From d7498093d0f5e0db052ef88815d57c2648d09425 Mon Sep 17 00:00:00 2001 From: lltommy Date: Thu, 9 Apr 2020 14:34:54 +0200 Subject: Updating schema and examples. This is still work in progress but we get there --- bh20sequploader/bh20seq-schema.yml | 60 ++++++++++++++++++++++++++------------ 1 file changed, 42 insertions(+), 18 deletions(-) (limited to 'bh20sequploader/bh20seq-schema.yml') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 6e0973a..38cfb48 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -1,36 +1,60 @@ $graph: -- name: sampleInformationSchema +- name: hostSchema type: record fields: - location: string - host: string - sequenceTechnology: string - assemblyMethod: string + host_id: string + host_species: string + host_common_name: string? + host_sex: string? + host_age: int? + host_age_unit: string? + host_health_status: string? + host_treatment: string? + additional_host_information: string? -- name: InstituteInformationSchema +- name: sampleSchema type: record fields: - OriginatingLab: string - SubmittingLab: string + collector_name: string + collecting_institution: string + specimen_source: string? + collection_date: string? + collection_location: string? + sample_storage_conditions: string? + additional_collection_information: string? -- name: SubmitterInformationSchema +- name: virusSchema type: record fields: - Submitter: string - submissionDate: string + virus_species: string? + virus_strain: string? -- name: VirusDetailSchema +- name: technologySchema type: record fields: - VirusName: string - AccessionId: string + sample_sequencing_technology: string + sequence_assembly_method: string? + sequencing_coverage: string? + +- name: submitterSchema + type: record + fields: + submitter_name: string + submitter_address: string? + originating_lab: string + lab_address: string? + provider_sample_id: string? + submitter_sample_id: string? + authors: string? + submitter_id: string? - name: MainSchema type: record documentRoot: true fields: - sampleInformation: sampleInformationSchema - InstituteInformation: InstituteInformationSchema - SubmitterInformation: SubmitterInformationSchema - VirusDetail: VirusDetailSchema + host: hostSchema + sample: sampleSchema + virus: virusSchema? + technology: technologySchema + submitter: submitterSchema \ No newline at end of file -- cgit v1.2.3 From deedb2ed7046bbe81136b8d9d1edc353984d356b Mon Sep 17 00:00:00 2001 From: lltommy Date: Thu, 9 Apr 2020 20:38:55 +0200 Subject: Adding functionality of turning keys into ontology terms (URI). This is work in progress - of course! --- bh20sequploader/bh20seq-schema.yml | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) (limited to 'bh20sequploader/bh20seq-schema.yml') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 38cfb48..fd9e854 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -3,14 +3,20 @@ $graph: - name: hostSchema type: record fields: + host_species: + type: string + jsonldPredicate: + _id: http://www.ebi.ac.uk/efo/EFO_0000532 host_id: string - host_species: string host_common_name: string? host_sex: string? host_age: int? host_age_unit: string? host_health_status: string? - host_treatment: string? + host_treatment: + type: string? + jsonldPredicate: + _id: http://www.ebi.ac.uk/efo/EFO_0000727 additional_host_information: string? - name: sampleSchema @@ -20,7 +26,10 @@ $graph: collecting_institution: string specimen_source: string? collection_date: string? - collection_location: string? + collection_location: + type: string? + jsonldPredicate: + _id: https://schema.org/fromLocation sample_storage_conditions: string? additional_collection_information: string? @@ -33,9 +42,18 @@ $graph: - name: technologySchema type: record fields: - sample_sequencing_technology: string - sequence_assembly_method: string? - sequencing_coverage: string? + sample_sequencing_technology: + type: string + jsonldPredicate: + _id: http://www.ebi.ac.uk/efo/EFO_0000532 + sequence_assembly_method: + type: string? + jsonldPredicate: + _id: http://www.ebi.ac.uk/efo/EFO_0002699 + sequencing_coverage: + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/FLU_0000848 - name: submitterSchema type: record -- cgit v1.2.3 From dbe094a150d6c969b3d69f112b3538e6a87a74a2 Mon Sep 17 00:00:00 2001 From: Peter Amstutz Date: Thu, 9 Apr 2020 15:59:46 -0400 Subject: Add "sequencefile" for the metadata subject. --- bh20sequploader/bh20seq-schema.yml | 13 ++++++++++++- example/metadata.yaml | 2 +- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'bh20sequploader/bh20seq-schema.yml') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index fd9e854..5c962d1 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -1,3 +1,8 @@ +$base: http://biohackathon.org/bh20-seq-schema +$namespaces: + sch: https://schema.org/ + efo: http://www.ebi.ac.uk/efo/ + obo: http://purl.obolibrary.org/obo/ $graph: - name: hostSchema @@ -75,4 +80,10 @@ $graph: sample: sampleSchema virus: virusSchema? technology: technologySchema - submitter: submitterSchema \ No newline at end of file + submitter: submitterSchema + sequencefile: + doc: The subject (eg the fasta/fastq file) that this metadata describes + type: string? + jsonldPredicate: + _id: "@id" + _type: "@id" diff --git a/example/metadata.yaml b/example/metadata.yaml index 8a93379..41ff93e 100644 --- a/example/metadata.yaml +++ b/example/metadata.yaml @@ -35,4 +35,4 @@ submitter: provider_sample_id: string submitter_sample_id: string authors: testAuthor - submitter_id: X12 \ No newline at end of file + submitter_id: X12 -- cgit v1.2.3