From 6032a373003affa641ca1e70a44c29a232b5b3ed Mon Sep 17 00:00:00 2001 From: lltommy Date: Tue, 28 Apr 2020 20:31:42 +0200 Subject: Changes to the structure - we use lists now instead of strings where it makes sense. This allows us to have multiple values where in makes sense --- example/maximum_metadata_example.yaml | 44 +++++++++++++++++++++++++++++++++++ example/metadata.yaml | 43 ---------------------------------- example/minimal_example.yaml | 18 -------------- example/minimal_metadata_example.yaml | 0 4 files changed, 44 insertions(+), 61 deletions(-) create mode 100644 example/maximum_metadata_example.yaml delete mode 100644 example/metadata.yaml delete mode 100644 example/minimal_example.yaml create mode 100644 example/minimal_metadata_example.yaml (limited to 'example') diff --git a/example/maximum_metadata_example.yaml b/example/maximum_metadata_example.yaml new file mode 100644 index 0000000..0a6d910 --- /dev/null +++ b/example/maximum_metadata_example.yaml @@ -0,0 +1,44 @@ +id: placeholder + +host: + host_id: XX1 + host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606 + host_sex: http://purl.obolibrary.org/obo/PATO_0000384 + host_age: 20 + host_age_unit: http://purl.obolibrary.org/obo/UO_0000036 + host_health_status: http://purl.obolibrary.org/obo/NCIT_C25269 + host_treatment: Process in which the act is intended to modify or alter host status (Compounds) + host_vaccination: [vaccines1,vaccine2] + additional_host_information: Optional free text field for addtional information + +sample: + sample_id: Id of the sample as defined by the submitter + collector_name: Name of the person that took the sample + collecting_institution: Institute that was responsible of sampling + specimen_source: [http://purl.obolibrary.org/obo/NCIT_C155831,http://purl.obolibrary.org/obo/NCIT_C155835] + collection_date: "2020-01-01" + collection_location: http://www.wikidata.org/entity/Q148 + sample_storage_conditions: frozen specimen + source_database_accession: [http://identifiers.org/insdc/LC522350.1#sequence] + additional_collection_information: Optional free text field for addtional information + +virus: + virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049 + virus_strain: SARS-CoV-2/human/CHN/HS_8/2020 + +technology: + sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0009173,http://www.ebi.ac.uk/efo/EFO_0009173] + sequence_assembly_method: Protocol used for assembly + sequencing_coverage: [70, 100] + additional_technology_information: Optional free text field for addtional information + +submitter: + submitter_name: [John Doe] + submitter_address: John Doe's adress + originating_lab: John Doe kitchen + lab_address: John Doe's address + provider_sample_id: XXX1 + submitter_sample_id: XXX2 + authors: [John Doe, Joe Boe, Jonny Oe] + submitter_orcid: [https://orcid.org/0000-0000-0000-0000,https://orcid.org/0000-0000-0000-0001] + additional_submitter_information: Optional free text field for addtional information \ No newline at end of file diff --git a/example/metadata.yaml b/example/metadata.yaml deleted file mode 100644 index a76616c..0000000 --- a/example/metadata.yaml +++ /dev/null @@ -1,43 +0,0 @@ -id: placeholder - -host: - host_id: XX1 - host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606 - host_sex: http://purl.obolibrary.org/obo/NCIT_C27993 - host_age: 20 - host_age_unit: http://purl.obolibrary.org/obo/UO_0000036 - host_health_status: http://purl.obolibrary.org/obo/NCIT_C25269 - host_treatment: Process in which the act is intended to modify or alter host status (Compounds) - host_vaccination: List of vaccines given to the host (RRIDs?) - additional_host_information: Field for additional host information - -sample: - sample_id: Id of the sample as defined by the submitter - collector_name: Name of the person that took the sample - collecting_institution: Institute that was responsible of sampling - specimen_source: http://purl.obolibrary.org/obo/NCIT_C155831 - specimen_source2: http://purl.obolibrary.org/obo/NCIT_C155835 - collection_date: "2020-01-01" - collection_location: http://www.wikidata.org/entity/Q148 - sample_storage_conditions: XXX - additional_collection_information: XXX - -virus: - virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049 - virus_strain: SARS-CoV-2/human/CHN/HS_8/2020 - -technology: - sample_sequencing_technology: http://www.ebi.ac.uk/efo/EFO_0009173 - sample_sequencing_technology2: http://www.ebi.ac.uk/efo/EFO_0009173 - sequence_assembly_method: Protocol used for assembly - sequencing_coverage: 70 - -submitter: - submitter_name: John Doe - submitter_address: John Doe's adress - originating_lab: John Doe kitchen - lab_address: John Doe's address - provider_sample_id: HmX - submitter_sample_id: xXx - authors: John Doe et all - submitter_orcid: https://orcid.org/0000-0000-0000-0000 \ No newline at end of file diff --git a/example/minimal_example.yaml b/example/minimal_example.yaml deleted file mode 100644 index 0e36a25..0000000 --- a/example/minimal_example.yaml +++ /dev/null @@ -1,18 +0,0 @@ -id: placeholder - -host: - host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606 - -sample: - sample_id: XX - collection_date: 2020-01 - collection_location: http://www.wikidata.org/entity/Q148 - -virus: - virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049 - -technology: - sample_sequencing_technology: http://www.ebi.ac.uk/efo/EFO_0008632 - -submitter: - authors: John Doe \ No newline at end of file diff --git a/example/minimal_metadata_example.yaml b/example/minimal_metadata_example.yaml new file mode 100644 index 0000000..e69de29 -- cgit v1.2.3 From f795744116a9e86ab2a5c5e78761162e9d4ff7e0 Mon Sep 17 00:00:00 2001 From: lltommy Date: Tue, 28 Apr 2020 20:43:03 +0200 Subject: Adding field 'publication' to the maximum example --- example/maximum_metadata_example.yaml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'example') diff --git a/example/maximum_metadata_example.yaml b/example/maximum_metadata_example.yaml index 0a6d910..260e4e4 100644 --- a/example/maximum_metadata_example.yaml +++ b/example/maximum_metadata_example.yaml @@ -33,12 +33,13 @@ technology: additional_technology_information: Optional free text field for addtional information submitter: + authors: [John Doe, Joe Boe, Jonny Oe] submitter_name: [John Doe] submitter_address: John Doe's adress originating_lab: John Doe kitchen lab_address: John Doe's address provider_sample_id: XXX1 submitter_sample_id: XXX2 - authors: [John Doe, Joe Boe, Jonny Oe] + publication: PMID00001113 submitter_orcid: [https://orcid.org/0000-0000-0000-0000,https://orcid.org/0000-0000-0000-0001] additional_submitter_information: Optional free text field for addtional information \ No newline at end of file -- cgit v1.2.3 From b4ec03398d5e74eeb33a4a2a396fe4518c0c5465 Mon Sep 17 00:00:00 2001 From: lltommy Date: Tue, 28 Apr 2020 20:48:42 +0200 Subject: Whatever happend to the minimal metadata, I restored it --- example/minimal_metadata_example.yaml | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'example') diff --git a/example/minimal_metadata_example.yaml b/example/minimal_metadata_example.yaml index e69de29..1e8d3f5 100644 --- a/example/minimal_metadata_example.yaml +++ b/example/minimal_metadata_example.yaml @@ -0,0 +1,18 @@ +id: placeholder + +host: + host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606 + +sample: + sample_id: XX + collection_date: 2020-01 + collection_location: http://www.wikidata.org/entity/Q148 + +virus: + virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049 + +technology: + sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632] + +submitter: + authors: [John Doe] \ No newline at end of file -- cgit v1.2.3 From ceb34edf0449cca328dfe8cf61277d7f05ea7cf9 Mon Sep 17 00:00:00 2001 From: lltommy Date: Tue, 28 Apr 2020 22:09:37 +0200 Subject: Decision to settle for float instead of integers for the coverage --- bh20sequploader/bh20seq-schema.yml | 2 +- bh20sequploader/bh20seq-shex.rdf | 2 +- example/maximum_metadata_example.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'example') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index f36a6e6..d3e992a 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -152,7 +152,7 @@ $graph: _id: http://www.ebi.ac.uk/efo/EFO_0002699 sequencing_coverage: doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. [100]) - if multiple technologies were used multiple float values can be submitted e.g. [100, 20] - type: int[]? + type: float[]? jsonldPredicate: _id: http://purl.obolibrary.org/obo/FLU_0000848 additional_technology_information: diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index 4ec957d..fe6deee 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -57,7 +57,7 @@ PREFIX wikidata: :technologyShape { obo:OBI_0600047 IRI {0,3} ; efo:EFO_0002699 xsd:string ?; - obo:FLU_0000848 xsd:integer {0,2}; + obo:FLU_0000848 xsd:float {0,3}; sio:SIO_001167 xsd:string ?; } diff --git a/example/maximum_metadata_example.yaml b/example/maximum_metadata_example.yaml index 260e4e4..0ba9ada 100644 --- a/example/maximum_metadata_example.yaml +++ b/example/maximum_metadata_example.yaml @@ -29,7 +29,7 @@ virus: technology: sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0009173,http://www.ebi.ac.uk/efo/EFO_0009173] sequence_assembly_method: Protocol used for assembly - sequencing_coverage: [70, 100] + sequencing_coverage: [70.0, 100.0] additional_technology_information: Optional free text field for addtional information submitter: -- cgit v1.2.3 From 5c05facbdb1e35556256cd11d6a814822ebb6159 Mon Sep 17 00:00:00 2001 From: lltommy Date: Thu, 30 Apr 2020 18:00:58 +0200 Subject: Last addition/edits to the meta data schema --- bh20sequploader/bh20seq-schema.yml | 15 ++++++++++++--- bh20sequploader/bh20seq-shex.rdf | 5 +++-- example/maximum_metadata_example.yaml | 1 + example/minimal_metadata_example.yaml | 2 +- 4 files changed, 17 insertions(+), 6 deletions(-) (limited to 'example') diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index d3e992a..99e1a11 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -49,6 +49,7 @@ $graph: jsonldPredicate: _id: http://purl.obolibrary.org/obo/NCIT_C25688 _type: "@id" + noLinkCheck: true host_treatment: doc: Process in which the act is intended to modify or alter host status type: string? @@ -59,6 +60,13 @@ $graph: type: string[]? jsonldPredicate: _id: http://purl.obolibrary.org/obo/VO_0000002 + ethnicity: + doc: Ethinicity of the host e.g. http://purl.obolibrary.org/obo/HANCESTRO_0010 + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001014 + _type: "@id" + noLinkCheck: true additional_host_information: doc: Field for additional host information type: string? @@ -91,7 +99,7 @@ $graph: jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0001895 collecting_institution: - doc: Institute that was responsible of sampeling + doc: Institute that was responsible for sampeling type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/NCIT_C41206 @@ -118,12 +126,13 @@ $graph: jsonldPredicate: _id: http://edamontology.org/data_2091 _type: "@id" + noLinkCheck: true - name: virusSchema type: record fields: virus_species: - doc: The name of a taxon from the NCBI taxonomy database + doc: The name of virus species from the NCBI taxonomy database, e.g. http://purl.obolibrary.org/obo/NCBITaxon_2697049 for Severe acute respiratory syndrome coronavirus 2 type: string jsonldPredicate: _id: http://edamontology.org/data_1875 @@ -152,7 +161,7 @@ $graph: _id: http://www.ebi.ac.uk/efo/EFO_0002699 sequencing_coverage: doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. [100]) - if multiple technologies were used multiple float values can be submitted e.g. [100, 20] - type: float[]? + type: double[]? jsonldPredicate: _id: http://purl.obolibrary.org/obo/FLU_0000848 additional_technology_information: diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index fe6deee..cdf2296 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -27,6 +27,7 @@ PREFIX wikidata: efo:EFO_0000727 xsd:string ?; obo:VO_0000002 xsd:string {0,10}; sio:SIO_001167 xsd:string ?; + sio:SIO_001014 [ obo:HANCESTRO_~ ] ? ; #ethnicity } :sampleShape { @@ -42,7 +43,7 @@ PREFIX wikidata: } :submitterShape { - obo:NCIT_C42781 xsd:string * ; + obo:NCIT_C42781 xsd:string + ; sio:SIO_000116 xsd:string *; sio:SIO_000172 xsd:string ?; obo:NCIT_C37984 xsd:string ?; @@ -57,7 +58,7 @@ PREFIX wikidata: :technologyShape { obo:OBI_0600047 IRI {0,3} ; efo:EFO_0002699 xsd:string ?; - obo:FLU_0000848 xsd:float {0,3}; + obo:FLU_0000848 xsd:double OR xsd:integer {0,3}; sio:SIO_001167 xsd:string ?; } diff --git a/example/maximum_metadata_example.yaml b/example/maximum_metadata_example.yaml index 0ba9ada..1bc70d7 100644 --- a/example/maximum_metadata_example.yaml +++ b/example/maximum_metadata_example.yaml @@ -9,6 +9,7 @@ host: host_health_status: http://purl.obolibrary.org/obo/NCIT_C25269 host_treatment: Process in which the act is intended to modify or alter host status (Compounds) host_vaccination: [vaccines1,vaccine2] + ethnicity: http://purl.obolibrary.org/obo/HANCESTRO_0010 additional_host_information: Optional free text field for addtional information sample: diff --git a/example/minimal_metadata_example.yaml b/example/minimal_metadata_example.yaml index 1e8d3f5..51f8a87 100644 --- a/example/minimal_metadata_example.yaml +++ b/example/minimal_metadata_example.yaml @@ -5,7 +5,7 @@ host: sample: sample_id: XX - collection_date: 2020-01 + collection_date: "2020-01-01" collection_location: http://www.wikidata.org/entity/Q148 virus: -- cgit v1.2.3