From 0d620147847f795dc2553e7e7f4ab1017b808dc7 Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 12:40:29 -0500 Subject: [PATCH 01/11] add yaml files to branch --- .../schemas/submitted_expression_array.yaml | 87 +++++++++++++++++++ .../schemas/submitted_genotyping_array.yaml | 86 ++++++++++++++++++ 2 files changed, 173 insertions(+) create mode 100644 gdcdictionary/schemas/submitted_expression_array.yaml create mode 100644 gdcdictionary/schemas/submitted_genotyping_array.yaml diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml new file mode 100644 index 0000000..57ff596 --- /dev/null +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -0,0 +1,87 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_expression_array" +title: Submitted Expression Array +type: object +namespace: https://gdc.cancer.gov +category: data_file +project: '*' +program: '*' +description: >- + Data file containing raw data from an expression array. +additionalProperties: false +submittable: true +downloadable: true +previous_version_downloadable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - file_state + - state + - error_type + +links: + - name: aliquots + backref: submitted_expression_arrays + label: derived_from + target_type: aliquot + multiplicity: many_to_one + required: true + +required: + - submitter_id + - file_name + - file_size + - md5sum + - data_category + - data_format + - data_type + - experimental_strategy + - platform + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Transcriptome Profiling + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - CEL + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Raw Intensities + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + enum: + - Expression Array + + platform: + $ref: + - "_terms.yaml#/platform/common" + enum: + - GeneChip U133 Plus 2.0 + - GeneChip U133A + + aliquots: + $ref: "_definitions.yaml#/to_one" diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml new file mode 100644 index 0000000..071aa71 --- /dev/null +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -0,0 +1,86 @@ +$schema: "http://json-schema.org/draft-04/schema#" + +id: "submitted_genotyping_array" +title: Submitted Genotyping Array +type: object +namespace: https://gdc.cancer.gov +category: data_file +project: '*' +program: '*' +description: >- + Data file containing raw data from a genotyping array. +additionalProperties: false +submittable: true +downloadable: true +previous_version_downloadable: true +validators: null + +systemProperties: + - id + - project_id + - created_datetime + - updated_datetime + - file_state + - state + - error_type + +links: + - name: aliquots + backref: submitted_genotyping_arrays + label: derived_from + target_type: aliquot + multiplicity: many_to_one + required: true + +required: + - submitter_id + - file_name + - file_size + - md5sum + - data_category + - data_format + - data_type + - experimental_strategy + - platform + +uniqueKeys: + - [id] + - [project_id, submitter_id] + +properties: + + $ref: + - "_definitions.yaml#/data_file_properties" + + data_category: + $ref: + - "_terms.yaml#/data_category/common" + enum: + - Copy Number Variation + + data_type: + $ref: + - "_terms.yaml#/data_type/common" + enum: + - Raw Intensities + + data_format: + $ref: + - "_terms.yaml#/data_format/common" + enum: + - CEL + + experimental_strategy: + $ref: + - "_terms.yaml#/experimental_strategy/common" + enum: + - Genotyping Array + + platform: + $ref: + - "_terms.yaml#/platform/common" + enum: + - Affymetrix SNP 6.0 + + aliquots: + $ref: "_definitions.yaml#/to_one" From d4cbada61def353d54a6beba02c8123535c7291a Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 12:48:03 -0500 Subject: [PATCH 02/11] remove incorrect data_format from submitted_methylation --- gdcdictionary/schemas/submitted_methylation.yaml | 2 -- 1 file changed, 2 deletions(-) diff --git a/gdcdictionary/schemas/submitted_methylation.yaml b/gdcdictionary/schemas/submitted_methylation.yaml index e4efc72..d87af4b 100644 --- a/gdcdictionary/schemas/submitted_methylation.yaml +++ b/gdcdictionary/schemas/submitted_methylation.yaml @@ -70,8 +70,6 @@ properties: term: $ref: "_terms.yaml#/data_format" enum: - - ARR - - CEL - IDAT assay_method: From afce63534a8448dec8c8eb5e822a4fedffcef288 Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 12:49:33 -0500 Subject: [PATCH 03/11] format new node yamls --- .../schemas/submitted_expression_array.yaml | 27 +++++++++++------- .../schemas/submitted_genotyping_array.yaml | 28 ++++++++++++------- 2 files changed, 35 insertions(+), 20 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 57ff596..9cffbd9 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -3,16 +3,14 @@ $schema: "http://json-schema.org/draft-04/schema#" id: "submitted_expression_array" title: Submitted Expression Array type: object -namespace: https://gdc.cancer.gov +namespace: https://dcp.bionimbus.org/ category: data_file -project: '*' program: '*' +project: '*' description: >- Data file containing raw data from an expression array. additionalProperties: false submittable: true -downloadable: true -previous_version_downloadable: true validators: null systemProperties: @@ -20,17 +18,26 @@ systemProperties: - project_id - created_datetime - updated_datetime - - file_state - state + - file_state - error_type links: - - name: aliquots - backref: submitted_expression_arrays - label: derived_from - target_type: aliquot - multiplicity: many_to_one + - exclusive: false required: true + subgroup: + - name: core_metadata_collections + backref: submitted_aligned_reads_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - name: aliquots + backref: submitted_expression_arrays + label: derived_from + target_type: aliquot + multiplicity: many_to_one + required: true required: - submitter_id diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 071aa71..265012e 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -3,16 +3,14 @@ $schema: "http://json-schema.org/draft-04/schema#" id: "submitted_genotyping_array" title: Submitted Genotyping Array type: object -namespace: https://gdc.cancer.gov +namespace: https://dcp.bionimbus.org/ category: data_file -project: '*' program: '*' +project: '*' description: >- Data file containing raw data from a genotyping array. additionalProperties: false submittable: true -downloadable: true -previous_version_downloadable: true validators: null systemProperties: @@ -20,17 +18,26 @@ systemProperties: - project_id - created_datetime - updated_datetime - - file_state - state + - file_state - error_type links: - - name: aliquots - backref: submitted_genotyping_arrays - label: derived_from - target_type: aliquot - multiplicity: many_to_one + - exclusive: false required: true + subgroup: + - name: core_metadata_collections + backref: submitted_aligned_reads_files + label: data_from + target_type: core_metadata_collection + multiplicity: many_to_many + required: false + - name: aliquots + backref: submitted_expression_arrays + label: derived_from + target_type: aliquot + multiplicity: many_to_one + required: true required: - submitter_id @@ -80,6 +87,7 @@ properties: $ref: - "_terms.yaml#/platform/common" enum: + - Affymetrix - Affymetrix SNP 6.0 aliquots: From 22fc634c5bd5dc79ef242cd1fe839e319d7bbbfa Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 13:10:41 -0500 Subject: [PATCH 04/11] fix properties ref --- gdcdictionary/schemas/submitted_expression_array.yaml | 4 +--- gdcdictionary/schemas/submitted_genotyping_array.yaml | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 9cffbd9..f574120 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -55,9 +55,7 @@ uniqueKeys: - [project_id, submitter_id] properties: - - $ref: - - "_definitions.yaml#/data_file_properties" + $ref: "_definitions.yaml#/data_file_properties" data_category: $ref: diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 265012e..4a1c186 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -55,9 +55,7 @@ uniqueKeys: - [project_id, submitter_id] properties: - - $ref: - - "_definitions.yaml#/data_file_properties" + $ref: "_definitions.yaml#/data_file_properties" data_category: $ref: From 37def7e6050c0a9505fb4e2794779069a45fd222 Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 13:15:05 -0500 Subject: [PATCH 05/11] remove 'common/' from term refs --- gdcdictionary/schemas/submitted_expression_array.yaml | 10 +++++----- gdcdictionary/schemas/submitted_genotyping_array.yaml | 10 +++++----- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index f574120..52cf2de 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -59,31 +59,31 @@ properties: data_category: $ref: - - "_terms.yaml#/data_category/common" + - "_terms.yaml#/data_category" enum: - Transcriptome Profiling data_format: $ref: - - "_terms.yaml#/data_format/common" + - "_terms.yaml#/data_format" enum: - CEL data_type: $ref: - - "_terms.yaml#/data_type/common" + - "_terms.yaml#/data_type" enum: - Raw Intensities experimental_strategy: $ref: - - "_terms.yaml#/experimental_strategy/common" + - "_terms.yaml#/experimental_strategy" enum: - Expression Array platform: $ref: - - "_terms.yaml#/platform/common" + - "_terms.yaml#/platform" enum: - GeneChip U133 Plus 2.0 - GeneChip U133A diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 4a1c186..a1e9e6f 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -59,31 +59,31 @@ properties: data_category: $ref: - - "_terms.yaml#/data_category/common" + - "_terms.yaml#/data_category" enum: - Copy Number Variation data_type: $ref: - - "_terms.yaml#/data_type/common" + - "_terms.yaml#/data_type" enum: - Raw Intensities data_format: $ref: - - "_terms.yaml#/data_format/common" + - "_terms.yaml#/data_format" enum: - CEL experimental_strategy: $ref: - - "_terms.yaml#/experimental_strategy/common" + - "_terms.yaml#/experimental_strategy" enum: - Genotyping Array platform: $ref: - - "_terms.yaml#/platform/common" + - "_terms.yaml#/platform" enum: - Affymetrix - Affymetrix SNP 6.0 From 42d0fc1c9343a7b8c51da33263d71fa71481492f Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 13:20:11 -0500 Subject: [PATCH 06/11] further fix format of props --- .../schemas/submitted_expression_array.yaml | 22 ++++++++++--------- .../schemas/submitted_genotyping_array.yaml | 18 +++++++-------- 2 files changed, 20 insertions(+), 20 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 52cf2de..2756a93 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -58,35 +58,37 @@ properties: $ref: "_definitions.yaml#/data_file_properties" data_category: - $ref: - - "_terms.yaml#/data_category" + term: + $ref: "_terms.yaml#/data_category" enum: - Transcriptome Profiling data_format: - $ref: - - "_terms.yaml#/data_format" + term: + $ref: "_terms.yaml#/data_format" enum: - CEL data_type: - $ref: - - "_terms.yaml#/data_type" + term: + $ref: "_terms.yaml#/data_type" enum: - Raw Intensities experimental_strategy: - $ref: - - "_terms.yaml#/experimental_strategy" + term: + $ref: "_terms.yaml#/experimental_strategy" enum: - Expression Array platform: - $ref: - - "_terms.yaml#/platform" + term: + $ref: "_terms.yaml#/platform" enum: - GeneChip U133 Plus 2.0 - GeneChip U133A aliquots: $ref: "_definitions.yaml#/to_one" + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index a1e9e6f..659e0da 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -58,35 +58,33 @@ properties: $ref: "_definitions.yaml#/data_file_properties" data_category: - $ref: - - "_terms.yaml#/data_category" + term: + $ref: "_terms.yaml#/data_category" enum: - Copy Number Variation data_type: - $ref: - - "_terms.yaml#/data_type" + $ref: "_terms.yaml#/data_type" enum: - Raw Intensities data_format: - $ref: - - "_terms.yaml#/data_format" + $ref: "_terms.yaml#/data_format" enum: - CEL experimental_strategy: - $ref: - - "_terms.yaml#/experimental_strategy" + $ref: "_terms.yaml#/experimental_strategy" enum: - Genotyping Array platform: - $ref: - - "_terms.yaml#/platform" + $ref: "_terms.yaml#/platform" enum: - Affymetrix - Affymetrix SNP 6.0 aliquots: $ref: "_definitions.yaml#/to_one" + core_metadata_collections: + $ref: "_definitions.yaml#/to_many" From 1d9ad233b85186fd7950c2a49e490f119ac7c96b Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 13:25:34 -0500 Subject: [PATCH 07/11] fix links --- gdcdictionary/schemas/submitted_expression_array.yaml | 4 ++-- gdcdictionary/schemas/submitted_genotyping_array.yaml | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 2756a93..9b93c12 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -27,7 +27,7 @@ links: required: true subgroup: - name: core_metadata_collections - backref: submitted_aligned_reads_files + backref: submitted_expression_arrays label: data_from target_type: core_metadata_collection multiplicity: many_to_many @@ -37,7 +37,7 @@ links: label: derived_from target_type: aliquot multiplicity: many_to_one - required: true + required: false required: - submitter_id diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 659e0da..289be6d 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -27,17 +27,17 @@ links: required: true subgroup: - name: core_metadata_collections - backref: submitted_aligned_reads_files + backref: submitted_genotyping_arrays label: data_from target_type: core_metadata_collection multiplicity: many_to_many required: false - name: aliquots - backref: submitted_expression_arrays + backref: submitted_genotyping_arrays label: derived_from target_type: aliquot multiplicity: many_to_one - required: true + required: false required: - submitter_id From f0fbd501d094185cfff5a8e9236d6ad0298e38da Mon Sep 17 00:00:00 2001 From: eric Date: Thu, 9 Oct 2025 13:28:47 -0500 Subject: [PATCH 08/11] add type to required props --- gdcdictionary/schemas/submitted_expression_array.yaml | 3 ++- gdcdictionary/schemas/submitted_genotyping_array.yaml | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 9b93c12..40ed0cd 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -40,13 +40,14 @@ links: required: false required: + - type - submitter_id - file_name - file_size - md5sum - data_category - - data_format - data_type + - data_format - experimental_strategy - platform diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 289be6d..283efc2 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -40,13 +40,14 @@ links: required: false required: + - type - submitter_id - file_name - file_size - md5sum - data_category - - data_format - data_type + - data_format - experimental_strategy - platform From baef72f789d3fbb813b03215cd8e62be284991f9 Mon Sep 17 00:00:00 2001 From: eric <98181083+ciresiemanym@users.noreply.github.com> Date: Thu, 9 Oct 2025 16:07:06 -0500 Subject: [PATCH 09/11] Update submitted_expression_array.yaml --- gdcdictionary/schemas/submitted_expression_array.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gdcdictionary/schemas/submitted_expression_array.yaml b/gdcdictionary/schemas/submitted_expression_array.yaml index 40ed0cd..24ee685 100644 --- a/gdcdictionary/schemas/submitted_expression_array.yaml +++ b/gdcdictionary/schemas/submitted_expression_array.yaml @@ -7,7 +7,7 @@ namespace: https://dcp.bionimbus.org/ category: data_file program: '*' project: '*' -description: >- +description: > Data file containing raw data from an expression array. additionalProperties: false submittable: true From c106325acba2c1134a2bb552cc9678e0f6543af7 Mon Sep 17 00:00:00 2001 From: eric <98181083+ciresiemanym@users.noreply.github.com> Date: Thu, 9 Oct 2025 16:07:30 -0500 Subject: [PATCH 10/11] Update submitted_genotyping_array.yaml --- gdcdictionary/schemas/submitted_genotyping_array.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gdcdictionary/schemas/submitted_genotyping_array.yaml b/gdcdictionary/schemas/submitted_genotyping_array.yaml index 283efc2..5c62d05 100644 --- a/gdcdictionary/schemas/submitted_genotyping_array.yaml +++ b/gdcdictionary/schemas/submitted_genotyping_array.yaml @@ -7,7 +7,7 @@ namespace: https://dcp.bionimbus.org/ category: data_file program: '*' project: '*' -description: >- +description: > Data file containing raw data from a genotyping array. additionalProperties: false submittable: true From c3d95ebb92674f5659733fe6842cfb14aaa460e2 Mon Sep 17 00:00:00 2001 From: eric <98181083+ciresiemanym@users.noreply.github.com> Date: Wed, 15 Oct 2025 09:05:54 -0500 Subject: [PATCH 11/11] Update reference_file.yaml --- gdcdictionary/schemas/reference_file.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/gdcdictionary/schemas/reference_file.yaml b/gdcdictionary/schemas/reference_file.yaml index 82f9653..6087a6f 100644 --- a/gdcdictionary/schemas/reference_file.yaml +++ b/gdcdictionary/schemas/reference_file.yaml @@ -87,6 +87,7 @@ properties: - ALT - AMB - ANN + - ARR - AVRO - BCF - BED