From 6280dbbb4438240aa159ceabd85f72c741bd3c23 Mon Sep 17 00:00:00 2001 From: "Stephanie M. Gogarten" Date: Mon, 9 Sep 2024 16:01:01 -0700 Subject: [PATCH 1/2] add an enumerated value to analyte_type --- CHANGELOG.md | 7 +++++++ GREGoR_data_model.json | 4 ++-- sheets_to_JSON.R | 3 ++- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2a51cf4..6cb38c8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,12 @@ # Change log +## 1.6.1 + +|Table |Field |Change notes | +|:-------|:------------|:------------------------------| +|analyte |analyte_type |added PBMC as enumerated value | + + ## 1.6 |Table |Field |Change notes | diff --git a/GREGoR_data_model.json b/GREGoR_data_model.json index 33ea412..fc2e3b1 100644 --- a/GREGoR_data_model.json +++ b/GREGoR_data_model.json @@ -1,7 +1,7 @@ { "name": "GREGoR Data Model", "description": "Data model for the GREGoR consortium", - "version": "1.6", + "version": "1.6.1", "tables": [ { "table": "participant", @@ -638,7 +638,7 @@ "required": true, "description": "analyte derived from the primary_biosample. The actual thing you're sticking into a machine to analyze/sequence", "data_type": "enumeration", - "enumerations": ["DNA", "RNA", "cDNA", "blood plasma", "frozen whole blood", "high molecular weight DNA", "urine"], + "enumerations": ["DNA", "RNA", "cDNA", "blood plasma", "frozen whole blood", "high molecular weight DNA", "urine", "PBMC"], "examples": "DNA" }, { diff --git a/sheets_to_JSON.R b/sheets_to_JSON.R index 243c977..10a4b42 100644 --- a/sheets_to_JSON.R +++ b/sheets_to_JSON.R @@ -7,7 +7,7 @@ library(jsonlite) url <- "https://docs.google.com/spreadsheets/d/1p_0nhKMvKBueSrUAQMCe9cHv16WyhKSX_jnxNCuGFWg" model_name = "GREGoR Data Model" model_description = "Data model for the GREGoR consortium" -model_version = "1.6" +model_version = "1.6.1" # table metadata meta <- read_sheet(url, sheet="Table overview/status", skip=1) @@ -95,3 +95,4 @@ out # save the final version write(out, "GREGoR_data_model.json") + From 75fbc58daf93443420dfd7ab0470b93f7ed6c6a9 Mon Sep 17 00:00:00 2001 From: "Stephanie M. Gogarten" Date: Tue, 10 Sep 2024 11:11:38 -0700 Subject: [PATCH 2/2] reinstate SNV/INDEL as allowed value for genetic findings revert data model to v1.6, replacing previous changes --- CHANGELOG.md | 60 +++++++++++++++++++----------------------- GREGoR_data_model.json | 6 ++--- sheets_to_JSON.R | 3 +-- 3 files changed, 31 insertions(+), 38 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6cb38c8..91b2050 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,40 +1,34 @@ # Change log -## 1.6.1 - -|Table |Field |Change notes | -|:-------|:------------|:------------------------------| -|analyte |analyte_type |added PBMC as enumerated value | - - ## 1.6 -|Table |Field |Change notes | -|:-------------------------------|:-----------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------| -|called_variants_nanopore |variant_types |added STR as enumerated value | -|called_variants_pac_bio |variant_types |added STR as enumerated value | -|genetic_findings |experiment_id |added 'see_notes' and 'see_MOD' as example values (this field will be required for validation) | -|genetic_findings |variant_type |changed allowable values to match other 'called_variants' tables (SNV, INDEL as separate values posssibly with delimiter instead of SNV/INDEL | -|genetic_findings |pos |added note describing that this is .vcf-style coordinates | -|genetic_findings |pos |updated conditional requirement to align with variant_type change | -|genetic_findings |GREGoR_variant_classification |required if known disease gene | -|genetic_findings |gene_disease_validity_notes |required if known disease gene | -|genetic_findings |gene_disease_validity_notes |added; not required | -|genetic_findings |VRS_ID |added; not required | -|experiment_rna_short_read |depletion_targets |added; not required | -|called_variants_nanopore |chrom |added; not required | -|called_variants_pac_bio |chrom |added; not required | -|called_variants_optical_mapping |chrom |added; not required | -|aligned_nanopore |num_reads |changed data type to float for large number support | -|aligned_nanopore |num_bases |changed data type to float for large number support | -|aligned_nanopore |num_aligned_reads |changed data type to float for large number support | -|aligned_nanopore |num_aligned_bases |changed data type to float for large number support | -|aligned_nanopore |read_length_mean |changed data type to float | -|aligned_pac_bio |num_reads |changed data type to float for large number support | -|aligned_pac_bio |num_bases |changed data type to float for large number support | -|aligned_pac_bio |num_aligned_reads |changed data type to float for large number support | -|aligned_pac_bio |num_aligned_bases |changed data type to float for large number support | -|aligned_pac_bio |read_length_mean |changed data type to float | +|Table |Field |Change notes | +|:-------------------------------|:-----------------------------|:-------------------------------------------------------------------------------------------------| +|called_variants_nanopore |variant_types |added STR as enumerated value | +|called_variants_pac_bio |variant_types |added STR as enumerated value | +|genetic_findings |experiment_id |added 'see_notes' and 'see_MOD' as example values (this field will be required for validation) | +|genetic_findings |variant_type |added more specific enumerated values (possibly with delimiter) to match 'called_variants' tables | +|genetic_findings |pos |added note describing that this is .vcf-style coordinates | +|genetic_findings |pos |updated conditional requirement to align with variant_type change | +|genetic_findings |GREGoR_variant_classification |required if known disease gene | +|genetic_findings |gene_disease_validity_notes |required if known disease gene | +|genetic_findings |gene_disease_validity_notes |added; not required | +|genetic_findings |VRS_ID |added; not required | +|experiment_rna_short_read |depletion_targets |added; not required | +|called_variants_nanopore |chrom |added; not required | +|called_variants_pac_bio |chrom |added; not required | +|called_variants_optical_mapping |chrom |added; not required | +|aligned_nanopore |num_reads |changed data type to float for large number support | +|aligned_nanopore |num_bases |changed data type to float for large number support | +|aligned_nanopore |num_aligned_reads |changed data type to float for large number support | +|aligned_nanopore |num_aligned_bases |changed data type to float for large number support | +|aligned_nanopore |read_length_mean |changed data type to float | +|aligned_pac_bio |num_reads |changed data type to float for large number support | +|aligned_pac_bio |num_bases |changed data type to float for large number support | +|aligned_pac_bio |num_aligned_reads |changed data type to float for large number support | +|aligned_pac_bio |num_aligned_bases |changed data type to float for large number support | +|aligned_pac_bio |read_length_mean |changed data type to float | +|analyte |analyte_type |added PBMC as enumerated value | ## 1.5.2 diff --git a/GREGoR_data_model.json b/GREGoR_data_model.json index fc2e3b1..231206a 100644 --- a/GREGoR_data_model.json +++ b/GREGoR_data_model.json @@ -1,7 +1,7 @@ { "name": "GREGoR Data Model", "description": "Data model for the GREGoR consortium", - "version": "1.6.1", + "version": "1.6", "tables": [ { "table": "participant", @@ -343,10 +343,10 @@ "column": "variant_type", "required": true, "data_type": "enumeration", - "enumerations": ["SNV", "INDEL", "SV", "CNV", "RE", "MEI", "STR"], + "enumerations": ["SNV/INDEL", "SV", "RE", "SNV", "INDEL", "CNV", "MEI", "STR"], "multi_value_delimiter": "|", "examples": "SNV|CNV", - "notes": "SNV: single nucelotide variants\nINDEL: short insertion/deletions (<50bp)\nRE: repeat elements\nSV: structural variants, including copy number variants and mobile element insertions" + "notes": "SNV/INDEL: single nucelotide variants or short insertion/deletions (<50bp)\nRE: repeat elements\nSV: structural variants, including copy number variants and mobile element insertions" }, { "column": "sv_type", diff --git a/sheets_to_JSON.R b/sheets_to_JSON.R index 10a4b42..243c977 100644 --- a/sheets_to_JSON.R +++ b/sheets_to_JSON.R @@ -7,7 +7,7 @@ library(jsonlite) url <- "https://docs.google.com/spreadsheets/d/1p_0nhKMvKBueSrUAQMCe9cHv16WyhKSX_jnxNCuGFWg" model_name = "GREGoR Data Model" model_description = "Data model for the GREGoR consortium" -model_version = "1.6.1" +model_version = "1.6" # table metadata meta <- read_sheet(url, sheet="Table overview/status", skip=1) @@ -95,4 +95,3 @@ out # save the final version write(out, "GREGoR_data_model.json") -