gfvo_examples.ttl

@prefix : <http://www.biointerchange.org/gfvo#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix faldo: <http://biohackathon.org/resource/faldo#> .
@prefix so: <http://purl.bioontology.org/ontology/SO/SO> .

#################################################################
#
#    Example 1
#
#    Encoding loci and basic genomic feature annotations. The
#    example covers lines 0-3 of the example gene description
#    given in the GFF3 specification.
#           (http://www.sequenceontology.org/resources/gff3.html)
#
#    Please note that this seemingly verbose data representation
#    is slighly misleading. The reuse of non-literals as well as
#    binary RDF encodings such as RDF/HDT permits a more concise
#    representation of the same data.
#
#    This example also avoids blank nodes, so that this file can
#    be conveniently viewed using the Protege ontology editor.
#    Using blank nodes, the line
#
#        :hasIdentifier :ExampleSet1Feature1Identifier ;
#
#    can be substituted with
#
#        :hasIdentifier [
#            a :Identifier ;
#            :hasValue "gene00001" ;
#        ]
#
#################################################################

# This example is representing the contents of a GFF3 file, version 3.
:Example1Version a :Version ;
                 :hasValue "gff-version 3" .

# Two genomic features are described in the file, where an extra comment
# was added to clarify the provenance of this example representation.
:ExampleSet1 a :File ;
             :hasIdentifier :Example1Version ;
             :hasMember :ExampleSet1Feature1 ,
                        :ExampleSet1Feature2 ;
             rdfs:comment "A simple example of a hierarchical genomic feature dependency. This example is an excerpt of another example given in the GFF3 specification (http://sequenceontology.org/resources/gff3.html)."@en .

# Features in this example are placed on a single landmark, which has
# an identifier associated with it (it cannot be anonymous in GFF3, even
# though GFVO permits landmarks without explicit identifier), and it
# has a range of sequence positions it covers (expressed by a separate
# pragma statement in GFF3).
:ExampleSet1Landmark a :Landmark ;
                     :hasIdentifier :ExampleSet1LandmarkIdentifier ;
                     :hasAttribute :ExampleSet1LandmarkRegion .

:ExampleSet1LandmarkIdentifier a :Identifier ;
                               :hasValue "ctg123" .

:ExampleSet1LandmarkRegion a faldo:Region ;
                           faldo:begin :ExampleSet1LandmarkStartPosition ;
                           faldo:end :ExampleSet1LandmarkEndPosition .

:ExampleSet1LandmarkStartPosition a faldo:ExactPosition ;
                                  faldo:position 1 .

:ExampleSet1LandmarkEndPosition a faldo:ExactPosition ;
                                faldo:position 1497228 .

# GFF3, GTF and GVF make use of named attributes. There are predefined (reserved)
# names, but users can also freely contribute their own attributes. In this example,
# only one labeled attribute is used, whose name we define upfront.
#
# Note: It might be a bit confusing that the label "Name" is applied to an attribute
#       of type "Name". This is just an artifact of the chosen example and it is of
#       course possible to label a "Name" attribute arbitrarily.
:ExampleSet1AttributeName a :Label ;
                          :hasValue "Name" .

# First feature of the GFF3 file (line 2): a gene.
:ExampleSet1Feature1 a :Feature ,
                       so:0000704 ;
                     :isLocatedOn :ExampleSet1Landmark ;
                     :hasPart :ExampleSet1Feature1Locus ;
                     :hasIdentifier :ExampleSet1Feature1Identifier ;
                     :hasAttribute :ExampleSet1Feature1Name .

:ExampleSet1Feature1Locus a :Locus ;
                          :hasAttribute :ExampleSet1Feature1Region .

:ExampleSet1Feature1Region a faldo:Region ;
                           faldo:begin :ExampleSet1FeatureStartPosition ;
                           faldo:end :ExampleSet1Feature1EndPosition .

# The start coordinate of both features is the same in this example. So this
# entity is used by both :ExampleSet1Feature1 and :ExampleSet1Feature2.
:ExampleSet1FeatureStartPosition a faldo:ExactPosition ;
                                 faldo:position 1000 .

:ExampleSet1Feature1EndPosition a faldo:ExactPosition ;
                                faldo:position 9000 .

:ExampleSet1Feature1Identifier a :Identifier ;
                               :hasValue "gene00001" .

:ExampleSet1Feature1Name a :Name ;
                         :hasAttribute :ExampleSet1AttributeName ;
                         :hasValue "EDEN" .

# Second feature of the GFF3 file (line 3): a transcription factor
# binding site.
# It references the first feature via a "Parent" attribute.
:ExampleSet1Feature2 a :Feature ,
                       so:0000235 ;
                     :isLocatedOn :ExampleSet1Landmark ;
                     :hasPart :ExampleSet1Feature2Locus ;
                     :hasIdentifier :ExampleSet1Feature2Identifier ;
                     :hasSource :ExampleSet1Feature1 .

:ExampleSet1Feature2Locus a :Locus ;
                          :hasAttribute :ExampleSet1Feature1Region .

:ExampleSet1Feature2Region a faldo:Region ;
                           faldo:begin :ExampleSet1FeatureStartPosition ;
                           faldo:end :ExampleSet1Feature2EndPosition .

:ExampleSet1Feature2EndPosition a faldo:ExactPosition ;
                                faldo:position 1012 .

:ExampleSet1Feature2Identifier a :Identifier ;
                               :hasValue "tfbs00001" .

#################################################################
#
#    Example 2
#
#    Encoding of a sequence alignment. This is part of the GFF3
#    specification, denoting the alignment between the reference
#    sequence "chr3" and the target sequence "EST23".
#           (http://www.sequenceontology.org/resources/gff3.html)
#
#################################################################

:ExampleSet2 a :Collection ;
             :hasMember :ExampleSet2Feature1 ,
                        :ExampleSet2Feature2 ;
             rdfs:comment "An example of a sequence alignment. This example is an excerpt of another example given in the GFF3 specification (http://sequenceontology.org/resources/gff3.html)."@en .

:ExampleSet2Landmark a :Landmark ;
                     :hasIdentifier :ExampleSet2LandmarkIdentifier .

:ExampleSet2LandmarkIdentifier a :Identifier ;
                               :hasValue "chr3" .

# Reference sequence feature:
:ExampleSet2Feature1 a :Feature ;
                     :isLocatedOn :ExampleSet2Landmark ;
                     :hasIdentifier :ExampleSet2Feature1Identifier .

:ExampleSet1Feature1Identifier a :Identifier ;
                               :hasValue "Match1" .

# Target sequence feature:
:ExampleSet2Feature2 a :Feature ,
                       so:0000343 ;
                     :isLocatedOn :ExampleSet2Landmark ;
                     :hasIdentifier :ExampleSet2Feature2Identifier .

:ExampleSet1Feature2Identifier a :Identifier ;
                               :hasValue "EST23" .

# Description of the sequence alignment between :ExampleSet2Feature1
# and :ExampleSet2Feature2 (features "Match1" and "EST23").
:ExampleSet2SequenceAlignment a :SequenceAlignment ;
                              :hasAttribute :ExampleSet2AlignmentLocus ;
                              :hasSource :ExampleSet2Feature1 ;
                              :hasInput :ExampleSet2Feature2 ;
                              :hasFirstPart :ExampleSet2AlignmentOperation1 ;
                              :hasOrderedPart :ExampleSet2AlignmentOperation2 ,
                                              :ExampleSet2AlignmentOperation3 ,
                                              :ExampleSet2AlignmentOperation4 ;
                              :hasLastPart :ExampleSet2AlignmentOperation5 .

# The locus describes the region over which the alignment operation
# is being carried out.
:ExampleSet2AlignmentLocus a :Locus ;
                           :hasAttribute :ExampleSet2AlignmentRegion .

:ExampleSet2AlignmentRegion a faldo:Region ;
                            faldo:begin :ExampleSet2AlignmentStartPosition ;
                            faldo:end :ExampleSet2AlignmentEndPosition .

:ExampleSet2AlignmentStartPosition a faldo:ExactPosition ;
                                   faldo:position 1 .

:ExampleSet2AlignmentEndPosition a faldo:ExactPosition ;
                                 faldo:position 21 .

# Description of an actual alignment operation.
:ExampleSet2AlignmentOperation1 rdf:type :Match ;
                                :hasAttribute :ExampleSet2AlignmentOperation1Span ;
                                :isBefore :ExampleSet2AlignmentOperation2 .

:ExampleSet2AlignmentOperation1Span a :Span ;
                                    :hasValue 8 .

:ExampleSet2AlignmentOperation2 rdf:type :TargetSequenceGap ;
                                :hasAttribute :ExampleSet2AlignmentOperation2Span ;
                                :isAfter :ExampleSet2AlignmentOperation1 ;
                                :isBefore :ExampleSet2AlignmentOperation3 .

:ExampleSet2AlignmentOperation2Span a :Span ;
                                    :hasValue 3 .

:ExampleSet2AlignmentOperation3 rdf:type :Match ;
                                :hasAttribute :ExampleSet2AlignmentOperation3Span ;
                                :isAfter :ExampleSet2AlignmentOperation2 ;
                                :isBefore :ExampleSet2AlignmentOperation4 .

:ExampleSet2AlignmentOperation3Span a :Span ;
                                    :hasValue 6 .

:ExampleSet2AlignmentOperation4 rdf:type :ReferenceSequenceGap ;
                                :hasAttribute :ExampleSet2AlignmentOperation4Span ;
                                :isAfter :ExampleSet2AlignmentOperation3 ;
                                :isBefore :ExampleSet2AlignmentOperation5 .

:ExampleSet2AlignmentOperation4Span a :Span ;
                                    :hasValue 1 .

:ExampleSet2AlignmentOperation5 rdf:type :Match ;
                                :hasAttribute :ExampleSet2AlignmentOperation5Span ;
                                :isAfter :ExampleSet2AlignmentOperation4 .

:ExampleSet2AlignmentOperation5Span a :Span ;
                                    :hasValue 6 .

#################################################################
#
#    Example 3
#
#    Encoding of genotypes/sequence variants. This is part of the GVF
#    specification, denoting two variants for two separate
#    sequenced individuals: "Variant_seq=A,T;Genotype=0:1,1:1".
#    (See "Genotype" in the GVF specification at
#     http://www.sequenceontology.org/resources/gvf.html)
#
#################################################################

:ExampleSet3 a :Collection ;
             :hasMember :ExampleSet3Feature1 ;
             rdfs:comment "Encoding of genotypes/sequence variants. This example is part of the GVF specification, denoting two variants for two separate sequenced individuals (http://www.sequenceontology.org/resources/gvf.html)."@en .

# The individuals that were sequenced are represented by named, but otherwise
# unspecified, instances. This provides sufficient information to distinguish
# between the individuals that were sequenced.
:ExampleSet3SequencedIndividual1 rdf:type :SequencedIndividual .
:ExampleSet3SequencedIndividual2 rdf:type :SequencedIndividual .

# Genomic feature that captures the two described genotypes.
:ExampleSet3Feature1 a :Feature ;
                     :hasAttribute :ExampleSet3Genotype1 ,
                                   :ExampleSet3Genotype2 .

# Genotype for the first individual.
#
# The genotype's phased variants are linked via "hasFirstPart" and
# "hasLastPart" here, which are descendants of "hasOrderedPart".
# The object properties "isBefore"/"isAfter" connect the phased variants.
#
# Note: for an unphased genotype, it is sufficient to use "hasPart" only.
:ExampleSet3Genotype1 a :Genotype ;
                      :hasParticipant :ExampleSet3SequencedIndividual1 ;
                      :hasQuality :Heterozygous ;
                      :hasAttribute :ExampleSet3Phase ;
                      :hasFirstPart :ExampleSet3ReferenceA_AT ;
                      :hasLastPart :ExampleSet3VariantT_AT .

# Ordering of the variants permits the expression of phased genotypes.
# It is recommended to use "isBefore", but the use of "isAfter" is optional.
:ExampleSet3ReferenceA_AT :isBefore :ExampleSet3VariantT_AT .
:ExampleSet3VariantT_AT :isAfter :ExampleSet3ReferenceA_AT .

# Genotype of the second individual.
:ExampleSet3Genotype2 a :Genotype ;
                      :hasParticipant :ExampleSet3SequencedIndividual2 ;
                      :hasQuality :Homozygous ;
                      :hasAttribute :ExampleSet3Phase ;
                      :hasFirstPart :ExampleSet3VariantT_TT ;
                      :hasLastPart :ExampleSet3VariantT_TT .

# As above: variant ordering to phase the genotype.
:ExampleSet3VariantT_TT :isBefore :ExampleSet3VariantT_TT ;
                        :isAfter :ExampleSet3VariantT_TT .

# Having an instance to denote the presence of phase information
# might appear redundant across data sets. On the other hand, it
# permits data providers to enrich their own or other providers'
# data set with additional information (annotations) about used
# protocols/equipment/tools.
:ExampleSet3Phase a :GameticPhase .

# For VCF data, the type can also be "ReferenceSequence", which
# denotes that the sequence is located on a reference genome. This
# would be indicated -- in a VCF file -- by a "0" in the GT field
# (e.g., "0|1" (phased) or "0/1" (unphased) to indicate a genotype
# whose first allele is on the reference genome and the second allele
# is an alternative allele).
:ExampleSet3ReferenceA_AT a :ReferenceSequence ;
                          :hasValue "A" .

:ExampleSet3VariantT_AT a :SequenceVariant ;
                        :hasValue "T" .

:ExampleSet3VariantT_TT a :SequenceVariant ;
                        :hasValue "T" .

#################################################################
#
#    Example 4
#
#    Encoding of a Phred score. GVF leaves it open how the
#    "score" (column 6) should be interpreted, but recommends
#    the use of Phred scores. If a data provider knows that
#    a Phred score was utilized, then this can be represented
#    via GFVO.
#    (See "Column Descriptions" in the GVF specification at
#     http://www.sequenceontology.org/resources/gvf.html)
#
#################################################################

:ExampleSet4 a :Collection ;
             :hasMember :ExampleSet4Feature1 ;
             rdfs:comment "Encoding of a Phred score. This example is motivated by the GVF specification, which encourages -- but does not enforce -- the use of Phred scores (http://www.sequenceontology.org/resources/gvf.html)."@en .

# Interpreting "score" (column 6) of a GVF file as Phred score.
:ExampleSet4Feature1 a :Feature ;
                     :hasAttribute :ExampleSet4Feature1Score .

# Use of "PhredScore" instead of "Score" to denote the specific
# type of score being used.
:ExampleSet4Feature1Score a :PhredScore ;
                          :hasValue 38 .