Skip to content

Job request: 5714

Organisation:
University of Bristol
Workspace:
covid-ve-change-over-time--manuscript
ID:
dwxu4htis7drjr4e
View repo View project.yaml

This page shows the technical details of what happened when the authorised researcher Elsie Horne requested one or more actions to be run against real patient data within a secure environment.

By cross-referencing the list of jobs with the pipeline section below, you can infer what security level the outputs were written to.

The output security levels are:

  • highly_sensitive
    • Researchers can never directly view these outputs
    • Researchers can only request code is run against them
  • moderately_sensitive
    • Can be viewed by an approved researcher by logging into a highly secure environment
    • These are the only outputs that can be requested for public release via a controlled output review service.

Jobs

Pipeline

Show project.yaml 
version: '3.0'

expectations:

  population_size: 100000

actions:

  ## # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 
  ## DO NOT EDIT project.yaml or study_definition_1-6.py DIRECTLY 
  ## These files are created by create-project.R 
  ## Edit and run create-project.R to update the project.yaml 
  ## Edit study_definition_k.py and run create-project.R to update 
  ## study_definition_1-6.py 
  ## # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # 
  ## #################################### 
  ## preliminaries 
  ## #################################### 

  design:
    run: r:latest analysis/design.R
    outputs:
      moderately_sensitive:
        study_dates_json: output/lib/study_parameters.json
        study_dates_rds: output/lib/study_parameters.rds
        jcvi_groups: output/lib/jcvi_groups.csv
        elig_dates: output/lib/elig_dates.csv
        regions: output/lib/regions.csv
        model_varlist: output/lib/model_varlist.rds
        outcomes: output/lib/outcomes.rds
        strata_vars: output/lib/strata_vars.rds
        subgroups: output/lib/subgroups.rds

  ## #################################### 
  ## study definition 
  ## #################################### 
  ## generate dummy data for study_definition 

  dummy_data_vax:
    run: r:latest analysis/dummy_data_vax.R
    needs:
    - design
    outputs:
      moderately_sensitive:
        dummy_data: analysis/dummy_data_vax.feather

  ## study definition 

  generate_study_population:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_vax
      --output-format feather
    dummy_data_file: analysis/dummy_data_vax.feather
    needs:
    - design
    - dummy_data_vax
    outputs:
      highly_sensitive:
        cohort: output/input_vax.feather

  ## #################################### 
  ## preprocessing 
  ## #################################### 
  ## process data from study_definition 

  data_input_process:
    run: r:latest analysis/preprocess/data_input_process.R
    needs:
    - design
    - dummy_data_vax
    - generate_study_population
    outputs:
      highly_sensitive:
        data_wide_vax_dates: output/data/data_wide_vax_dates.rds
        data_processed: output/data/data_processed.rds
      moderately_sensitive:
        data_properties: output/tables/data_*_tabulate.txt

  ## apply eligiblity criteria from boxes a and b 

  data_eligible_ab:
    run: r:latest analysis/preprocess/data_eligible_ab.R
    needs:
    - design
    - data_input_process
    outputs:
      highly_sensitive:
        data_eligible_a: output/data/data_eligible_a.rds
        data_eligible_b: output/data/data_eligible_b.rds
      moderately_sensitive:
        eligibility_count_ab: output/tables/eligibility_count_ab.csv
        group_age_ranges: output/lib/group_age_ranges.csv

  ## #################################### 
  ## second_vax_period 
  ## #################################### 
  ## identify second vaccination time periods 
  ## create dataset for identifying second vaccination time periods 

  data_2nd_vax_dates:
    run: r:latest analysis/second_vax_period/data_2nd_vax_dates.R
    needs:
    - design
    - data_input_process
    - data_eligible_ab
    outputs:
      highly_sensitive:
        data_vax_plot: output/second_vax_period/data/data_vax_plot.rds
        second_vax_period_dates_rds: output/second_vax_period/data/second_vax_period_dates.rds
      moderately_sensitive:
        second_vax_period_dates_txt: output/second_vax_period/tables/second_vax_period_dates.txt

  ## plot second vaccination time periods 

  plot_2nd_vax_dates:
    run: r:latest analysis/second_vax_period/plot_2nd_vax_dates.R
    needs:
    - design
    - data_eligible_ab
    - data_2nd_vax_dates
    outputs:
      moderately_sensitive:
        plots_by_region: output/second_vax_period/images/plot_by_region_*.png

  ## apply eligiblity criteria from boxes c, d and e 

  data_eligible_cde:
    run: r:latest analysis/preprocess/data_eligible_cde.R
    needs:
    - design
    - data_input_process
    - data_eligible_ab
    - data_2nd_vax_dates
    outputs:
      highly_sensitive:
        data_eligible_e_vax: output/data/data_eligible_e_vax.rds
        data_eligible_e_unvax: output/data/data_eligible_e_unvax.rds
        data_eligible_e: output/data/data_eligible_e.csv
      moderately_sensitive:
        eligibility_count_cde: output/tables/eligibility_count_cde.csv

  ## #################################### 
  ## study definition ever and k 
  ## #################################### 
  ## study definition ever 

  generate_ever_data:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_ever
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_ever.feather

  ## study definition for period 1 

  generate_input_1:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_1
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_1.feather

  ## study definition for period 2 

  generate_input_2:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_2
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_2.feather

  ## study definition for period 3 

  generate_input_3:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_3
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_3.feather

  ## study definition for period 4 

  generate_input_4:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_4
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_4.feather

  ## study definition for period 5 

  generate_input_5:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_5
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_5.feather

  ## study definition for period 6 

  generate_input_6:
    run: cohortextractor:latest generate_cohort --study-definition study_definition_6
      --output-format feather
    needs:
    - design
    - data_eligible_cde
    outputs:
      highly_sensitive:
        cohort: output/input_6.feather

  ## #################################### 
  ## process covariates data 
  ## #################################### 
  ## (includes anytest_date) 

  data_covariates_process:
    run: r:latest analysis/preprocess/data_covariates_process.R
    needs:
    - design
    - data_input_process
    - data_eligible_cde
    - generate_ever_data
    - generate_input_1
    - generate_input_2
    - generate_input_3
    - generate_input_4
    - generate_input_5
    - generate_input_6
    outputs:
      highly_sensitive:
        data_covariates: output/data/data_covariates.rds

  ## min and max follow-up dates for plots 

  data_min_max_fu:
    run: r:latest analysis/comparisons/data_min_max_fu.R
    needs:
    - design
    - data_input_process
    - data_covariates_process
    outputs:
      highly_sensitive:
        data_min_max_fu: output/lib/data_min_max_fu.rds

  ## #################################### 
  ## subsequent vaccination 
  ## #################################### 
  ## plot cumulative incidence of subsequent vaccination 

  plot_cumulative_incidence:
    run: r:latest analysis/subsequent_vax/plot_cumulative_incidence.R
    needs:
    - design
    - data_input_process
    - data_eligible_cde
    outputs:
      moderately_sensitive:
        ci_vax: output/subsequent_vax/images/ci_vax_*.png
        survtable: output/subsequent_vax/tables/survtable_*.txt

  ## #################################### 
  ## table 1 for report 
  ## #################################### 
  ## create table 1 for all and for each subgroup 

  table1:
    run: r:latest analysis/report/table1.R
    needs:
    - design
    - data_input_process
    - data_eligible_cde
    - data_covariates_process
    outputs:
      moderately_sensitive:
        eligibility_count_p1: output/tables/eligibility_count_p1.csv
        table_csv: output/report/tables/table1_*_REDACTED.csv
        table_html: output/report/tables/table1_*_REDACTED.html

  ## #################################### 
  ## process time to event data 
  ## #################################### 
  ## process tte data 

  data_tte_process_BNT162b2:
    run: r:latest analysis/comparisons/data_tte_process.R BNT162b2
    needs:
    - design
    - data_input_process
    - data_covariates_process
    outputs:
      highly_sensitive:
        data_tte_brand_outcome: output/tte/data/data_tte_BNT162b2*.rds
      moderately_sensitive:
        event_counts: output/tte/tables/event_counts_BNT162b2.csv

  data_tte_process_ChAdOx:
    run: r:latest analysis/comparisons/data_tte_process.R ChAdOx
    needs:
    - design
    - data_input_process
    - data_covariates_process
    outputs:
      highly_sensitive:
        data_tte_brand_outcome: output/tte/data/data_tte_ChAdOx*.rds
      moderately_sensitive:
        event_counts: output/tte/tables/event_counts_ChAdOx.csv

  data_tte_process_both:
    run: r:latest analysis/comparisons/data_tte_process.R both
    needs:
    - design
    - data_input_process
    - data_covariates_process
    outputs:
      highly_sensitive:
        data_tte_brand_outcome: output/tte/data/data_tte_both*.rds
      moderately_sensitive:
        event_counts: output/tte/tables/event_counts_both.csv

Timeline

  • Created:

  • Started:

  • Finished:

  • Runtime: 00:18:33

These timestamps are generated and stored using the UTC timezone on the TPP backend.

Job request

Status
Succeeded
Backend
TPP
Workspace
covid-ve-change-over-time--manuscript
Requested by
Elsie Horne
Branch
main
Force run dependencies
No
Git commit hash
0e548c9
Requested actions
  • data_eligible_ab
  • data_eligible_cde

Code comparison

Compare the code used in this job request