-EJP-RD-LOVD ShEx Validation Manifest.md

the manifest can be used in:

• ShEx.JS shex-simple interface

using the rawlink address

.manifest.yaml

- schemaLabel: some example schema
  schemaURL: example.shex
  dataLabel: and example data
  dataURL: example.ttl
  queryMap: |-
    <https://databases.lovd.nl/shared/variants/0000001345#00000064>@<#VariantOnTranscription>,
    <https://databases.lovd.nl/shared/variants/0000001344#00000064>@<#VariantOnTranscription>,
    <https://databases.lovd.nl/shared/variants/0000001345#vog>@<#VariantOnGenome>,
    <https://databases.lovd.nl/shared/variants/0000001344#vog>@<#VariantOnGenome>,
    <https://databases.lovd.nl/shared/variants/0000001345>@<#GeneticMeasurementOutput>,
    <https://databases.lovd.nl/shared/variants/0000001344>@<#GeneticMeasurementOutput>,
    <https://databases.lovd.nl/shared/screenings/0000000117#genotype>@<#GenotypeAttribute>,
    <https://databases.lovd.nl/shared/screenings/0000000117>@<#GeneticMeasurementProcess>,
    indiv:diagnosis@<#DiagnosisAttribute>,
    indiv:findings@<#DiagnosisMeasurementOutput>,
    indiv:examination@<#DiagnosisMeasurementProcess>,
    indiv:role@<#PatientRoleShape>,
    <https://databases.lovd.nl/shared/individuals/00000125>@<#PersonShape>,
    indiv:identifier@<#PatientIdentifierShape>,
  status: conformant

example.shex

PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX indiv: <https://databases.lovd.nl/shared/individuals/00000125#>
PREFIX sio: <https://sio.semanticscience.org/resource/SIO_>
PREFIX ncit: <http://purl.obolibrary.org/obo/NCIT_>

<#PatientIdentifierShape> CLOSED {
                         a          [sio:000115];   # identifier
                         rdfs:label ["Identifier"]?;
  /*denotes           */ sio:000020 @<#PatientRoleShape>;
  /*has value         */ sio:000300 /[0-9]+/
}

<#PersonShape> CLOSED {
                         a          [sio:000498];  # person
                         rdfs:label ["Person"]?;
  /*has identifier    */ sio:000671 @<#PatientIdentifierShape>;
  /*has role          */ sio:000228 @<#PatientRoleShape>;
  /*has attribute     */ sio:000008 @<#DiagnosisMeasurementProcess>;
                         sio:000008 @<#GenotypeAttribute>+
}

<#PatientRoleShape> CLOSED {
                         a          [sio:000016];  # role
                         a          [<http://purl.obolibrary.org/obo/OBI_0000093>];
                         rdfs:label ["Patient role"];
  /*is realized in    */ sio:000356 @<#DiagnosisMeasurementProcess>;
                         sio:000356 @<#GeneticMeasurementProcess>
}

<#DiagnosisMeasurementProcess> CLOSED {
                         a          [sio:000006];  # process
                         a          [ncit:C15220]; # Diagnosis
                         rdfs:label ["Diagnosis measurement process"];
  /*has output        */ sio:000229 @<#DiagnosisMeasurementOutput>
}

<#DiagnosisMeasurementOutput> CLOSED {
                         a          [ncit:C70856]; # Observation Result
                         a          [sio:000015];  # information content entity
                         rdfs:label ["Diagnosis measurement output"];
  /*refers to         */ sio:000628 @<#DiagnosisAttribute>
}

<#DiagnosisAttribute> CLOSED {
                         a          [sio:000614];  # attribute
                         a          [<https://www.omim.org/entry/243500>];
                         rdfs:label ["Diagnosis attribute"];
  /*is about          */ sio:000332 [ncit:C2991] # Disease or Disorder
}

<#GeneticMeasurementProcess> CLOSED {
                         a          [sio:000006];  # process
                         a          [ncit:C15709]; # Genetic Testing
                         rdfs:label ["Genetic measurement process"];
  /*has participant   */ sio:000132 IRI; # should a regex enforce this as a HUGO URL?
  /*has input         */ sio:000230 [sio:010010]; # deoxyribonucleic acid
                         sio:000230 [sio:010450]; # RNA transcript
  /*has output        */ sio:000229 @<#GeneticMeasurementOutput>+
}

<#GenotypeAttribute> CLOSED {
                         a          [sio:000614];
                         a          [ncit:C103223]; # Genetic Finding
                         rdfs:label ["Genetic attribute"]
}

<#GeneticMeasurementOutput> CLOSED {
                         a          [sio:000015];  # information content entity
                         a          [ncit:C45766]; # Genomic Identifier
                         rdfs:label ["Genetic measurement output"];
  /*refers to         */ sio:000628 @<#GenotypeAttribute>;
  /*has part          */ sio:000028 @<#VariantOnGenome>;
                         sio:000028 @<#VariantOnTranscription>
}

<#VariantOnGenome> CLOSED {
                         a          [sio:000015];   # information content entity
                         a          [ncit:C172243]; # HGVS Genomic Variation Annotation
  /*has value         */ sio:000300 /NC_[0-9]+\.[0-9]:g\.[0-9]+G>A/
}

<#VariantOnTranscription> CLOSED {
                         a          [sio:000015];   # information content entity
                         a          [ncit:C172244]; # HGVS Transcript Variation Annotation
  /*Gene identifier   */ ncit:C48664 IRI; # HUGO URL?
  /*Gene symbol       */ ncit:C43568 ["IVD"];
  /*NCBI transcript ID*/ ncit:C171335 /NM_[0-9]+\.[0-9]/;
  /*has value         */ sio:000300 /NM_[0-9]+\.[0-9]:[c]\.[0-9]{3}(\+1G>A)?/
}

example.ttl

PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX indiv: <https://databases.lovd.nl/shared/individuals/00000125#>
PREFIX sio: <https://sio.semanticscience.org/resource/SIO_>
PREFIX ncit: <http://purl.obolibrary.org/obo/NCIT_>

# Example TTL file, based on https://databases.lovd.nl/shared/individuals/00000125.
# This Identifier is an Identifier;
indiv:identifier a sio:000115;
  # has label "Identifier";
  rdfs:label "Identifier";
  # denotes a Role;
  sio:000020 indiv:role;
  # has value "00000125".
  sio:000300 "00000125" .

# This Individual is a Person;
<https://databases.lovd.nl/shared/individuals/00000125> a sio:000498;
  # has label "Person";
  rdfs:label "Person";
  # has an identifier;
  sio:000671 indiv:identifier;
  # has a Role;
  sio:000228 indiv:role;
  # has attributes Examination and Genotype.
  sio:000008 indiv:examination,
    <https://databases.lovd.nl/shared/screenings/0000000117#genotype> .

# This Role is a Role and a Patient role;
indiv:role a sio:000016,
    <http://purl.obolibrary.org/obo/OBI_0000093>;
  # has label "Patient role";
  rdfs:label "Patient role";
  # is realized in Examination and Screening.
  sio:000356 indiv:examination,
    <https://databases.lovd.nl/shared/screenings/0000000117> .

# Examination. This is the "Diagnosis measurement process".
# This Examination is a Process and a Diagnosis; (I don't agree with the latter; it would better be described as a "Diagnostic procedure" (http://purl.obolibrary.org/obo/NCIT_C18020).)
indiv:examination a sio:000006,
    ncit:C15220;
  # has label "Diagnosis measurement process";
  rdfs:label "Diagnosis measurement process";
  # has output Findings.
  sio:000229 indiv:findings .

# Findings. This is the "Diagnosis output".
# There are actually no values here. There are units and frequency, but it's not clear what we can store here.
# These Findings are an Observation result and an Information content entity;
indiv:findings a ncit:C70856,
    sio:000015;
  # has label "Diagnosis measurement output";
  rdfs:label "Diagnosis measurement output";
  # refers to Diagnosis.
  sio:000628 indiv:diagnosis .

# Diagnosis. This is the "Diagnosis attribute".
# Diagnosis is a Attribute and Isovaleric acidemia;
indiv:diagnosis a sio:000614,
    <https://www.omim.org/entry/243500>;
  # has label "Diagnosis attribute";
  rdfs:label "Diagnosis attribute";
  # is about Disease or disorder.
  sio:000332 ncit:C2991 .

# Screening. This is the "Genotype measurement process".
# This Screening is a Process and a Genetic Testing;
<https://databases.lovd.nl/shared/screenings/0000000117> a sio:000006,
    ncit:C15709;
  # has label "Genetic measurement process";
  rdfs:label "Genetic measurement process";
  # has participant IVD gene; (this was added by me; I am trying to explain genes are screened and couldn't find a better relationship than participant; the example data uses SIO_000229, has_output, which makes no sense at all.)
  sio:000132 <https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:6186>;
  # has input DNA and RNA;
  sio:000230 sio:010010,
    sio:010450;
  # has output Variants.
  sio:000229 <https://databases.lovd.nl/shared/variants/0000001344>,
    <https://databases.lovd.nl/shared/variants/0000001345> .

# Genotype. This is the "Genotype attribute". There is actually no data here, so what is the sense?
# This Genotype is an Attribute and a Genetic finding.
<https://databases.lovd.nl/shared/screenings/0000000117#genotype> a sio:000614,
    ncit:C103223;
  # has label "Genetic attribute".
  rdfs:label "Genetic attribute".

# Genetic code. This doesn't seem to have a name in the graph, it's merely described as "HGVS/OMIM/HGNC genetic code".
# This Genetic code is an Information content entity and a Genomic identifier;
<https://databases.lovd.nl/shared/variants/0000001344> a sio:000015,
    ncit:C45766;
  # has label "Genetic measurement output";
  rdfs:label "Genetic measurement output";
  # refers to Genotype; (I don't know why, because Genotype doesn't contain any data.)
  sio:000628 <https://databases.lovd.nl/shared/screenings/0000000117#genotype>;
  # has part VOG + VOTs. I added this myself, as I don't want to add loose values.
  sio:000028 <https://databases.lovd.nl/shared/variants/0000001344#vog>,
    <https://databases.lovd.nl/shared/variants/0000001344#00000064> .

# VOG (added by me).
# This VOG is an Information content entity and HGVS Genomic Variation Annotation;
<https://databases.lovd.nl/shared/variants/0000001344#vog> a sio:000015,
    ncit:C172243;
  # has value "NC_000015.9:g.40702997G>A".
  sio:000300 "NC_000015.9:g.40702997G>A" .

# VOT (added by me).
# This VOT is an Information content entity and HGVS Transcript Variation Annotation;
<https://databases.lovd.nl/shared/variants/0000001344#00000064> a sio:000015,
    ncit:C172244;
  # Gene identifier;
  ncit:C48664 <https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:6186>;
  # Gene symbol;
  ncit:C43568 "IVD";
  # NCBI transcript identifier;
  ncit:C171335 "NM_002225.3";
  # has value "NM_002225.3:c.465+1G>A".
  sio:000300 "NM_002225.3:c.465+1G>A" .

# Genetic code. This doesn't seem to have a name in the graph, it's merely described as "HGVS/OMIM/HGNC genetic code".
# This Genetic code is an Information content entity and a Genomic identifier;
<https://databases.lovd.nl/shared/variants/0000001345> a sio:000015,
    ncit:C45766;
  # has label "Genetic measurement output";
  rdfs:label "Genetic measurement output";
  # refers to Genotype; (I don't know why, because Genotype doesn't contain any data.)
  sio:000628 <https://databases.lovd.nl/shared/screenings/0000000117#genotype>;
  # has part VOG + VOTs. I added this myself, as I don't want to add loose values.
  sio:000028 <https://databases.lovd.nl/shared/variants/0000001345#vog>,
    <https://databases.lovd.nl/shared/variants/0000001345#00000064> .

# VOG (added by me).
# This VOG is an Information content entity and HGVS Genomic Variation Annotation;
<https://databases.lovd.nl/shared/variants/0000001345#vog> a sio:000015,
    ncit:C172243;
  # has value "NC_000015.9:g.40699897G>A".
  sio:000300 "NC_000015.9:g.40699897G>A" .

# VOT (added by me).
# This VOT is an Information content entity and HGVS Transcript Variation Annotation;
<https://databases.lovd.nl/shared/variants/0000001345#00000064> a sio:000015,
    ncit:C172244;
  # Gene identifier;
  ncit:C48664 <https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:6186>;
  # Gene symbol;
  ncit:C43568 "IVD";
  # NCBI transcript identifier;
  ncit:C171335 "NM_002225.3";
  # has value "NM_002225.3:c.214G>A".
  sio:000300 "NM_002225.3:c.214G>A" .

# FIXME: Classification? Effect?

  # affects: http://semanticscience.org/resource/SIO_001158
  # function: http://semanticscience.org/resource/SIO_000017