Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Nightly Build from 01-08-2025 #8232

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Nightly Build from 01-08-2025 #8232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
171 changes: 136 additions & 35 deletions nightly.planx-pla.net/etlMapping.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,54 +1,155 @@
mappings:
- name: bloodpac
doc_type: case
- name: gen3.biodatacatalyst.nhlbi.nih.gov_subject
doc_type: subject
type: aggregator
root: case
root: subject
props:
- name: submitter_id
- name: project_id
- name: consent_codes
- name: geographic_site
flatten_props:
- path: demographics
props:
- name: gender
- name: race
- name: ethnicity
- name: age_at_index
- name: hispanic_subgroup
- name: subcohort
- name: weight_baseline
- name: bmi_baseline
- name: height_baseline
- path: medical_histories
props:
- name: diabetes
- name: hypertension
- name: cerebrovascular_disease
- name: chronic_respiratory_disease
- name: coronary_artery_disease
- name: asthma
- name: cabg_presence
- name: copd
- name: emphysema
- name: heart_failure
- name: myocardial_infarction
- name: stroke
- name: cac_score
- name: cac_volume
- name: carotid_plaque
- name: carotid_stenosis
- name: cimt_1
- name: cimt_2
- name: vte_case_status
- name: vte_followup_start_age
- name: vte_prior_history

- path: medication_records
props:
- name: hypertension_meds
- name: antihypertensive_meds
- name: fasting_lipids
- name: lipid_lowering_medication
- path: lab_results
props:
- name: lymphocyte_ncnc_bld
- name: mch_entmass_rbc
- name: mcv_entvol_rbc
- name: mchc_mcnc_rbc
- name: monocyte_ncnc_bld
- name: neutrophil_ncnc_bld
- name: pmv_entvol_bld
- name: rbc_ncnc_bld
- name: rdw_ratio_rbc
- name: hemoglobin_mcnc_bld
- name: platelet_ncnc_bld
- name: hematocrit_vfr_bld
- name: wbc_ncnc_bld
- name: basophil_ncnc_bld
- name: eosinophil_ncnc_bld
- name: unit_triglycerides
- name: hdl
- name: ldl
- name: triglycerides
- name: total_cholesterol
aggregated_props:
- name: _biospecimens_count
path: biospecimens
fn: count
- name: annotated_sex
path: demographics
src: annotated_sex
fn: set
- name: race
path: demographics
src: race
fn: set
- name: ethnicity
path: demographics
src: ethnicity
fn: set
- name: _samples_count
path: biospecimens.samples
path: samples
fn: count
- name: _aliquots_count
path: biospecimens.samples.aliquots
fn: count
- name: _analytes_count
path: biospecimens.samples.aliquots.analytes
fn: count
- name: _cell_images_count
path: biospecimens.samples.aliquots.analytes.cell_images
fn: count
- name: _mass_cytometry_assays_count
path: biospecimens.samples.aliquots.analytes.mass_cytometry_assays
fn: count
- name: _mass_cytometry_images_count
path: biospecimens.samples.aliquots.analytes.mass_cytometry_assays.mass_cytometry_images
path: samples.aliquots
fn: count
- name: _read_groups_count
path: biospecimens.samples.aliquots.analytes.read_groups
path: samples.aliquots.read_groups
fn: count
- name: _slide_images_count
path: biospecimens.samples.aliquots.slide_images
- name: _submitted_unaligned_reads_files_count
path: samples.aliquots.read_groups.submitted_unaligned_reads_files
fn: count
- name: _submitted_aligned_reads_files_count
path: biospecimens.samples.aliquots.analytes.read_groups.submitted_aligned_reads_files
fn: count
- name: _submitted_methylations_count
path: biospecimens.samples.aliquots.analytes.submitted_methylation_files
path: samples.aliquots.read_groups.submitted_aligned_reads_files
fn: count
- name: _submitted_somatic_mutations_count
path: biospecimens.samples.aliquots.analytes.read_groups.submitted_somatic_mutations
fn: count
- name: _submitted_unaligned_reads_files_count
path: biospecimens.samples.aliquots.analytes.read_groups.submitted_unaligned_reads_files
- name: _simple_germline_variations_count
path: samples.aliquots.read_groups.simple_germline_variations
fn: count
- name: current_smoker_baseline
path: exposures
src: current_smoker_baseline
fn: set
- name: ever_smoker_baseline
path: exposures
src: ever_smoker_baseline
fn: set
parent_props:
- path: studies[studies_submitter_id:submitter_id].projects[code]
- path: studies[studies_submitter_id:submitter_id].projects[code].programs[programs_name:name]
joining_props:
- index: file
join_on: _subject_id
props:
- name: data_format
src: data_format
fn: set
- name: data_type
src: data_type
fn: set
- name: file_count
src: _file_id
fn: count
- name: gen3.biodatacatalyst.nhlbi.nih.gov_file
doc_type: file
type: collector
root: None
category: data_file
props:
- name: object_id
- name: md5sum
- name: file_name
- name: file_size
- name: data_category
- name: data_format
- name: data_type
- name: state
- name: callset
- name: bucket_path
- name: source_node
injecting_props:
subject:
props:
- name: _subject_id
src: id
fn: set
- name: project_id
program:
props:
- name: programs_name
src: name
fn: set
Loading
Loading