Skip to content

helenhe96/clinical-data-science-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Analytical Data Science Programming Exercise

Requirements

R version >= 4.2 recommended.

Install required packages before running:

install.packages(c(
  "tidyverse",
  "admiral",
  "sdtm.oak",
  "pharmaverseraw",
  "pharmaversesdtm",
  "gt",
  "gtsummary",
  "pharmaverseadam"
))

Repository Structure

  • question_1_sdtm/ SDTM DS domain mapping using sdtm.oak from pharmaverse raw inputs
  • question_2_adam/ ADaM ADSL derivation using admiral from pharmaversesdtm inputs
  • question_3_tlg/ TLG outputs (1 table + 2 figures) from pharmaverseadam ADAE/ADSL

Data Sources

All example datasets are sourced from the pharmaverse ecosystem:

  • SDTM raw inputs: pharmaverseraw
  • SDTM domains: pharmaversesdtm
  • ADaM datasets: pharmaverseadam

No external data files are required beyond those included in the repository.

Recommended Run Order

From the project root directory, run in R:

source("question_1_sdtm/01_create_ds_domain.R")
source("question_2_adam/create_adsl.R")
source("question_3_tlg/01_create_ae_summary_table.R")
source("question_3_tlg/02_create_visualizations.R")

Logging and Reproducibility Notes

  • Each script writes a run log using sink() to its corresponding run_log*.txt file.
  • Outputs are created/overwritten on each run.
  • Scripts assume the working directory is the project root (so relative paths resolve correctly).

Question 1 (SDTM DS)

Files

  • question_1_sdtm/01_create_ds_domain.R : Builds the SDTM DS domain
  • question_1_sdtm/sdtm_ct.csv : Controlled terminology used for mapping

How to run

From the project root directory, run in R:

source("question_1_sdtm/01_create_ds_domain.R")

Outputs (created/overwritten on each run)

  • question_1_sdtm/ds.csv
  • question_1_sdtm/run_log.txt

Question 2 (ADaM ADSL)

Files

  • question_2_adam/create_adsl.R : Builds the ADaM ADSL dataset

How to run

From the project root directory, run in R:

source("question_2_adam/create_adsl.R")

Outputs (created/overwritten on each run)

  • question_2_adam/adsl.csv
  • question_2_adam/run_log.txt

Question 3 (TLG – Tables, Listings, Figures)

Files

  • question_3_tlg/01_create_ae_summary_table.R : Builds the TEAE hierarchical summary table
  • question_3_tlg/02_create_visualizations.R : Generates AE visualizations

How to run

From the project root directory, run in R:

source("question_3_tlg/01_create_ae_summary_table.R")
source("question_3_tlg/02_create_visualizations.R")

Outputs (created/overwritten on each run)

Part 1

  • question_3_tlg/ae_summary_table.html
  • question_3_tlg/run_log_01.txt

Part 2

  • question_3_tlg/ae_severity_by_treatment.png
  • question_3_tlg/top10_ae_with_ci.png
  • question_3_tlg/run_log_02.txt

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors