Testing : new alias creation jenkins_subject_alias_new

jenkins-dcp.planx-pla.net/etlMapping.yaml

@@ -6,115 +6,74 @@ mappings:
     props:
       - name: submitter_id
       - name: project_id
-      - name: consent_codes
-      - name: geographic_site
-    flatten_props:
-      - path: demographics
-        props:
-          - 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: blood_pressure_test
-        props:
-          - name: bp_systolic
-          - name: bp_diastolic
-        sorted_by: updated_datetime, desc
-      - 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
+      - name: sex
+      - name: age_value
+      - name: ancestry
+      - name: disease_description
+      - name: phenotype_present
+      - name: phenotype_absent
+      - name: disease_id
+      - name: solve_state
+      - name: congenital_status
+      - name: age_of_onset
+      - name: phenotype_group
+      - name: anvil_project_id
+#    flatten_props:
     aggregated_props:
-      - name: annotated_sex
-        path: demographics
-        src: annotated_sex
+      - name: sample_provider
+        path: samples
+        src: sample_provider
+        fn: set
+      - name: tissue_affected_status
+        path: samples
+        src: tissue_affected_status
+        fn: set
+      - name: tissue_type
+        path: samples
+        src: tissue_type
+        fn: set
+      - name: sample_type
+        path: samples
+        src: sample_type
+        fn: set
+      - name: original_material_type
+        path: samples
+        src: original_material_type
+        fn: set
+      - name: exome_capture_platform
+        path: samples.sequencings
+        src: exome_capture_platform
+        fn: set
+      - name: library_prep_kit_method
+        path: samples.sequencings
+        src: library_prep_kit_method
+        fn: set
+      - name: capture_region_bed_file
+        path: samples.sequencings
+        src: capture_region_bed_file
         fn: set
-      - name: race
-        path: demographics
-        src: race
+      - name: reference_genome_build
+        path: samples.sequencings
+        src: reference_genome_build
         fn: set
-      - name: ethnicity
-        path: demographics
-        src: ethnicity
+      - name: sequencing_assay
+        path: samples.sequencings
+        src: sequencing_assay
+        fn: set
+      - name: alignment_method
+        path: samples.sequencings
+        src: alignment_method
+        fn: set
+      - name: data_processing_pipeline
+        path: samples.sequencings
+        src: data_processing_pipeline
         fn: set
       - name: _samples_count
         path: samples
         fn: count
-      - name: _aliquots_count
-        path: samples.aliquots
-        fn: count
-      - name: _read_groups_count
-        path: samples.aliquots.read_groups
-        fn: count
-      - name: _submitted_unaligned_reads_files_count
-        path: samples.aliquots.read_groups.submitted_unaligned_reads_files
-        fn: count
-      - name: _submitted_aligned_reads_files_count
-        path: samples.aliquots.read_groups.submitted_aligned_reads_files
+      - name: _sequencings_count
+        path: samples.sequencings
         fn: count
-      - 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
@@ -125,35 +84,80 @@ mappings:
           - name: data_type
             src: data_type
             fn: set
+          - name: data_category
+            src: data_category
+            fn: set
           - name: file_count
             src: _file_id
             fn: count
+    parent_props:
+      - path: projects[project_code:code]
+      - path: projects[project_name:name]
+      - path: projects[project_dbgap_phs:dbgap_phs]
+      - path: projects[project_dbgap_consent_text:dbgap_consent_text]
+      - path: projects[project_short_name:short_name]
+      - path: projects[project_dbgap_accession_number:dbgap_accession_number]
   - name: jenkins-dcp.planx-pla.net_file
     doc_type: file
     type: collector
     root: None
     category: data_file
     props:
+      - name: project_id
+      - name: submitter_id
       - 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: data_category
+      - name: analyte_type
+      - name: sequencing_assay
       - name: source_node
     injecting_props:
       subject:
         props:
           - name: _subject_id
             src: id
             fn: set
-          - name: project_id
-      program:
-        props:
-          - name: programs_name
-            src: name
+          - name: subject_submitter_id
+            src: submitter_id
+            fn: set
+          - name: anvil_project_id
+            src: anvil_project_id
+            fn: set
+          - name: sex
+            src: sex
+            fn: set
+          - name: age_value
+            src: age_value
+            fn: set
+          - name: ancestry
+            src: ancestry
+            fn: set
+          - name: disease_description
+            src: disease_description
+            fn: set
+          - name: phenotype_present
+            src: phenotype_present
+            fn: set
+          - name: phenotype_absent
+            src: phenotype_absent
+            fn: set
+          - name: disease_id
+            src: disease_id
+            fn: set
+          - name: solve_state
+            src: solve_state
+            fn: set
+          - name: congenital_status
+            src: congenital_status
+            fn: set
+          - name: age_of_onset
+            src: age_of_onset
             fn: set
+          - name: phenotype_group
+            src: phenotype_group
+            fn: set

jenkins-dcp.planx-pla.net/manifest.json

@@ -270,7 +270,7 @@
     "environment": "qaplanetv1",
     "hostname": "jenkins-dcp.planx-pla.net",
     "revproxy_arn": "arn:aws:acm:us-east-1:707767160287:certificate/c676c81c-9546-4e9a-9a72-725dd3912bc8",
-    "dictionary_url": "https://s3.amazonaws.com/dictionary-artifacts/gtexdictionary/master/schema.json",
+    "dictionary_url": "https://s3.amazonaws.com/dictionary-artifacts/anvil/master/schema.json",
     "portal_app": "gitops",
     "kube_bucket": "kube-qaplanetv1-gen3",
     "logs_bucket": "logs-qaplanetv1-gen3",
@@ -291,7 +291,7 @@
   "guppy": {
     "indices": [
       {
-        "index": "jenkins_subject_alias",
+        "index": "jenkins_subject_new_alias",
         "type": "subject"
       },
       {