
    mode = "last",
    check_type = "none"
  )

Sample of Data

Combine PC and EX Data

Here we combine PC and EX records. We will derive the relative time variables AFRLT (Actual Relative Time from First Dose), APRLT (Actual Relative Time from Previous Dose), and NPRLT (Nominal Relative Time from Previous Dose).

adppk_aprlt <- bind_rows(adppk_nom_prev, ex_exp) %>%
  group_by(USUBJID, DRUG) %>%
  mutate(
    FANLDTM = min(FANLDTM, na.rm = TRUE),
    min_NFRLT = min(NFRLT, na.rm = TRUE),
    maxdate = max(ADT[EVID == 0], na.rm = TRUE), .after = USUBJID
  ) %>%
  arrange(USUBJID, ADTM) %>%
  ungroup() %>%
  filter(ADT <= maxdate) %>%
  # Derive Actual Relative Time from First Dose (AFRLT)
  derive_vars_duration(
    new_var = AFRLT,
    start_date = FANLDTM,
    end_date = ADTM,
    out_unit = "hours",
    floor_in = FALSE,
    add_one = FALSE
  ) %>%
  # Derive Actual Relative Time from Reference Dose (APRLT)
  derive_vars_duration(
    new_var = APRLT,
    start_date = ADTM_prev,
    end_date = ADTM,
    out_unit = "hours",
    floor_in = FALSE,
    add_one = FALSE
  ) %>%
  # Derive APRLT
  mutate(
    APRLT = case_when(
      EVID == 1 ~ 0,
      is.na(APRLT) ~ AFRLT,
      TRUE ~ APRLT
    ),
    NPRLT = case_when(
      EVID == 1 ~ 0,
      is.na(NFRLT_prev) ~ NFRLT - min_NFRLT,
      TRUE ~ NFRLT - NFRLT_prev
    )
  )

Sample of Data

Derive Analysis Variables

The expected analysis variable for ADPPK is DV or dependent variable. For this example DV is set to the numeric concentration value PCSTRESN. We will also include AVAL equivalent to DV for consistency with CDISC ADaM standards. MDV missing dependent variable will also be included.

# ---- Derive Analysis Variables ----
# Derive actual dose DOSEA and planned dose DOSEP,
# Derive AVAL and DV

adppk_aval <- adppk_aprlt %>%
  mutate(
    # Derive Actual Dose
    DOSEA = case_when(
      EVID == 1 ~ EXDOSE,
      is.na(EXDOSE_prev) ~ EXDOSE_first,
      TRUE ~ EXDOSE_prev
    ),
    # Derive Planned Dose
    DOSEP = case_when(
      TRT01P == "Xanomeline High Dose" ~ 81,
      TRT01P == "Xanomeline Low Dose" ~ 54,
      TRT01P == "Placebo" ~ 0
    ),
    # Derive PARAMCD
    PARAMCD = case_when(
      EVID == 1 ~ "DOSE",
      TRUE ~ PCTESTCD
    ),
    ALLOQ = PCLLOQ,
    # Derive CMT
    CMT = case_when(
      EVID == 1 ~ 1,
      PCSPEC == "PLASMA" ~ 2,
      TRUE ~ 3
    ),
    # Derive BLQFL/BLQFN
    BLQFL = case_when(
      PCSTRESC == "<BLQ" ~ "Y",
      TRUE ~ "N"
    ),
    BLQFN = case_when(
      PCSTRESC == "<BLQ" ~ 1,
      TRUE ~ 0
    ),
    AMT = case_when(
      EVID == 1 ~ EXDOSE,
      TRUE ~ NA_real_
    ),
    # Derive DV and AVAL
    DV = PCSTRESN,
    DVID = PCTESTCD,
    AVAL = DV,
    DVL = case_when(
      DV != 0 ~ log(DV),
      TRUE ~ NA_real_
    ),
    # Derive MDV
    MDV = case_when(
      EVID == 1 ~ 1,
      is.na(DV) ~ 1,
      TRUE ~ 0
    ),
    AVALU = case_when(
      EVID == 1 ~ NA_character_,
      TRUE ~ PCSTRESU
    ),
    RLTU = "h",
    USTRESC = PCSTRESC,
    UDTC = format_ISO8601(ADTM),
    II = if_else(EVID == 1, 1, 0),
    SS = if_else(EVID == 1, 1, 0),
    ADDL = 0,
    OCC = 1,
  )

Sample of Data

Add ASEQ

# ---- Add ASEQ ----

adppk_aseq <- adppk_aval %>%
  # Calculate ASEQ
  derive_var_obs_number(
    new_var = ASEQ,
    by_vars = exprs(STUDYID, USUBJID),
    order = exprs(AFRLT, EVID, CMT),
    check_type = "error"
  ) %>%
  mutate(
    PROJID = DRUG,
    PROJIDN = 1,
    PART = 1,
  )

Derive Covariates Using `{metatools}`

In this step we will create our numeric covariates using the metatools::create_var_from_codelist() function.

#---- Derive Covariates ----
# Include numeric values for STUDYIDN, USUBJIDN, SEXN, RACEN etc.

covar <- adsl %>%
  create_var_from_codelist(metacore, input_var = STUDYID, out_var = STUDYIDN) %>%
  create_var_from_codelist(metacore, input_var = SEX, out_var = SEXN) %>%
  create_var_from_codelist(metacore, input_var = RACE, out_var = RACEN) %>%
  create_var_from_codelist(metacore, input_var = ETHNIC, out_var = AETHNIC) %>%
  create_var_from_codelist(metacore, input_var = AETHNIC, out_var = AETHNICN) %>%
  create_var_from_codelist(metacore, input_var = ARMCD, out_var = COHORT) %>%
  create_var_from_codelist(metacore, input_var = ARMCD, out_var = COHORTC) %>%
  create_var_from_codelist(metacore, input_var = COUNTRY, out_var = COUNTRYN) %>%
  create_var_from_codelist(metacore, input_var = COUNTRY, out_var = COUNTRYL) %>%
  mutate(
    STUDYIDN = as.numeric(word(USUBJID, 1, sep = fixed("-"))),
    SITEIDN = as.numeric(word(USUBJID, 2, sep = fixed("-"))),
    USUBJIDN = as.numeric(word(USUBJID, 3, sep = fixed("-"))),
    SUBJIDN = as.numeric(SUBJID),
    ROUTE = unique(ex$EXROUTE),
    FORM = unique(ex$EXDOSFRM),
    REGION1 = COUNTRY,
    REGION1N = COUNTRYN,
    SUBJTYPC = "Volunteer",
  ) %>%
  create_var_from_codelist(metacore, input_var = FORM, out_var = FORMN) %>%
  create_var_from_codelist(metacore, input_var = ROUTE, out_var = ROUTEN) %>%
  create_var_from_codelist(metacore, input_var = SUBJTYPC, out_var = SUBJTYP)

Sample of Data

Derive Additional Baselines

Next we add additional baselines from vital signs and laboratory data.

labsbl <- lb %>%
  filter(LBBLFL == "Y" & LBTESTCD %in% c("CREAT", "ALT", "AST", "BILI")) %>%
  mutate(LBTESTCDB = paste0(LBTESTCD, "BL")) %>%
  select(STUDYID, USUBJID, LBTESTCDB, LBSTRESN)

covar_vslb <- covar %>%
  derive_vars_merged(
    dataset_add = vs,
    filter_add = VSTESTCD == "HEIGHT",
    by_vars = exprs(STUDYID, USUBJID),
    new_vars = exprs(HTBL = VSSTRESN)
  ) %>%
  derive_vars_merged(
    dataset_add = vs,
    filter_add = VSTESTCD == "WEIGHT" & VSBLFL == "Y",
    by_vars = exprs(STUDYID, USUBJID),
    new_vars = exprs(WTBL = VSSTRESN)
  ) %>%
  derive_vars_transposed(
    dataset_merge = labsbl,
    by_vars = exprs(STUDYID, USUBJID),
    key_var = LBTESTCDB,
    value_var = LBSTRESN
  ) %>%
  mutate(
    BMIBL = compute_bmi(height = HTBL, weight = WTBL),
    BSABL = compute_bsa(
      height = HTBL,
      weight = HTBL,
      method = "Mosteller"
    ),
    CRCLBL = compute_egfr(
      creat = CREATBL, creatu = "SI", age = AGE, weight = WTBL, sex = SEX,
      method = "CRCL"
    ),
    EGFRBL = compute_egfr(
      creat = CREATBL, creatu = "SI", age = AGE, weight = WTBL, sex = SEX,
      method = "CKD-EPI"
    )
  ) %>%
  rename(TBILBL = BILIBL)

Sample of Data

Combine with Covariates

We combine our covariates with the rest of the data

# Combine covariates with APPPK data

adppk_prefinal <- adppk_aseq %>%
  derive_vars_merged(
    dataset_add = select(covar_vslb, !!!negate_vars(adsl_vars)),
    by_vars = exprs(STUDYID, USUBJID)
  ) %>%
  arrange(STUDYIDN, USUBJIDN, AFRLT, EVID) %>%
  # Add RECSEQ
  # Exclude records if needed
  mutate(
    RECSEQ = row_number(),
    EXCLFCOM = "None"
  ) %>%
  create_var_from_codelist(metacore, input_var = DVID, out_var = DVIDN) %>%
  create_var_from_codelist(metacore, input_var = EXCLFCOM, out_var = EXCLF)

Check Data With metacore and metatools

We use {metacore} objects with {metatools} functions to perform a number of checks on the data. We will drop variables not in the specs and make sure all the variables from the specs are included.

adppk <- adppk_prefinal %>%
  drop_unspec_vars(metacore) %>% # Drop unspecified variables from specs
  check_variables(metacore) %>% # Check all variables specified are present and no more
  check_ct_data(metacore) %>% # Checks all variables with CT only contain values within the CT
  order_cols(metacore) %>% # Orders the columns according to the spec
  sort_by_key(metacore) # Sorts the rows by the sort keys

Apply Labels and Formats with xportr

Using {xportr} we check variable type, assign variable lenght, add variable labels, add variable formats, and save a transport file with xportr::xportr_write().

dir <- tempdir() # Change to whichever directory you want to save the dataset in

adppk_xpt <- adppk %>%
  xportr_type(metacore, domain = "ADPPK") %>% # Coerce variable type to match spec
  xportr_length(metacore) %>% # Assigns SAS length from a variable level metadata
  xportr_label(metacore) %>% # Assigns variable label from metacore specifications
  xportr_format(metacore) %>% # Assigns variable format from metacore specifications
  xportr_df_label(metacore) %>% # Assigns dataset label from metacore specifications
  xportr_write(file.path(dir, "adppk.xpt")) # Write xpt v5 transport file

--- title: "ADPPK" order: 3 --- ```{r setup script, include=FALSE, purl=FALSE} invisible_hook_purl <- function(before, options, ...) { knitr::hook_purl(before, options, ...) NULL } knitr::knit_hooks$set(purl = invisible_hook_purl) source("functions/print_df.R") ``` The Population PK Analysis Data (ADPPK) follows the CDISC Implementation Guide (<https://www.cdisc.org/standards/foundational/adam/basic-data-structure-adam-poppk-implementation-guide-v1-0>). Population PK models generally make use of nonlinear mixed effects models that require numeric variables. The data used in the models will include both dosing and concentration records, relative time variables, and numeric covariate variables. A `DV` or dependent variable is often expected. For more details see the `{admiral}` [vignette](https://pharmaverse.github.io/admiral/articles/pk_adnca.html){target="_blank"}. ## First Load Packages First we will load the packages required for our project. We will use `{admiral}` for the creation of analysis data. `{admiral}` requires `{dplyr}`, `{lubridate}` and `{stringr}`. Find other `{admiral}` functions and related variables by searching [admiraldiscovery](<https://pharmaverse.github.io/admiraldiscovery/articles/reactable.html>). We will use `{metacore}` and `{metatools}` to store and manipulate metadata from our specifications. We will use `{xportr}` to perform checks on the final data and export to a transport file. The source SDTM data will come from the CDISC pilot study data stored in `{pharmaversesdtm}`. ```{r echo=TRUE, message=FALSE} #| label: Load Packages # Load Packages library(admiral) library(dplyr) library(lubridate) library(stringr) library(metacore) library(metatools) library(xportr) library(readr) library(pharmaversesdtm) library(pharmaverseadam) ``` ## Next Load Specifications for Metacore We have saved our specifications in an Excel file and will load them into `{metacore}` with the `metacore::spec_to_metacore()` function. ```{r echo=TRUE, message=FALSE} #| label: Load Specs #| warning: false # ---- Load Specs for Metacore ---- metacore <- spec_to_metacore("./metadata/pk_spec.xlsx") %>% select_dataset("ADPPK") ``` ## Load Source Datasets We will load are SDTM data from `{pharmaversesdtm}`. The main components of this will be exposure data from `EX` and pharmacokinetic concentration data from `PC`. We will use `ADSL` for baseline characteristics and we will derive additional baselines from vital signs `VS` and laboratory data `LB`. ```{r} #| label: Load Source # ---- Load source datasets ---- # Load PC, EX, VS, LB and ADSL ex <- pharmaversesdtm::ex pc <- pharmaversesdtm::pc vs <- pharmaversesdtm::vs lb <- pharmaversesdtm::lb adsl <- pharmaverseadam::adsl ex <- convert_blanks_to_na(ex) pc <- convert_blanks_to_na(pc) vs <- convert_blanks_to_na(vs) lb <- convert_blanks_to_na(lb) ``` ## Derivations ### Derive PC Dates Here we use `{admiral}` functions for working with dates and we will also create a nominal time from first dose `NFRLT` for `PC` data based on `PCTPTNUM`. ```{r} #| label: PC Dates # ---- Derivations ---- # Get list of ADSL vars required for derivations adsl_vars <- exprs(TRTSDT, TRTSDTM, TRT01P, TRT01A) pc_dates <- pc %>% # Join ADSL with PC (need TRTSDT for ADY derivation) derive_vars_merged( dataset_add = adsl, new_vars = adsl_vars, by_vars = exprs(STUDYID, USUBJID) ) %>% # Derive analysis date/time # Impute missing time to 00:00:00 derive_vars_dtm( new_vars_prefix = "A", dtc = PCDTC, time_imputation = "00:00:00" ) %>% # Derive dates and times from date/times derive_vars_dtm_to_dt(exprs(ADTM)) %>% derive_vars_dtm_to_tm(exprs(ADTM)) %>% # Derive event ID and nominal relative time from first dose (NFRLT) mutate( EVID = 0, DRUG = PCTEST, NFRLT = if_else(PCTPTNUM < 0, 0, PCTPTNUM), .after = USUBJID ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(pc_dates %>% select(USUBJID, PCTEST, ADTM, VISIT, PCTPT, NFRLT)) ``` ### Get Dosing Information Here we also create nominal time from first dose `NFRLT` for `EX` data based on `VISITDY`. ```{r} #| label: Dosing # ---- Get dosing information ---- ex_dates <- ex %>% derive_vars_merged( dataset_add = adsl, new_vars = adsl_vars, by_vars = exprs(STUDYID, USUBJID) ) %>% # Keep records with nonzero dose filter(EXDOSE > 0) %>% # Add time and set missing end date to start date # Impute missing time to 00:00:00 # Note all times are missing for dosing records in this example data # Derive Analysis Start and End Dates derive_vars_dtm( new_vars_prefix = "AST", dtc = EXSTDTC, time_imputation = "00:00:00" ) %>% derive_vars_dtm( new_vars_prefix = "AEN", dtc = EXENDTC, time_imputation = "00:00:00" ) %>% # Derive event ID and nominal relative time from first dose (NFRLT) mutate( EVID = 1, NFRLT = case_when( VISITDY == 1 ~ 0, TRUE ~ 24 * VISITDY ) ) %>% # Set missing end dates to start date mutate(AENDTM = case_when( is.na(AENDTM) ~ ASTDTM, TRUE ~ AENDTM )) %>% # Derive dates from date/times derive_vars_dtm_to_dt(exprs(ASTDTM)) %>% derive_vars_dtm_to_dt(exprs(AENDTM)) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(ex_dates %>% select( USUBJID, EXTRT, EXDOSFRQ, EXSTDTC, EXENDTC, VISIT, VISITDY )) ``` ### Expand Dosing Records Since there is a start date and end date for dosing records we need to expand the dosing records between the start date and end date using the function `admiral::create_single_dose_dataset()`. ```{r} #| label: Expand ex_exp <- ex_dates %>% create_single_dose_dataset( dose_freq = EXDOSFRQ, start_date = ASTDT, start_datetime = ASTDTM, end_date = AENDT, end_datetime = AENDTM, nominal_time = NFRLT, lookup_table = dose_freq_lookup, lookup_column = CDISC_VALUE, keep_source_vars = exprs( STUDYID, USUBJID, EVID, EXDOSFRQ, EXDOSFRM, NFRLT, EXDOSE, EXDOSU, EXTRT, ASTDT, ASTDTM, AENDT, AENDTM, VISIT, VISITNUM, VISITDY, TRT01A, TRT01P, DOMAIN, EXSEQ, !!!adsl_vars ) ) %>% # Derive AVISIT based on nominal relative time # Derive AVISITN to nominal time in whole days using integer division # Define AVISIT based on nominal day mutate( AVISITN = NFRLT %/% 24 + 1, AVISIT = paste("Day", AVISITN), ADTM = ASTDTM, DRUG = EXTRT ) %>% # Derive dates and times from datetimes derive_vars_dtm_to_dt(exprs(ADTM)) %>% derive_vars_dtm_to_tm(exprs(ADTM)) %>% derive_vars_dtm_to_tm(exprs(ASTDTM)) %>% derive_vars_dtm_to_tm(exprs(AENDTM)) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df( ex_exp %>% select(USUBJID, DRUG, EXDOSFRQ, ASTDT, AVISIT, NFRLT) ) ``` ### Find First Dose In this section we will find the first dose for each subject and drug. ```{r} #| label: First Dose # ---- Find first dose per treatment per subject ---- # ---- Join with ADPPK data and keep only subjects with dosing ---- adppk_first_dose <- pc_dates %>% derive_vars_merged( dataset_add = ex_exp, filter_add = (!is.na(ADTM)), new_vars = exprs(FANLDTM = ADTM, EXDOSE_first = EXDOSE), order = exprs(ADTM, EXSEQ), mode = "first", by_vars = exprs(STUDYID, USUBJID, DRUG) ) %>% filter(!is.na(FANLDTM)) %>% # Derive AVISIT based on nominal relative time # Derive AVISITN to nominal time in whole days using integer division # Define AVISIT based on nominal day mutate( AVISITN = NFRLT %/% 24 + 1, AVISIT = paste("Day", AVISITN), ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(adppk_first_dose %>% select(USUBJID, FANLDTM, NFRLT, ADTM, AVISITN, AVISIT, PCTPT)) ``` ### Find Previous Dose For `ADPPK` we will find the previous dose with respect to actual time and nominal time. ```{r} #| label: Previous Dose # ---- Find previous dose ---- adppk_prev <- adppk_first_dose %>% derive_vars_joined( dataset_add = ex_exp, by_vars = exprs(USUBJID), order = exprs(ADTM), new_vars = exprs( ADTM_prev = ADTM, EXDOSE_prev = EXDOSE, AVISIT_prev = AVISIT, AENDTM_prev = AENDTM ), join_vars = exprs(ADTM), join_type = "all", filter_add = NULL, filter_join = ADTM > ADTM.join, mode = "last", check_type = "none" ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(adppk_prev %>% select(USUBJID, VISIT, ADTM, VISIT, PCTPT, ADTM_prev, AVISIT_prev)) ``` ### Find Previous Nominal Dose ```{r} #| label: Previous Nominal Dose adppk_nom_prev <- adppk_prev %>% derive_vars_joined( dataset_add = ex_exp, by_vars = exprs(USUBJID), order = exprs(NFRLT), new_vars = exprs(NFRLT_prev = NFRLT), join_vars = exprs(NFRLT), join_type = "all", filter_add = NULL, filter_join = NFRLT > NFRLT.join, mode = "last", check_type = "none" ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(adppk_nom_prev %>% select(USUBJID, VISIT, ADTM, NFRLT, NFRLT_prev)) ``` ### Combine PC and EX Data Here we combine `PC` and `EX` records. We will derive the relative time variables `AFRLT` (Actual Relative Time from First Dose), `APRLT` (Actual Relative Time from Previous Dose), and `NPRLT` (Nominal Relative Time from Previous Dose). ```{r} #| label: Combine adppk_aprlt <- bind_rows(adppk_nom_prev, ex_exp) %>% group_by(USUBJID, DRUG) %>% mutate( FANLDTM = min(FANLDTM, na.rm = TRUE), min_NFRLT = min(NFRLT, na.rm = TRUE), maxdate = max(ADT[EVID == 0], na.rm = TRUE), .after = USUBJID ) %>% arrange(USUBJID, ADTM) %>% ungroup() %>% filter(ADT <= maxdate) %>% # Derive Actual Relative Time from First Dose (AFRLT) derive_vars_duration( new_var = AFRLT, start_date = FANLDTM, end_date = ADTM, out_unit = "hours", floor_in = FALSE, add_one = FALSE ) %>% # Derive Actual Relative Time from Reference Dose (APRLT) derive_vars_duration( new_var = APRLT, start_date = ADTM_prev, end_date = ADTM, out_unit = "hours", floor_in = FALSE, add_one = FALSE ) %>% # Derive APRLT mutate( APRLT = case_when( EVID == 1 ~ 0, is.na(APRLT) ~ AFRLT, TRUE ~ APRLT ), NPRLT = case_when( EVID == 1 ~ 0, is.na(NFRLT_prev) ~ NFRLT - min_NFRLT, TRUE ~ NFRLT - NFRLT_prev ) ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(adppk_aprlt %>% select(USUBJID, FANLDTM, AVISIT, PCTPT, APRLT, NPRLT)) ``` ### Derive Analysis Variables The expected analysis variable for `ADPPK` is `DV` or dependent variable. For this example `DV` is set to the numeric concentration value `PCSTRESN`. We will also include `AVAL` equivalent to `DV` for consistency with CDISC ADaM standards. `MDV` missing dependent variable will also be included. ```{r} #| label: Analysis Variables # ---- Derive Analysis Variables ---- # Derive actual dose DOSEA and planned dose DOSEP, # Derive AVAL and DV adppk_aval <- adppk_aprlt %>% mutate( # Derive Actual Dose DOSEA = case_when( EVID == 1 ~ EXDOSE, is.na(EXDOSE_prev) ~ EXDOSE_first, TRUE ~ EXDOSE_prev ), # Derive Planned Dose DOSEP = case_when( TRT01P == "Xanomeline High Dose" ~ 81, TRT01P == "Xanomeline Low Dose" ~ 54, TRT01P == "Placebo" ~ 0 ), # Derive PARAMCD PARAMCD = case_when( EVID == 1 ~ "DOSE", TRUE ~ PCTESTCD ), ALLOQ = PCLLOQ, # Derive CMT CMT = case_when( EVID == 1 ~ 1, PCSPEC == "PLASMA" ~ 2, TRUE ~ 3 ), # Derive BLQFL/BLQFN BLQFL = case_when( PCSTRESC == "<BLQ" ~ "Y", TRUE ~ "N" ), BLQFN = case_when( PCSTRESC == "<BLQ" ~ 1, TRUE ~ 0 ), AMT = case_when( EVID == 1 ~ EXDOSE, TRUE ~ NA_real_ ), # Derive DV and AVAL DV = PCSTRESN, DVID = PCTESTCD, AVAL = DV, DVL = case_when( DV != 0 ~ log(DV), TRUE ~ NA_real_ ), # Derive MDV MDV = case_when( EVID == 1 ~ 1, is.na(DV) ~ 1, TRUE ~ 0 ), AVALU = case_when( EVID == 1 ~ NA_character_, TRUE ~ PCSTRESU ), RLTU = "h", USTRESC = PCSTRESC, UDTC = format_ISO8601(ADTM), II = if_else(EVID == 1, 1, 0), SS = if_else(EVID == 1, 1, 0), ADDL = 0, OCC = 1, ) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(adppk_aval %>% select(USUBJID, AVISIT, EVID, NFRLT, DV)) ``` ### Add ASEQ ```{r} #| label: ASEQ # ---- Add ASEQ ---- adppk_aseq <- adppk_aval %>% # Calculate ASEQ derive_var_obs_number( new_var = ASEQ, by_vars = exprs(STUDYID, USUBJID), order = exprs(AFRLT, EVID, CMT), check_type = "error" ) %>% mutate( PROJID = DRUG, PROJIDN = 1, PART = 1, ) ``` ## Derive Covariates Using `{metatools}` In this step we will create our numeric covariates using the `metatools::create_var_from_codelist()` function. ```{r} #| label: Covariates #---- Derive Covariates ---- # Include numeric values for STUDYIDN, USUBJIDN, SEXN, RACEN etc. covar <- adsl %>% create_var_from_codelist(metacore, input_var = STUDYID, out_var = STUDYIDN) %>% create_var_from_codelist(metacore, input_var = SEX, out_var = SEXN) %>% create_var_from_codelist(metacore, input_var = RACE, out_var = RACEN) %>% create_var_from_codelist(metacore, input_var = ETHNIC, out_var = AETHNIC) %>% create_var_from_codelist(metacore, input_var = AETHNIC, out_var = AETHNICN) %>% create_var_from_codelist(metacore, input_var = ARMCD, out_var = COHORT) %>% create_var_from_codelist(metacore, input_var = ARMCD, out_var = COHORTC) %>% create_var_from_codelist(metacore, input_var = COUNTRY, out_var = COUNTRYN) %>% create_var_from_codelist(metacore, input_var = COUNTRY, out_var = COUNTRYL) %>% mutate( STUDYIDN = as.numeric(word(USUBJID, 1, sep = fixed("-"))), SITEIDN = as.numeric(word(USUBJID, 2, sep = fixed("-"))), USUBJIDN = as.numeric(word(USUBJID, 3, sep = fixed("-"))), SUBJIDN = as.numeric(SUBJID), ROUTE = unique(ex$EXROUTE), FORM = unique(ex$EXDOSFRM), REGION1 = COUNTRY, REGION1N = COUNTRYN, SUBJTYPC = "Volunteer", ) %>% create_var_from_codelist(metacore, input_var = FORM, out_var = FORMN) %>% create_var_from_codelist(metacore, input_var = ROUTE, out_var = ROUTEN) %>% create_var_from_codelist(metacore, input_var = SUBJTYPC, out_var = SUBJTYP) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(covar %>% select(USUBJID, SEX, SEXN, RACE, RACEN)) ``` ### Derive Additional Baselines Next we add additional baselines from vital signs and laboratory data. ```{r} #| label: Baselines labsbl <- lb %>% filter(LBBLFL == "Y" & LBTESTCD %in% c("CREAT", "ALT", "AST", "BILI")) %>% mutate(LBTESTCDB = paste0(LBTESTCD, "BL")) %>% select(STUDYID, USUBJID, LBTESTCDB, LBSTRESN) covar_vslb <- covar %>% derive_vars_merged( dataset_add = vs, filter_add = VSTESTCD == "HEIGHT", by_vars = exprs(STUDYID, USUBJID), new_vars = exprs(HTBL = VSSTRESN) ) %>% derive_vars_merged( dataset_add = vs, filter_add = VSTESTCD == "WEIGHT" & VSBLFL == "Y", by_vars = exprs(STUDYID, USUBJID), new_vars = exprs(WTBL = VSSTRESN) ) %>% derive_vars_transposed( dataset_merge = labsbl, by_vars = exprs(STUDYID, USUBJID), key_var = LBTESTCDB, value_var = LBSTRESN ) %>% mutate( BMIBL = compute_bmi(height = HTBL, weight = WTBL), BSABL = compute_bsa( height = HTBL, weight = HTBL, method = "Mosteller" ), CRCLBL = compute_egfr( creat = CREATBL, creatu = "SI", age = AGE, weight = WTBL, sex = SEX, method = "CRCL" ), EGFRBL = compute_egfr( creat = CREATBL, creatu = "SI", age = AGE, weight = WTBL, sex = SEX, method = "CKD-EPI" ) ) %>% rename(TBILBL = BILIBL) ``` ```{r eval=TRUE, echo=FALSE, purl=FALSE} print_df(covar_vslb %>% select(USUBJID, WTBL, HTBL, BMIBL, CRCLBL)) ``` ### Combine with Covariates We combine our covariates with the rest of the data ```{r} #| label: Combine with Covariates # Combine covariates with APPPK data adppk_prefinal <- adppk_aseq %>% derive_vars_merged( dataset_add = select(covar_vslb, !!!negate_vars(adsl_vars)), by_vars = exprs(STUDYID, USUBJID) ) %>% arrange(STUDYIDN, USUBJIDN, AFRLT, EVID) %>% # Add RECSEQ # Exclude records if needed mutate( RECSEQ = row_number(), EXCLFCOM = "None" ) %>% create_var_from_codelist(metacore, input_var = DVID, out_var = DVIDN) %>% create_var_from_codelist(metacore, input_var = EXCLFCOM, out_var = EXCLF) ``` ## Check Data With metacore and metatools We use `{metacore}` objects with `{metatools}` functions to perform a number of checks on the data. We will drop variables not in the specs and make sure all the variables from the specs are included. ```{r} #| label: Metacore #| warning: false adppk <- adppk_prefinal %>% drop_unspec_vars(metacore) %>% # Drop unspecified variables from specs check_variables(metacore) %>% # Check all variables specified are present and no more check_ct_data(metacore) %>% # Checks all variables with CT only contain values within the CT order_cols(metacore) %>% # Orders the columns according to the spec sort_by_key(metacore) # Sorts the rows by the sort keys ``` ## Apply Labels and Formats with xportr Using {xportr} we check variable type, assign variable lenght, add variable labels, add variable formats, and save a transport file with `xportr::xportr_write()`. ```{r} #| label: xportr dir <- tempdir() # Change to whichever directory you want to save the dataset in adppk_xpt <- adppk %>% xportr_type(metacore, domain = "ADPPK") %>% # Coerce variable type to match spec xportr_length(metacore) %>% # Assigns SAS length from a variable level metadata xportr_label(metacore) %>% # Assigns variable label from metacore specifications xportr_format(metacore) %>% # Assigns variable format from metacore specifications xportr_df_label(metacore) %>% # Assigns dataset label from metacore specifications xportr_write(file.path(dir, "adppk.xpt")) # Write xpt v5 transport file ```

First Load Packages

Next Load Specifications for Metacore

Load Source Datasets

Derivations

Derive PC Dates

Sample of Data

Get Dosing Information

Sample of Data

Expand Dosing Records

Sample of Data

Find First Dose

Sample of Data

Find Previous Dose

Sample of Data

Find Previous Nominal Dose

Sample of Data

Combine PC and EX Data

Sample of Data

Derive Analysis Variables

Sample of Data

Add ASEQ

Derive Covariates Using {metatools}

Sample of Data

Derive Additional Baselines

Sample of Data

Combine with Covariates

Check Data With metacore and metatools

Apply Labels and Formats with xportr

Derive Covariates Using `{metatools}`