diff --git a/src/data/valid/Biosample-possibly-exhaustive.yaml b/src/data/valid/Biosample-possibly-exhaustive.yaml index c5290bf1c5..1bb31c59fc 100644 --- a/src/data/valid/Biosample-possibly-exhaustive.yaml +++ b/src/data/valid/Biosample-possibly-exhaustive.yaml @@ -1580,10 +1580,10 @@ other_treatment: unconstrained text start_date_inc: '2023-01-27' start_time_inc: 13:42+0000 project_id: no example from MIxS -replicate_number: '1' +replicate_number: 1 sample_shipped: 15 g sample_type: soil - water extract -technical_reps: '2' +technical_reps: 2 analysis_type: - metabolomics - metagenomics diff --git a/src/data/valid/Database-interleaved.yaml b/src/data/valid/Database-interleaved.yaml index abb1bfbbb8..ce8a4ef219 100644 --- a/src/data/valid/Database-interleaved.yaml +++ b/src/data/valid/Database-interleaved.yaml @@ -3009,10 +3009,10 @@ biosample_set: start_date_inc: '2023-01-27' start_time_inc: 13:42+0000 project_id: no example from MIxS - replicate_number: '1' + replicate_number: 1 sample_shipped: 15 g sample_type: soil - water extract - technical_reps: '2' + technical_reps: 2 analysis_type: - metabolomics - metagenomics diff --git a/src/schema/core.yaml b/src/schema/core.yaml index fef9a7c4ff..524cb1f42c 100644 --- a/src/schema/core.yaml +++ b/src/schema/core.yaml @@ -9,9 +9,7 @@ imports: - attribute_values - basic_slots - basic_classes - - portal_emsl - - portal_jgi_metagenomics - - portal_jgi_metatranscriptomics + - portal_user_facility - portal_mixs_inspired - portal_sample_id diff --git a/src/schema/portal_emsl.yaml b/src/schema/portal_emsl.yaml deleted file mode 100644 index c88ed66885..0000000000 --- a/src/schema/portal_emsl.yaml +++ /dev/null @@ -1,85 +0,0 @@ -name: emsl -description: This file defines terms that appear in the 'EMSL' section of the NMDC - sample metadata submission portal, which is implemented with DataHarmonizer as of - Spring 2022 -title: 'NMDC Schema supplement for Submission Portal: EMSL' -id: https://w3id.org/nmdc/emsl -license: https://creativecommons.org/publicdomain/zero/1.0/ -prefixes: - linkml: https://w3id.org/linkml/ - nmdc: https://w3id.org/nmdc/ -imports: - - nmdc_types - - portal_enums -default_prefix: nmdc -default_range: string -slots: - emsl_store_temp: - description: The temperature at which the sample should be stored upon delivery - to EMSL - title: EMSL sample storage temperature, deg. C - todos: - - add 'see_also's with link to NEXUS info - comments: - - Enter a temperature in celsius. Numeric portion only. - examples: - - value: '-80' - rank: 4 - string_serialization: '{float}' - recommended: true - slot_group: EMSL - project_id: - description: Proposal IDs or names associated with dataset - title: project ID - rank: 1 - string_serialization: '{text}' - slot_group: EMSL - recommended: true - replicate_number: - description: If sending biological replicates, indicate the rep number here. - title: replicate number - comments: - - This will guide staff in ensuring your samples are blocked & randomized correctly - rank: 6 - string_serialization: '{integer}' - slot_group: EMSL - recommended: true - sample_shipped: - description: The total amount or size (volume (ml), mass (g) or area (m2) ) of - sample sent to EMSL. - title: sample shipped amount - comments: - - This field is only required when completing metadata for samples being submitted - to EMSL for analyses. - examples: - - value: 15 g - - value: 100 uL - - value: 5 mL - rank: 3 - string_serialization: '{float} {unit}' - slot_group: EMSL - recommended: true - sample_type: - description: Type of sample being submitted - title: sample type - comments: - - This can vary from 'environmental package' if the sample is an extraction. - examples: - - value: water extracted soil - rank: 2 - slot_group: EMSL - range: SampleTypeEnum - recommended: true - technical_reps: - description: If sending technical replicates of the same sample, indicate the - replicate count. - title: number technical replicate - comments: - - This field is only required when completing metadata for samples being submitted - to EMSL for analyses. - examples: - - value: '2' - rank: 5 - string_serialization: '{integer}' - slot_group: EMSL - recommended: true diff --git a/src/schema/portal_jgi_metagenomics.yaml b/src/schema/portal_jgi_metagenomics.yaml deleted file mode 100644 index c9d31b444d..0000000000 --- a/src/schema/portal_jgi_metagenomics.yaml +++ /dev/null @@ -1,52 +0,0 @@ -name: jgi_metagenomics -description: This file defines terms that appear in the 'JGI-Metagenomics' section - of the NMDC sample metadata submission portal, which is implemented with DataHarmonizer - as of Spring 2022 -title: 'NMDC Schema supplement for Submission Portal: JGI-Metagenomics' -id: https://w3id.org/nmdc/portal/jgi_metagenomics - -license: https://creativecommons.org/publicdomain/zero/1.0/ - -imports: - - portal_enums - - nmdc_types - -prefixes: - linkml: "https://w3id.org/linkml/" - nmdc: "https://w3id.org/nmdc/" - -default_prefix: nmdc -default_range: string - -slots: - dna_collect_site: - description: Provide information on the site your DNA sample was collected from - title: DNA collection site - examples: - - value: untreated pond water - rank: 15 - string_serialization: '{text}' - slot_group: JGI-Metagenomics - recommended: true - dna_isolate_meth: - description: Describe the method/protocol/kit used to extract DNA/RNA. - title: DNA isolation method - examples: - - value: phenol/chloroform extraction - rank: 16 - string_serialization: '{text}' - slot_group: JGI-Metagenomics - recommended: true - aliases: - - Sample Isolation Method - dna_organisms: - description: List any organisms known or suspected to grow in co-culture, as well - as estimated % of the organism in that culture. - title: DNA expected organisms - examples: - - value: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles - (1%) - rank: 14 - string_serialization: '{text}' - slot_group: JGI-Metagenomics - recommended: true diff --git a/src/schema/portal_jgi_metatranscriptomics.yaml b/src/schema/portal_jgi_metatranscriptomics.yaml deleted file mode 100644 index 27efce7943..0000000000 --- a/src/schema/portal_jgi_metatranscriptomics.yaml +++ /dev/null @@ -1,48 +0,0 @@ -name: jgi_metatranscriptomics -description: This file defines terms that appear in the 'JGI-Metatranscriptomics' - section of the NMDC sample metadata submission portal, which is implemented with - DataHarmonizer as of Spring 2022 -title: 'NMDC Schema supplement for Submission Portal: JGI-Metatranscriptomics' -id: https://w3id.org/nmdc/portal/jgi_metatranscriptomics -license: https://creativecommons.org/publicdomain/zero/1.0/ -prefixes: - linkml: "https://w3id.org/linkml/" - nmdc: "https://w3id.org/nmdc/" -imports: - - portal_enums - - nmdc_types -default_prefix: nmdc -default_range: string -slots: - rna_collect_site: - description: Provide information on the site your RNA sample was collected from - title: RNA collection site - examples: - - value: untreated pond water - rank: 15 - string_serialization: '{text}' - slot_group: JGI-Metatranscriptomics - recommended: true - rna_isolate_meth: - description: Describe the method/protocol/kit used to extract DNA/RNA. - title: RNA isolation method - examples: - - value: phenol/chloroform extraction - aliases: - - Sample Isolation Method - rank: 16 - string_serialization: '{text}' - slot_group: JGI-Metatranscriptomics - recommended: true - rna_organisms: - description: List any organisms known or suspected to grow in co-culture, as well - as estimated % of the organism in that culture. - title: RNA expected organisms - examples: - - value: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles - (1%) - rank: 14 - string_serialization: '{text}' - slot_group: JGI-Metatranscriptomics - recommended: true - diff --git a/src/schema/portal_user_facility.yaml b/src/schema/portal_user_facility.yaml new file mode 100644 index 0000000000..f9b1074453 --- /dev/null +++ b/src/schema/portal_user_facility.yaml @@ -0,0 +1,145 @@ +name: user_facility_metadata +description: This file defines terms that appear in the 'JGI-Metagenomics', `JGI-Metagenomics Long Read`, `JGI-Metatranscriptomics`, `EMSL` sections + of the NMDC sample metadata submission portal, which is implemented with DataHarmonizer + as of Spring 2022 +title: 'NMDC Schema supplement for Submission Portal: User Facility Metadata' +id: https://w3id.org/nmdc/portal/jgi_metagenomics + +license: https://creativecommons.org/publicdomain/zero/1.0/ + +imports: + - portal_enums + - nmdc_types + +prefixes: + linkml: "https://w3id.org/linkml/" + nmdc: "https://w3id.org/nmdc/" + +default_prefix: nmdc +default_range: string + +slots: + rna_collect_site: + description: Provide information on the site your RNA sample was collected from + title: RNA collection site + examples: + - value: untreated pond water + rank: 15 + recommended: true + deprecated: true; as of 2025-10-10, NMDC doesn't need to store this JGI metadata slot & it's now captured directly in the submission portal schema to support submissions + rna_isolate_meth: + description: Describe the method/protocol/kit used to extract DNA/RNA. + title: RNA isolation method + examples: + - value: phenol/chloroform extraction + aliases: + - Sample Isolation Method + rank: 16 + recommended: true + rna_organisms: + description: List any organisms known or suspected to grow in co-culture, as well + as estimated % of the organism in that culture. + title: RNA expected organisms + examples: + - value: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles + (1%) + rank: 14 + recommended: true + deprecated: true; as of 2025-10-10, NMDC doesn't need to store this JGI metadata slot & it's now captured directly in the submission portal schema to support submissions + dna_lr_isolate_meth: + description: Describe the method/protocol/kit used to extract DNA/RNA for long read sequencing. + title: DNA isolation method for long read sequencing + examples: + - value: phenol/chloroform extraction + rank: 16 + recommended: true + aliases: + - Sample Isolation Method + dna_collect_site: + description: Provide information on the site your DNA sample was collected from + title: DNA collection site + examples: + - value: untreated pond water + rank: 15 + recommended: true + deprecated: true; as of 2025-10-10, NMDC doesn't need to store this JGI metadata slot & it's now captured directly in the submission portal schema to support submissions + dna_isolate_meth: + description: Describe the method/protocol/kit used to extract DNA/RNA. + title: DNA isolation method + examples: + - value: phenol/chloroform extraction + rank: 16 + recommended: true + aliases: + - Sample Isolation Method + dna_organisms: + description: List any organisms known or suspected to grow in co-culture, as well + as estimated % of the organism in that culture. + title: DNA expected organisms + examples: + - value: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles + (1%) + rank: 14 + recommended: true + deprecated: true; as of 2025-10-10, NMDC doesn't need to store this JGI metadata slot & it's now captured directly in the submission portal schema to support submissions + emsl_store_temp: + description: The temperature at which the sample should be stored upon delivery + to EMSL + title: EMSL sample storage temperature, deg. C + range: float + todos: + - add 'see_also's with link to NEXUS info + comments: + - Enter a temperature in celsius. Numeric portion only. + examples: + - value: '-80' + rank: 4 + recommended: true + project_id: + description: Proposal IDs or names associated with dataset + title: project ID + rank: 1 + recommended: true + sample_shipped: + description: The total amount or size (volume (ml), mass (g) or area (m2) ) of + sample sent to EMSL. + title: sample shipped amount + comments: + - This field is only required when completing metadata for samples being submitted + to EMSL for analyses. + examples: + - value: 15 g + - value: 100 uL + - value: 5 mL + rank: 3 + recommended: true + sample_type: + description: Type of sample being submitted + title: sample type + comments: + - This can vary from 'environmental package' if the sample is an extraction. + examples: + - value: water extracted soil + rank: 2 + range: SampleTypeEnum + recommended: true + replicate_number: + description: If sending biological replicates, indicate the rep number here. + title: replicate number + range: integer + comments: + - This will guide staff in ensuring your samples are blocked & randomized correctly + rank: 6 + recommended: true + technical_reps: + description: If sending technical replicates of the same sample, indicate the + replicate count. + title: number technical replicate + range: integer + comments: + - This field is only required when completing metadata for samples being submitted + to EMSL for analyses. + examples: + - value: '2' + rank: 5 + recommended: true diff --git a/src/scripts/check_schema_self_containment.py b/src/scripts/check_schema_self_containment.py index 94606239a6..7a0ee2b48e 100644 --- a/src/scripts/check_schema_self_containment.py +++ b/src/scripts/check_schema_self_containment.py @@ -28,10 +28,8 @@ "src/schema/nmdc_subsets.yaml", "src/schema/nmdc_types.yaml", "src/schema/nmdc.yaml", - "src/schema/portal_emsl.yaml", "src/schema/portal_enums.yaml", - "src/schema/portal_jgi_metagenomics.yaml", - "src/schema/portal_jgi_metatranscriptomics.yaml", + "src/schema/portal_user_facility.yaml", "src/schema/portal_mixs_inspired.yaml", "src/schema/portal_sample_id.yaml" }