diff --git a/.sqlfluff b/.sqlfluff index 995d6dc..7b88f5a 100644 --- a/.sqlfluff +++ b/.sqlfluff @@ -10,7 +10,7 @@ project_dir = dbt_project target = dev # If needed, uncomment the line below to specify the directory where your # profiles.yml file is located -profiles_dir = ~/.dbt/include +profiles_dir = ~/.dbt/ [sqlfluff:indentation] tab_space_size = 2 diff --git a/dags/kids_first/kf_sd_1nns3k8v.py b/dags/kids_first/kf_sd_1nns3k8v.py new file mode 100644 index 0000000..4d86a13 --- /dev/null +++ b/dags/kids_first/kf_sd_1nns3k8v.py @@ -0,0 +1,36 @@ +from airflow.sdk import Variable + +from cosmos import ( + DbtDag, + ProjectConfig, + ProfileConfig, + ExecutionConfig, + RenderConfig, +) +from cosmos.profiles import PostgresUserPasswordProfileMapping + +profile_config = ProfileConfig( + # make sure target_name and profile_mapping align + profile_name=Variable.get("DBT_PROFILE_NAME"), + target_name="prd", + profile_mapping=PostgresUserPasswordProfileMapping( + conn_id="postgres_prd_svc", + profile_args={"schema": "prd"}, + ), +) + +example_study_dag = DbtDag( + project_config=ProjectConfig( + Variable.get("DBT_PROJECT_DIR"), + install_dbt_deps=True, + ), + profile_config=profile_config, + execution_config=ExecutionConfig( + dbt_executable_path=Variable.get("DBT_EXECUTABLE_PATH"), + ), + render_config=RenderConfig(select=["config.meta.study:kf_sd_1nns3k8v"]), + # normal dag parameters + schedule="@daily", + dag_id="kf_sd_1nns3k8v_dbt_dag", + tags=["POC", "Kids First"], +) \ No newline at end of file diff --git a/dbt_project/models/_metadata_description_files/docs_fields.md b/dbt_project/models/_metadata_description_files/docs_fields.md index 06b7cba..a5cd9aa 100644 --- a/dbt_project/models/_metadata_description_files/docs_fields.md +++ b/dbt_project/models/_metadata_description_files/docs_fields.md @@ -598,5 +598,104 @@ Link to request specimens from study biobank. {% enddocs %} +## Kids First Source Data Fields +### Clinical Data +{% docs family_relationship_target_participant_id %} +Participant ID of Proband of Family +{% enddocs %} + +{% docs aliquot_id %} +Aliquot ID from sequencing manifest +{% enddocs %} + +{% docs consent_group %} +Consent group of study +{% enddocs %} + +{% docs age_at_sample %} +Age sample was collected from sequencing manifest +{% enddocs %} + +{% docs sample_composition %} +Composition of specimen +{% enddocs %} + +{% docs sample_tissue_type %} +Tissue type of collected specimen +{% enddocs %} + +{% docs sex %} +Sex of pariticipant +{% enddocs %} + +{% docs age_at_phenotype %} +Age of participant when phenotype was asserted +{% enddocs %} + +{% docs vital_status %} +Vital status of participant +{% enddocs %} + + +### Broad Manifest + +{% docs collaborator_sample_id %} +Sample ID submitted by PI to sequencing center +{% enddocs %} + +{% docs collaborator_participant_id %} +Participant ID submitted by PI to sequencing center +{% enddocs %} + +{% docs cram_path %} +path of cram file from sequencing manifest +{% enddocs %} + +{% docs crai_path %} +path of crai file from sequencing manifest +{% enddocs %} + +{% docs md5_path %} +path of md5 file from sequencing manifest +{% enddocs %} + +{% docs root_sample_id %} +Specimen sample ID from sequencing manifest +{% enddocs %} + +### S3 Scrape + +{% docs mean_coverage %} +mean coverage value from sequencing manifest +{% enddocs %} + +{% docs bucket %} +s3 bucket for file +{% enddocs %} + +{% docs key %} +s3 key for file +{% enddocs %} + +{% docs last_modified %} +last time s3 file was modified +{% enddocs %} + +{% docs etag %} +etag hash from s3 manifest +{% enddocs %} + +{% docs size %} +size of file from s3 manifest +{% enddocs %} + +{% docs storage_class %} +s3 storage class for file +{% enddocs %} + + +## Study Specific Fields + +# SD_1NNS3K8V Fields \ No newline at end of file diff --git a/dbt_project/models/_metadata_description_files/docs_tables.md b/dbt_project/models/_metadata_description_files/docs_tables.md index 5d03390..d254b48 100644 --- a/dbt_project/models/_metadata_description_files/docs_tables.md +++ b/dbt_project/models/_metadata_description_files/docs_tables.md @@ -136,4 +136,30 @@ Stable table for int_specimens. Finalized mapping of transformed dataservice ent {% docs stable_study %} Stable table for int_study. Finalized mapping of transformed dataservice entities that are ready to be brought into the access layer. +{% enddocs %} + + +## Kids First Study SD_1NNS3K8V +{% docs kf_sd_1nns3k8v_src_clinical %} +Source table for Cody study source clinical data +{% enddocs %} + +{% docs kf_sd_1nns3k8v_src_sequencing %} +Source table for Cody study source sequencing data +{% enddocs %} + +{% docs kf_sd_1nns3k8v_src_s3 %} +Source table for Cody study s3 file manifest +{% enddocs %} + +{% docs kf_sd_1nns3k8v_int_clinical %} +Intermediate table for src_clinical. Transforms dataservice entities for better usability and clarity. Excludes certain entites that are not needed. +{% enddocs %} + +{% docs kf_sd_1nns3k8v_int_sequencing %} +Intermediate table for src_sequencing. Transforms dataservice entities for better usability and clarity. Excludes certain entites that are not needed. +{% enddocs %} + +{% docs kf_sd_1nns3k8v_int_s3 %} +Intermediate table for src_s3. Transforms dataservice entities for better usability and clarity. Excludes certain entites that are not needed. {% enddocs %} \ No newline at end of file diff --git a/dbt_project/models/kids_first/example_study/my_first_dbt_model.sql b/dbt_project/models/kids_first/example_study/my_first_dbt_model.sql index 5b51873..279006b 100644 --- a/dbt_project/models/kids_first/example_study/my_first_dbt_model.sql +++ b/dbt_project/models/kids_first/example_study/my_first_dbt_model.sql @@ -1,4 +1,3 @@ - /* Welcome to your first dbt model! Did you know that you can also configure models directly within SQL files? @@ -11,9 +10,9 @@ with source_data as ( - select 1 as id - union all - select null as id + select 1 as id + union all + select null as id ) diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int.yml b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int.yml new file mode 100644 index 0000000..ec4f3ea --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int.yml @@ -0,0 +1,87 @@ +version: 2 + +models: + +- name: kf_sd_1nns3k8v_int_clinical + description: '{{ doc("kf_sd_1nns3k8v_int_clinical") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: family_id + description: '{{ doc("family_id") }}' + - name: participant_id + description: '{{ doc("participant_id") }}' + - name: family_relationship_target_participant_id + description: '{{ doc("family_relationship_target_participant_id") }}' + - name: aliquot_id + description: '{{ doc("aliquot_id") }}' + - name: consent_group + description: '{{ doc("consent_group") }}' + - name: age_at_sample + description: '{{ doc("age_at_sample") }}' + - name: sample_composition + description: '{{ doc("sample_composition") }}' + - name: sample_tissue_type + description: '{{ doc("sample_tissue_type") }}' + - name: race + description: '{{ doc("race") }}' + - name: sex + description: '{{ doc("sex") }}' + - name: ethnicity + description: '{{ doc("ethnicity") }}' + - name: analyte_type + description: '{{ doc("analyte_type") }}' + - name: age_at_phenotype + description: '{{ doc("age_at_phenotype") }}' + - name: affected_status + description: '{{ doc("affected_status") }}' + - name: vital_status + description: '{{ doc("vital_status") }}' + +- name: kf_sd_1nns3k8v_int_sequencing + description: '{{ doc("kf_sd_1nns3k8v_int_sequencing") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: sample_id + description: '{{ doc("sample_id") }}' + - name: collaborator_sample_id + description: '{{ doc("collaborator_sample_id") }}' + - name: collaborator_participant_id + description: '{{ doc("collaborator_participant_id") }}' + - name: cram_path + description: '{{ doc("cram_path") }}' + - name: crai_path + description: '{{ doc("crai_path") }}' + - name: md5_path + description: '{{ doc("md5_path") }}' + - name: root_sample_id + description: '{{ doc("root_sample_id") }}' + - name: mean_coverage + description: '{{ doc("mean_coverage") }}' + - name: total_reads + description: '{{ doc("total_reads") }}' + - name: mean_read_length + description: '{{ doc("mean_read_length") }}' + + +- name: kf_sd_1nns3k8v_int_s3 + description: '{{ doc("kf_sd_1nns3k8v_int_s3") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: bucket + description: '{{ doc("bucket") }}' + - name: key + description: '{{ doc("key") }}' + - name: last_modified + description: '{{ doc("last_modified") }}' + - name: etag + description: '{{ doc("etag") }}' + - name: size + description: '{{ doc("size") }}' + - name: storage_class + description: '{{ doc("storage_class") }}' \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_clinical.sql b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_clinical.sql new file mode 100644 index 0000000..404613a --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_clinical.sql @@ -0,0 +1,21 @@ +{{ config( + schema='int' +) }} + +select distinct + "Family ID" as family_id, + "Participant ID" as participant_id, + "Family Relationship Target Participant ID" as family_relationship_target_participant_id, + alliquot_id as aliquot_id, + "Consent Group" as consent_group, + "Age at Sample" as age_at_sample, + "Sample Composition" as sample_composition, + "Sample Tissue Type" as sample_tissue_type, + "Race" as race, + "Sex" as sex, + "Ethnicity" as ethnicity, + "Analyte Type" as analyte_type, + "Age at Phenotype" as age_at_phenotype, + "Affected Status" as affected_status, + "Vital Status" as vital_status +from {{ ref('kf_sd_1nns3k8v_src_clinical') }} \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_s3.sql b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_s3.sql new file mode 100644 index 0000000..bb15b5e --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_s3.sql @@ -0,0 +1,12 @@ +{{ config( + schema='int' +) }} + +select distinct + "Bucket" as bucket, + "Key" as key, + "LastModified" as last_modified, + "ETag" as etag, + "Size" as size, + "StorageClass" as storage_class +from {{ ref('s3_scrape_cody') }} \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_sequencing.sql b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_sequencing.sql new file mode 100644 index 0000000..8ae9f7a --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/int/kf_sd_1nns3k8v_int_sequencing.sql @@ -0,0 +1,34 @@ +{{ config( + schema='int' +) }} + +select distinct + "entity:sample_id" as sample_id, + -- "project" as project, + collaborator_sample_id, + -- "version" as version, + -- "data_type" as data_type, + -- "pdo" as pdo, + -- "release_date" as release_date, + -- "reference_sequence_name" as reference_sequence_name, + collaborator_participant_id, + cram_path, + crai_path, + md5_path, + root_sample_id, + mean_coverage, + -- "adapter_rate" as adapter_rate, + -- "pf_hq_aligned_q20_bases" as pf_hq_aligned_q20_bases, + -- "pf_hq_aligned_reads" as pf_hq_aligned_reads, + -- "pf_mismatch_rate" as pf_mismatch_rate, + -- "pf_noise_reads" as pf_noise_reads, + -- "pf_reads" as pf_reads, + -- "pf_reads_aligned" as pf_reads_aligned, + total_reads, + mean_read_length +-- "pf_reads_rate" as pf_reads_rate, +-- "pf_reads_aligned_rate" as pf_reads_aligned_rate, +-- "pf_aligned_bases" as pf_aligned_bases, +-- "reads_aligned_in_pairs" as reads_aligned_in_pairs, + +from {{ ref('kf_sd_1nns3k8v_src_sequencing') }} \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src.yml b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src.yml new file mode 100644 index 0000000..3daf953 --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src.yml @@ -0,0 +1,97 @@ +version: 2 + +sources: + - name: kf_sd_1nns3k8v_src + database: includewarehouse + schema: prd_import + tables: + - name: kids_first_update + - name: sample + - name: s3_scrape_cody + + +models: + +- name: kf_sd_1nns3k8v_src_clinical + description: '{{ doc("kf_sd_1nns3k8v_src_clinical") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: "family_id" + description: '{{ doc("family_id") }}' + - name: participant_id + description: '{{ doc("participant_id") }}' + - name: family_relationship_target_participant_id + description: '{{ doc("family_relationship_target_participant_id") }}' + - name: aliquot_id + description: '{{ doc("aliquot_id") }}' + - name: consent_group + description: '{{ doc("consent_group") }}' + - name: age_at_sample + description: '{{ doc("age_at_sample") }}' + - name: sample_composition + description: '{{ doc("sample_composition") }}' + - name: sample_tissue_type + description: '{{ doc("sample_tissue_type") }}' + - name: race + description: '{{ doc("race") }}' + - name: sex + description: '{{ doc("sex") }}' + - name: ethnicity + description: '{{ doc("ethnicity") }}' + - name: analyte_type + description: '{{ doc("analyte_type") }}' + - name: age_at_phenotype + description: '{{ doc("age_at_phenotype") }}' + - name: affected_status + description: '{{ doc("affected_status") }}' + - name: vital_status + description: '{{ doc("vital_status") }}' + +- name: kf_sd_1nns3k8v_src_sequencing + description: '{{ doc("kf_sd_1nns3k8v_src_sequencing") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: sample_id + description: '{{ doc("sample_id") }}' + - name: collaborator_sample_id + description: '{{ doc("collaborator_sample_id") }}' + - name: collaborator_participant_id + description: '{{ doc("collaborator_participant_id") }}' + - name: cram_path + description: '{{ doc("cram_path") }}' + - name: crai_path + description: '{{ doc("crai_path") }}' + - name: md5_path + description: '{{ doc("md5_path") }}' + - name: root_sample_id + description: '{{ doc("root_sample_id") }}' + - name: mean_coverage + description: '{{ doc("mean_coverage") }}' + - name: total_reads + description: '{{ doc("total_reads") }}' + - name: mean_read_length + description: '{{ doc("mean_read_length") }}' + + +- name: kf_sd_1nns3k8v_src_s3 + description: '{{ doc("kf_sd_1nns3k8v_src_s3") }}' + config: + meta: + study: kf_sd_1nns3k8v + columns: + - name: bucket + description: '{{ doc("bucket") }}' + - name: key + description: '{{ doc("key") }}' + - name: last_modified + description: '{{ doc("last_modified") }}' + - name: etag + description: '{{ doc("etag") }}' + - name: size + description: '{{ doc("size") }}' + - name: storage_class + description: '{{ doc("storage_class") }}' \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_clinical.sql b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_clinical.sql new file mode 100644 index 0000000..83f5178 --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_clinical.sql @@ -0,0 +1,6 @@ +{{ config( + schema='src' +) }} + +select * +from {{ source('kf_sd_1nns3k8v_src', 'kids_first_update') }} \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_s3.sql b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_s3.sql new file mode 100644 index 0000000..d05fff0 --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_s3.sql @@ -0,0 +1,6 @@ +{{ config( + schema='src' +) }} + +select * +from {{ source('kf_sd_1nns3k8v_src', 's3_scrape_cody') }} \ No newline at end of file diff --git a/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_sequencing.sql b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_sequencing.sql new file mode 100644 index 0000000..12ecfce --- /dev/null +++ b/dbt_project/models/kids_first/sd_1nns3k8v/src/kf_sd_1nns3k8v_src_sequencing.sql @@ -0,0 +1,6 @@ +{{ config( + schema='src' +) }} + +select * +from {{ source('kf_sd_1nns3k8v_src', 'sample') }} \ No newline at end of file diff --git a/dbt_project/profiles.yml b/dbt_project/profiles.yml index 6269949..5388117 100644 --- a/dbt_project/profiles.yml +++ b/dbt_project/profiles.yml @@ -26,7 +26,7 @@ include_dbt_sandbox: user: "{{ env_var('INCLUDEWAREHOUSE_SCV_USERNAME') }}" password: "{{ env_var('INCLUDEWAREHOUSE_SCV_PASSWORD') }}" port: 5432 - dbname: postgres + dbname: includewarehouse schema: prd threads: 4 diff --git a/dbt_project/seeds/_seeds.yml b/dbt_project/seeds/_seeds.yml index 3ea41e7..d98ab0f 100644 --- a/dbt_project/seeds/_seeds.yml +++ b/dbt_project/seeds/_seeds.yml @@ -9,4 +9,26 @@ seeds: - name: letter description: A letter of the alphabet - name: letter_grouping - description: The grouping that the letter belongs to \ No newline at end of file + description: The grouping that the letter belongs to + + - name: s3_scrape_cody + config: + column_types: + Size: bigint + + - name: sample + config: + column_types: + # these were all the columns that had the highest integers and I narrowed it down to what would pass + total_reads: bigint + pf_aligned_bases: bigint + pf_hq_aligned_bases: bigint + pf_hq_aligned_q20_bases: bigint + genome_territory: bigint + library-1_estimated_library_size: bigint + # pf_reads: bigint + # pf_reads_aligned: bigint + # reads_aligned_in_pairs: bigint + # pf_hq_aligned_reads: bigint + # library-1_read_pairs: bigint + # pf_reads_improper_pairs: bigint \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_bsgf.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_bsgf.sql index 1880852..903b922 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_bsgf.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_bsgf.sql @@ -16,5 +16,5 @@ select distinct external_id, -- i think we can leave this out - it's rarely populated/used, visibility_reason, visibility_comment -from {{ ref('src_bsgf') }} +from {{ ref('kf_sd_1nns3k8v_src_bsgf') }} diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_diagnosis.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_diagnosis.sql index c1f0f61..493eae3 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_diagnosis.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_diagnosis.sql @@ -20,4 +20,4 @@ select distinct uberon_id_tumor_location, spatial_descriptor -from {{ ref('src_diagnosis') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_diagnosis') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_family.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_family.sql index cbf2906..42c91ee 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_family.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_family.sql @@ -13,4 +13,4 @@ select distinct visible, visibility_reason, visibility_comment -from {{ ref('src_family') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_family') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_genomic_files.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_genomic_files.sql index f34cf82..e223ec9 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_genomic_files.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_genomic_files.sql @@ -32,4 +32,4 @@ select distinct cavatica_file_id, cavatica_volume -from {{ ref('src_genomic_files') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_genomic_files') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_investigator.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_investigator.sql index f0719b9..60fc967 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_investigator.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_investigator.sql @@ -14,4 +14,4 @@ select distinct visible, visibility_reason, visibility_comment -from {{ ref('src_investigator') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_investigator') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_participant.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_participant.sql index 7327230..51c2866 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_participant.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_participant.sql @@ -22,4 +22,4 @@ select distinct visible, visibility_reason, -- can we standardize this a bit more? maybe release status instead of reason? and try to standardize more? visibility_comment -from {{ ref('src_participant') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_participant') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_phenotype.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_phenotype.sql index b755230..f7613d4 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_phenotype.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_phenotype.sql @@ -16,4 +16,4 @@ select distinct snomed_id_phenotype, external_id -from {{ ref('src_phenotype') }} +from {{ ref('kf_sd_1nns3k8v_src_phenotype') }} diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_segf.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_segf.sql index 05f30ff..446d4f5 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_segf.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_segf.sql @@ -13,4 +13,4 @@ select distinct kf_id as segf_id, visibility_reason, visibility_comment -from {{ ref ('src_segf') }} \ No newline at end of file +from {{ ref ('kf_sd_1nns3k8v_src_segf') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_sequencing_experiment.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_sequencing_experiment.sql index 749e045..42e4060 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_sequencing_experiment.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_sequencing_experiment.sql @@ -55,4 +55,4 @@ select distinct umi_barcode_read, umi_barcode_size -from {{ ref('src_sequencing_experiments') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_sequencing_experiments') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_specimens.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_specimens.sql index 7ec9c69..f7dc671 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_specimens.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_specimens.sql @@ -43,4 +43,4 @@ select distinct amount, amount_units, cell_entity -from {{ ref('src_specimens') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_specimens') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_study.sql b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_study.sql index 57f527f..7645f82 100644 --- a/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_study.sql +++ b/temp-models/sd_1nns3k8v_test/int/kf_sd_1nns3k8v_int_study.sql @@ -27,4 +27,4 @@ select distinct biobank_name, -- has been NA for kids first, only used for CBTN, should we keep? biobank_request_instructions, -- has been NA for kids first, only used for CBTN, should we keep? biobank_request_link -- has been NA for kids first, only used for CBTN, should we keep? -from {{ ref('src_study') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_src_study') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_bsgf.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_bsgf.sql index 77691a7..5efcb54 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_bsgf.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_bsgf.sql @@ -16,4 +16,4 @@ select distinct external_id, -- i think we can leave this out - it's rarely populated/used, visibility_reason, visibility_comment -from {{ ref('int_bsgf') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_bsgf') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_diagnosis.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_diagnosis.sql index 95a8076..cf672d0 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_diagnosis.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_diagnosis.sql @@ -19,4 +19,4 @@ select distinct uberon_id_tumor_location, spatial_descriptor -from {{ ref('int_diagnosis') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_diagnosis') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_family.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_family.sql index 9c68b90..f64c0ea 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_family.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_family.sql @@ -10,6 +10,6 @@ select distinct visible, visibility_reason, visibility_comment -from {{ ref('int_family') }} +from {{ ref('kf_sd_1nns3k8v_int_family') }} diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_genomic_file.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_genomic_file.sql index 48ce216..e40e1b1 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_genomic_file.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_genomic_file.sql @@ -27,4 +27,4 @@ select distinct file_version_descriptor, cavatica_volume -from {{ ref('int_genomic_files') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_genomic_files') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_investigator.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_investigator.sql index 0a3151a..0a8a032 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_investigator.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_investigator.sql @@ -14,4 +14,4 @@ select distinct visible, visibility_reason, visibility_comment -from {{ ref('int_investigator') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_investigator') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_participant.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_participant.sql index a10b326..d283148 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_participant.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_participant.sql @@ -21,4 +21,4 @@ select distinct visible, visibility_reason, visibility_comment -from {{ ref('int_participant') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_participant') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_phenotype.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_phenotype.sql index 057de7b..b38262b 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_phenotype.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_phenotype.sql @@ -13,4 +13,4 @@ select distinct observed, snomed_id_phenotype, external_id -from {{ ref('int_phenotype') }} +from {{ ref('kf_sd_1nns3k8v_int_phenotype') }} diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_segf.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_segf.sql index 7bf0a44..2677a68 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_segf.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_segf.sql @@ -13,4 +13,4 @@ select distinct segf_id, visibility_reason, visibility_comment -from {{ ref ('int_segf') }} \ No newline at end of file +from {{ ref ('kf_sd_1nns3k8v_int_segf') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_sequencing_experiment.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_sequencing_experiment.sql index ba14384..74fdaab 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_sequencing_experiment.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_sequencing_experiment.sql @@ -53,4 +53,4 @@ select distinct umi_barcode_offset, umi_barcode_read, umi_barcode_size -from {{ ref('int_sequencing_experiment') }} +from {{ ref('kf_sd_1nns3k8v_int_sequencing_experiment') }} diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_specimens.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_specimens.sql index 9a28948..d651227 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_specimens.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_specimens.sql @@ -40,4 +40,4 @@ select distinct amount, amount_units, cell_entity -from {{ ref('int_specimens') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_specimens') }} \ No newline at end of file diff --git a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_study.sql b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_study.sql index 615fbc1..77d94a9 100644 --- a/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_study.sql +++ b/temp-models/sd_1nns3k8v_test/stable/kf_sd_1nns3k8v_stable_study.sql @@ -27,4 +27,4 @@ select distinct biobank_name, -- has been NA for kids first, only used for CBTN, should we keep? biobank_request_instructions, -- has been NA for kids first, only used for CBTN, should we keep? biobank_request_link -- has been NA for kids first, only used for CBTN, should we keep? -from {{ ref('int_study') }} \ No newline at end of file +from {{ ref('kf_sd_1nns3k8v_int_study') }} \ No newline at end of file