From 1b5df01d2047ab5c591f2e0400a5c46cb2dc86ea Mon Sep 17 00:00:00 2001 From: lltommy Date: Thu, 12 Nov 2020 14:22:08 +0100 Subject: Proposed new technology shape/yaml structure --- bh20sequploader/bh20seq-schema.yml | 9 +++++++-- bh20sequploader/bh20seq-shex.rdf | 7 ++++--- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 645be5e..2b36e99 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -191,11 +191,16 @@ $graph: _id: http://purl.obolibrary.org/obo/OBI_0600047 _type: "@id" noLinkCheck: true - sequence_assembly_method: + alignment_protocol: doc: Field for additional information on the pipeline applied to obtain the assembly type: string? jsonldPredicate: - _id: http://www.ebi.ac.uk/efo/EFO_0002699 + _id: http://www.ebi.ac.uk/efo/EFO_0004917 + assembly_method: + doc: Assembly method refers to how the reads were assembled into contigs for which either a de novo (http://purl.obolibrary.org/obo/GENEPIO_0001628) or mapping/reference based (http://purl.obolibrary.org/obo/GENEPIO_0002028) strategy is used. + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/GENEPIO_0000090 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: double[]? diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index 6e2493b..602f6a0 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -63,10 +63,11 @@ PREFIX wikidata: } :technologyShape { - obo:OBI_0600047 IRI {0,3} ; #(sample_sequencing_technology) sequencing assay, optional ???????????? - efo:EFO_0002699 xsd:string ?; #(sequence_assembly_method) high throughput sequencer, optional ????????????? + obo:OBI_0600047 IRI {1,3} ; #(sample_sequencing_technology), sequencing assay, optional + efo:EFO_0004917 xsd:string ; #(alignment_protocol), high throughput sequence alignment protocol, optional + obo:GENEPIO_0000090 [obo:GENEPIO_0001628 obo:GENEPIO_0002028 ] ? ; #(assembly method), assembly method, optional, one of the two obo:FLU_0000848 xsd:double OR xsd:integer {0,3}; #(sequence coverage) sequence coverage, optional - sio:SIO_001167 xsd:string ?; #(additional_technology_information), comment, optional, string + sio:SIO_001167 xsd:string ?; #(additional_technology_information), comment, optional, string } :virusShape{ -- cgit v1.2.3