diff --git a/prometheus.data-commons.org/metadata/aggregate_config.json b/prometheus.data-commons.org/metadata/aggregate_config.json index f5db0252a..0424200fd 100644 --- a/prometheus.data-commons.org/metadata/aggregate_config.json +++ b/prometheus.data-commons.org/metadata/aggregate_config.json @@ -77,7 +77,8 @@ "default": 0 }, "__manifest": "path:__manifest", - "commons_url": "data.bloodpac.org" + "commons_url": "data.bloodpac.org", + "is_synthetic": "Yes" } }, "VPODC-study-level-metadata": { @@ -104,7 +105,8 @@ "default": 0 }, "__manifest": "", - "commons_url": "vpodc.data-commons.org" + "commons_url": "vpodc.data-commons.org", + "is_synthetic": "No" } }, "APOLLO-study-level-metadata": { @@ -134,14 +136,15 @@ "study_description": "path:name", "full_name": "", "short_name": "", - "commons": "gdc", + "commons": "GDC", "study_url": "", "_subjects_count": { "path": "summary.case_count", "default": 0 }, "__manifest": "", - "commons_url": "api.gdc.cancer.gov" + "commons_url": "api.gdc.cancer.gov", + "is_synthetic": "No" } }, "Proteomic-Data-Commons-study-level-metadata": { @@ -152,7 +155,7 @@ "keep_original_fields": false, "field_mappings": { "authz": "/VA", - "commons": "pdc", + "commons": "PDC", "tags": [ { "name": "path:disease_type", @@ -189,7 +192,8 @@ "supplementaryFilesCount": "path:supplementaryFilesCount", "nonSupplementaryFilesCount": "path:nonSupplementaryFilesCount", "contacts": "path:contacts", - "versions": "path:versions" + "versions": "path:versions", + "is_synthetic": "No" } }, "BloodPAC-subject-level-metadata": { @@ -213,11 +217,26 @@ "subject_ethnicity": "path:ethnicity", "subject_metastasis": "path:metastasis", "subject_cancer_type": "path:cancer_type", - "subject_cancer_grade": "path:cancer_grade", + "subject_cancer_grade": { + "path": "cancer_grade", + "filters": [ + "normalize_value" + ], + "filterParams": { + "normalize_value": { + "Grade 1": "Grade I", + "Grade 2": "Grade II", + "Grade 3": "Grade III", + "Grade 4": "Grade IV" + } + }, + "default": "" + }, "subject_cancer_stage": "path:cancer_stage", "subject_year_of_birth": "path:year_of_birth", "subject_primary_disease": "path:primary_disease", - "commons_url": "data.bloodpac.org" + "commons_url": "data.bloodpac.org", + "is_synthetic": "Yes" } }, "VPODC-subject-level-metadata": { @@ -234,7 +253,7 @@ "tags": { "path": "tags", "filters": [ - "normalize_tags" + "normalize_tags" ], "filterParams": { "normalize_tags": { @@ -284,14 +303,14 @@ ], "filterParams": { "normalize_value": { - "M": "Male", - "F": "Female", - "male": "Male", - "female": "Female", - "not reported": "Not Reported" + "M": "Male", + "F": "Female", + "male": "Male", + "female": "Female", + "not reported": "Not Reported" } }, - "default": "" + "default": "" }, "subject_ethnicity": { "path": "ethnicity", @@ -300,10 +319,10 @@ ], "filterParams": { "normalize_value": { - "NOT HISPANIC OR LATINO": "Not Hispanic or Latino", - "not reported": "Not Reported", - "DECLINED TO ANSWER": "Declined to Answer", - "HISPANIC OR LATINO": "Hispanic or Latino" + "NOT HISPANIC OR LATINO": "Not Hispanic or Latino", + "not reported": "Not Reported", + "DECLINED TO ANSWER": "Declined to Answer", + "HISPANIC OR LATINO": "Hispanic or Latino" } }, "default": "" @@ -323,14 +342,14 @@ ], "filterParams": { "normalize_value": { - "Grade 1": "Grade I", - "G1": "Grade I", - "Grade 2": "Grade II", - "G2": "Grade II", - "Grade 3": "Grade III", - "G3": "Grade III", - "Grade 4": "Grade IV", - "G4": "Grade IV" + "Grade 1": "Grade I", + "G1": "Grade I", + "Grade 2": "Grade II", + "G2": "Grade II", + "Grade 3": "Grade III", + "G3": "Grade III", + "Grade 4": "Grade IV", + "G4": "Grade IV" } }, "default": "" @@ -347,7 +366,8 @@ "path": "primary_disease", "default": "" }, - "commons_url": "vpodc.data-commons.org" + "commons_url": "vpodc.data-commons.org", + "is_synthetic": "No" } }, "APOLLO-subject-level-metadata": { @@ -403,16 +423,16 @@ } ], "_unique_id": "path:id", - "commons": "gdc", + "commons": "GDC", "disease_type": "path:disease_type", "primary_site": "path:primary_site", "subject_id": "path:submitter_id", - "subject_apollo_id": "", + "subject_apollo_id": "path:submitter_id", "subject_race": "path:demographic.race", "subject_gender": { "path": "demographic.gender", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -428,7 +448,7 @@ "subject_ethnicity": { "path": "demographic.ethnicity", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -445,7 +465,7 @@ "subject_cancer_grade": { "path": "diagnoses[*].tumor_grade", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -465,7 +485,8 @@ "subject_year_of_birth": "", "subject_primary_disease": "path:diagnoses[*].primary_diagnosis", "subject_type_of_exposure": "path:exposures[*].tobacco_smoking_status", - "commons_url": "api.gdc.cancer.gov" + "commons_url": "api.gdc.cancer.gov", + "is_synthetic": "No" } }, "Proteomic-Data-Commons-subject-level-metadata": { @@ -487,7 +508,7 @@ } ], "_unique_id": "path:case_submitter_id", - "commons": "pdc", + "commons": "GDC", "disease_type": "path:disease_type", "primary_site": "path:primary_site", "subject_id": "path:case_submitter_id", @@ -496,7 +517,7 @@ "subject_gender": { "path": "demographic.gender", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -512,7 +533,7 @@ "subject_ethnicity": { "path": "demographic.ethnicity", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -529,7 +550,7 @@ "subject_cancer_grade": { "path": "diagnoses[*].tumor_grade", "filters": [ - "normalize_value" + "normalize_value" ], "filterParams": { "normalize_value": { @@ -549,7 +570,186 @@ "subject_year_of_birth": "", "subject_primary_disease": "path:primary_diagnosis", "subject_type_of_exposure": "path:exposures[*].exposure_type", - "commons_url": "proteomic.datacommons.cancer.gov" + "commons_url": "proteomic.datacommons.cancer.gov", + "is_synthetic": "No" + } + }, + "VMOAT-study-level-metadata": { + "mds_url": "https://externalgen3.prometheus.data-commons.org/", + "commons_url": "externalgen3.prometheus.data-commons.org", + "adapter": "gen3", + "config": { + "guid_type": "VMOAT_promethueus_study_metadata", + "study_field": "gen3_discovery" + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "path:authz", + "tags": "path:tags", + "_unique_id": "path:_unique_id", + "study_id": "path:study_id", + "study_description": "path:study_description", + "full_name": "path:full_name", + "short_name": "path:short_name", + "commons": "path:commons", + "study_url": "path:study_url", + "data_source" : "path:data_source", + "_subjects_count": { + "path": "_subjects_count", + "default": 0 + }, + "__manifest": "path:__manifest", + "commons_url": "externalgen3.prometheus.data-commons.org", + "is_synthetic": "Yes" + } + }, + "VMOAT-subject-level-metadata": { + "mds_url": "https://externalgen3.prometheus.data-commons.org/", + "commons_url": "externalgen3.prometheus.data-commons.org", + "adapter": "gen3", + "config": { + "guid_type": "VMOAT_promethueus_study_metadata", + "study_field": "gen3_discovery" + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "path:authz", + "tags": "path:tags", + "_unique_id": "path:_unique_id", + "commons": "path:commons", + "subject_id": "path:_unique_id", + "subject_apollo_id": "path:apollo_id", + "subject_type_of_exposure": "path:exposure_type", + "subject_chemical_agents_of_exposure": "path:exposure_agent", + "data_source" : "path:data_source", + "commons_url": "externalgen3.prometheus.data-commons.org", + "is_synthetic": "Yes" + } + }, + "Metabolomic-study-level-metadata": { + "mds_url": "https://externalgen3.prometheus.data-commons.org/", + "commons_url": "externalgen3.prometheus.data-commons.org", + "adapter": "gen3", + "config": { + "guid_type": "Metabolomic_promethueus_study_metadata", + "study_field": "gen3_discovery" + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "path:authz", + "tags": "path:tags", + "_unique_id": "path:_unique_id", + "study_id": "path:study_id", + "study_description": "path:study_description", + "full_name": "path:full_name", + "short_name": "path:short_name", + "commons": "path:commons", + "study_url": "path:study_url", + "data_source" : "path:data_source", + "_subjects_count": { + "path": "_subjects_count", + "default": 0 + }, + "__manifest": "path:__manifest", + "commons_url": "externalgen3.prometheus.data-commons.org", + "is_synthetic": "Yes" + } + }, + "Metabolomic-subject-level-metadata": { + "mds_url": "https://externalgen3.prometheus.data-commons.org/", + "commons_url": "externalgen3.prometheus.data-commons.org", + "adapter": "gen3", + "config": { + "guid_type": "Metabolomic_promethueus_subject_metadata", + "study_field": "gen3_discovery" + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "path:authz", + "tags": "path:tags", + "_unique_id": "path:_unique_id", + "commons": "path:commons", + "subject_id": "path:subject_id", + "subject_apollo_id": "path:apollo_id", + "subject_race": "", + "subject_gender": "path:gender", + "subject_ethnicity": "", + "subject_metastasis": "", + "subject_cancer_type": "", + "subject_cancer_grade": "", + "subject_cancer_stage": "", + "subject_year_of_birth": "path:year_of_birth", + "subject_primary_disease": "", + "data_source" : "path:data_source", + "commons_url": "externalgen3.prometheus.data-commons.org", + "is_synthetic": "Yes" + } + }, + "TCIA-study-level-metadata": { + "mds_url": "https://services.cancerimagingarchive.net/nbia-api/services/v1/getPatientStudy?Collection=VAREPOP-APOLLO", + "commons_url": "services.cancerimagingarchive.net", + "adapter": "tcia", + "filters": { + "size": 100 + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "", + "tags": [ + { + "name": "TCIA", + "category": "Data Source" + } + ], + "_unique_id": "path:StudyInstanceUID", + "study_id": "path:StudyInstanceUID", + "study_description": "path:StudyDescription", + "full_name": "", + "short_name": "", + "commons": "", + "study_url": "", + "data_source" : "TCIA", + "_subjects_count": { + "path": "path:SeriesCount", + "default": 0 + }, + "__manifest": "", + "commons_url": "services.cancerimagingarchive.net", + "is_synthetic": "No" + } + }, + "TCIA-subject-level-metadata": { + "mds_url": "https://services.cancerimagingarchive.net/nbia-api/services/v1/getSeries?Collection=VAREPOP-APOLLO", + "commons_url": "services.cancerimagingarchive.net", + "adapter": "tcia", + "filters": { + "size": 100 + }, + "keep_original_fields": false, + "field_mappings": { + "authz": "", + "tags": [ + { + "name": "TCIA", + "category": "Data Source" + } + ], + "_unique_id": "path:SeriesInstanceUID", + "commons": "", + "subject_id": "path:SeriesInstanceUID", + "subject_apollo_id": "path:PatientID", + "subject_race": "", + "subject_gender": "", + "subject_ethnicity": "", + "subject_metastasis": "", + "subject_cancer_type": "", + "subject_cancer_grade": "", + "subject_cancer_stage": "", + "subject_year_of_birth": "", + "subject_primary_disease": "path:SeriesDescription", + "data_source" : "TCIA", + "commons_url": "services.cancerimagingarchive.net", + "is_synthetic": "No" } } }