From 5b1c62fd359f6f12db7042d61b8af69ca3e2343a Mon Sep 17 00:00:00 2001 From: Munyoki Kilyungi Date: Fri, 30 Jan 2026 00:47:26 +0300 Subject: Rename {genotype,molecular-traits}.scm. Signed-off-by: Munyoki Kilyungi --- examples/genotype-datasets.scm | 74 ++++++++++++++++++++ examples/genotype.scm | 74 -------------------- examples/molecular-traits-datasets.scm | 123 +++++++++++++++++++++++++++++++++ examples/molecular-traits.scm | 123 --------------------------------- 4 files changed, 197 insertions(+), 197 deletions(-) create mode 100755 examples/genotype-datasets.scm delete mode 100755 examples/genotype.scm create mode 100755 examples/molecular-traits-datasets.scm delete mode 100755 examples/molecular-traits.scm (limited to 'examples') diff --git a/examples/genotype-datasets.scm b/examples/genotype-datasets.scm new file mode 100755 index 0000000..f140600 --- /dev/null +++ b/examples/genotype-datasets.scm @@ -0,0 +1,74 @@ +#! /usr/bin/env guile +!# + +(use-modules (rnrs programs) + (rnrs io ports) + (srfi srfi-1) + (srfi srfi-26) + (ice-9 getopt-long) + (ice-9 match) + (ice-9 regex) + (transform strings) + (transform sql) + (transform triples) + (transform special-forms)) + + +(define-transformer gn:set->gn:dataset + (tables (Datasets + (inner-join InfoFiles "ON InfoFiles.DatasetId = Datasets.DatasetId") + (inner-join InbredSet "ON InbredSet.Id = InfoFiles.InbredSetId") + (inner-join GenoFreeze "ON GenoFreeze.InbredSetId = InbredSet.Id")) + "WHERE GenoFreeze.public > 0 GROUP BY Datasets.DatasetId") + (schema-triples + (gnt:has_genotype_data rdf:type owl:ObjectProperty) + (gnt:has_genotype_data rdfs:label "this resources has genotype data.") + (gnt:has_genotype_data rdfs:comment "Associates a resource with its genotype data.") + (gnt:has_genotype_data rdfs:domain gnc:set) + (gnt:has_genotype_data rdfs:range dcat:Dataset) + (gnt:has_genotype_data rdfs:subPropertyOf dct:relation)) + (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_") + (set gnt:has_genotype_data (string->identifier "dataset" (field GenoFreeze Name) #:separator "_")))) + +(define-transformer gn:dataset->gn:set + (tables (Datasets + (inner-join InfoFiles "ON InfoFiles.DatasetId = Datasets.DatasetId") + (inner-join InbredSet "ON InbredSet.Id = InfoFiles.InbredSetId") + (inner-join GenoFreeze "ON GenoFreeze.InbredSetId = InbredSet.Id")) + "WHERE GenoFreeze.public > 0 GROUP BY Datasets.DatasetId") + (triples (string->identifier "dataset" (field GenoFreeze Name) #:separator "_") + (set gnt:has_strain (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_")))) + + +(let* ((option-spec + '((settings (single-char #\s) (value #t)) + (output (single-char #\o) (value #t)) + (documentation (single-char #\d) (value #t)))) + (options (getopt-long (command-line) option-spec)) + (settings (option-ref options 'settings #f)) + (output (option-ref options 'output #f)) + (documentation (option-ref options 'documentation #f)) + (%connection-settings + (call-with-input-file settings + read))) + (with-documentation + (name "Genotype Datasets") + (connection %connection-settings) + (table-metadata? #f) + (prefixes + '(("dcat:" "") + ("dct:" "") + ("gn:" "") + ("gnc:" "") + ("gnt:" "") + ("rdf:" "") + ("rdfs:" "") + ("owl:" "") + ("skos:" "") + ("xkos:" "") + ("xsd:" ""))) + (inputs + (list gn:set->gn:dataset gn:dataset->gn:set)) + (outputs + `(#:documentation ,documentation + #:rdf ,output)))) diff --git a/examples/genotype.scm b/examples/genotype.scm deleted file mode 100755 index f140600..0000000 --- a/examples/genotype.scm +++ /dev/null @@ -1,74 +0,0 @@ -#! /usr/bin/env guile -!# - -(use-modules (rnrs programs) - (rnrs io ports) - (srfi srfi-1) - (srfi srfi-26) - (ice-9 getopt-long) - (ice-9 match) - (ice-9 regex) - (transform strings) - (transform sql) - (transform triples) - (transform special-forms)) - - -(define-transformer gn:set->gn:dataset - (tables (Datasets - (inner-join InfoFiles "ON InfoFiles.DatasetId = Datasets.DatasetId") - (inner-join InbredSet "ON InbredSet.Id = InfoFiles.InbredSetId") - (inner-join GenoFreeze "ON GenoFreeze.InbredSetId = InbredSet.Id")) - "WHERE GenoFreeze.public > 0 GROUP BY Datasets.DatasetId") - (schema-triples - (gnt:has_genotype_data rdf:type owl:ObjectProperty) - (gnt:has_genotype_data rdfs:label "this resources has genotype data.") - (gnt:has_genotype_data rdfs:comment "Associates a resource with its genotype data.") - (gnt:has_genotype_data rdfs:domain gnc:set) - (gnt:has_genotype_data rdfs:range dcat:Dataset) - (gnt:has_genotype_data rdfs:subPropertyOf dct:relation)) - (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_") - (set gnt:has_genotype_data (string->identifier "dataset" (field GenoFreeze Name) #:separator "_")))) - -(define-transformer gn:dataset->gn:set - (tables (Datasets - (inner-join InfoFiles "ON InfoFiles.DatasetId = Datasets.DatasetId") - (inner-join InbredSet "ON InbredSet.Id = InfoFiles.InbredSetId") - (inner-join GenoFreeze "ON GenoFreeze.InbredSetId = InbredSet.Id")) - "WHERE GenoFreeze.public > 0 GROUP BY Datasets.DatasetId") - (triples (string->identifier "dataset" (field GenoFreeze Name) #:separator "_") - (set gnt:has_strain (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_")))) - - -(let* ((option-spec - '((settings (single-char #\s) (value #t)) - (output (single-char #\o) (value #t)) - (documentation (single-char #\d) (value #t)))) - (options (getopt-long (command-line) option-spec)) - (settings (option-ref options 'settings #f)) - (output (option-ref options 'output #f)) - (documentation (option-ref options 'documentation #f)) - (%connection-settings - (call-with-input-file settings - read))) - (with-documentation - (name "Genotype Datasets") - (connection %connection-settings) - (table-metadata? #f) - (prefixes - '(("dcat:" "") - ("dct:" "") - ("gn:" "") - ("gnc:" "") - ("gnt:" "") - ("rdf:" "") - ("rdfs:" "") - ("owl:" "") - ("skos:" "") - ("xkos:" "") - ("xsd:" ""))) - (inputs - (list gn:set->gn:dataset gn:dataset->gn:set)) - (outputs - `(#:documentation ,documentation - #:rdf ,output)))) diff --git a/examples/molecular-traits-datasets.scm b/examples/molecular-traits-datasets.scm new file mode 100755 index 0000000..77bba08 --- /dev/null +++ b/examples/molecular-traits-datasets.scm @@ -0,0 +1,123 @@ +#! /usr/bin/env guile +!# + +(use-modules (srfi srfi-1) + (srfi srfi-26) + (ice-9 getopt-long) + (ice-9 match) + (ice-9 regex) + (transform strings) + (transform sql) + (transform triples) + (transform special-forms)) + + +(define-transformer gn:molecular-trait->gn:dataset + (tables (Tissue)) + (schema-triples + (gnc:molecular_trait a owl:Class) + (gnc:molecular_trait a skos:Concept) + (gnc:molecular_trait rdfs:subClassOf obo:UBERON_0000479) + (gnc:molecular_trait rdfs:label "Molecular Trait. This describes a melecular trait of a given species. We combine the species name and the tissue name in order to differentiate the traits across different inbredset groups.")) + (triples (string->identifier "trait" (field Tissue Short_Name) #:separator "_") + (set rdf:type 'gnc:molecular_trait) + (set skos:prefLabel (field Tissue Name)) + (set skos:altLabel (field Tissue Short_Name)))) + +(define-transformer gnc:molecular_trait->gn:molecular_trait + (tables (Tissue)) + (triples "gnc:molecular_trait" + (set skos:member (string->identifier "trait" (field Tissue Short_Name) #:separator "_")))) + +(define-transformer gn:set->gn:dataset + (tables (Species + (inner-join InbredSet "ON InbredSet.SpeciesId = Species.Id") + (inner-join ProbeFreeze "ON ProbeFreeze.InbredSetId = InbredSet.Id") + (inner-join ProbeSetFreeze "ON ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id") + (inner-join Tissue "ON ProbeFreeze.TissueId = Tissue.Id")) + "WHERE ProbeSetFreeze.public > 0 AND Species.Name != 'monkey' GROUP BY Species.Name, Tissue.Short_Name") + (schema-triples + (gnt:has_probeset_data rdf:type owl:ObjectProperty) + (gnt:has_probeset_data rdfs:label "this resources has this probeset data.") + (gnt:has_probeset_data rdfs:comment "Associates a resource with this probeset data.") + (gnt:has_probeset_data rdfs:domain gnc:set) + (gnt:has_probeset_data rdfs:range gnc:molecular_trait) + (gnt:has_probeset_data rdfs:subPropertyOf dct:relation)) + (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_") + (multiset gnt:has_probeset_data + (map (cut string->identifier "dataset" <> #:separator "_") + (string-split + (field ("GROUP_CONCAT(ProbeSetFreeze.Name SEPARATOR ',')" + dataset_name)) + #\,))))) + +(define-transformer gn:dataset->metadata + (tables (ProbeSetFreeze + (inner-join ProbeFreeze "ON ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id") + (inner-join InbredSet "ON InbredSet.Id = ProbeFreeze.InbredSetId") + (inner-join Species "ON InbredSet.SpeciesId = Species.Id") + (inner-join Tissue "ON ProbeFreeze.TissueId = Tissue.Id") + (inner-join AvgMethod "ON AvgMethod.AvgMethodId = ProbeSetFreeze.AvgID") + (inner-join InfoFiles "ON InfoFiles.InfoPageName = ProbeSetFreeze.Name") + (inner-join Datasets "ON InfoFiles.DatasetId = Datasets.DatasetId") + (left-join GeneChip "ON GeneChip.Id = InfoFiles.GeneChipId")) + "WHERE ProbeSetFreeze.public > 0 AND Species.Name != 'monkey'") + (schema-triples + (gnt:has_molecular_trait rdf:type owl:ObjectProperty) + (gnt:has_molecular_trait rdfs:domain gnc:set) + (gnt:has_molecular_trait rdfs:range gnc:molecular_trait) + (gnt:has_molecular_trait rdfs:label "has molecular trait") + (gnt:uses_genechip a owl:ObjectProperty) + (gnt:uses_genechip rdfs:domain dcat:Dataset) + (gnt:uses_genechip skos:definition "The Platform this resource uses..") + (gnt:uses_normalization_method rdfs:comment "The normalization method used for the molecular traits in this dataset") + (gnt:uses_normalization_method rdfs:domain dcat:Dataset) + (gnt:uses_normalization_method rdfs:label "Averaging method used for the molecular traits in this dataset.") + (gnt:uses_normalization_method rdfs:range gnc:avg_method)) + (triples (string->identifier "dataset" (field ProbeSetFreeze Name) #:separator "_") + (set dct:created (annotate-field (field ProbeSetFreeze CreateTime) '^^xsd:datetime)) + (set gnt:uses_normalization_method + (string->identifier "avg_method" (field AvgMethod Name AvgMethodName) #:separator "_")) + (set gnt:has_molecular_trait + (string->identifier "trait" (field Tissue Short_Name) #:separator "_")) + (set gnt:uses_genechip + (string->identifier "platform" (field GeneChip Name) #:separator "_")))) + + +(let* ((option-spec + '((settings (single-char #\s) (value #t)) + (output (single-char #\o) (value #t)) + (documentation (single-char #\d) (value #t)))) + (options (getopt-long (command-line) option-spec)) + (settings (option-ref options 'settings #f)) + (output (option-ref options 'output #f)) + (documentation (option-ref options 'documentation #f)) + (%connection-settings + (call-with-input-file settings + read))) + (with-documentation + (name "Molecular Trait Datasets") + (connection %connection-settings) + (table-metadata? #f) + (prefixes + '(("dcat:" "") + ("gn:" "") + ("obo:" "") + ("owl:" "") + ("xsd:" "") + ("dct:" "") + ("xkos:" "") + ("gnt:" "") + ("skos:" "") + ("gnc:" "") + ("rdf:" "") + ("rdfs:" ""))) + (inputs + (list + gn:dataset->metadata + gn:molecular-trait->gn:dataset + gn:set->gn:dataset + gnc:molecular_trait->gn:molecular_trait)) + (outputs + `(#:documentation ,documentation + #:rdf ,output)))) diff --git a/examples/molecular-traits.scm b/examples/molecular-traits.scm deleted file mode 100755 index 77bba08..0000000 --- a/examples/molecular-traits.scm +++ /dev/null @@ -1,123 +0,0 @@ -#! /usr/bin/env guile -!# - -(use-modules (srfi srfi-1) - (srfi srfi-26) - (ice-9 getopt-long) - (ice-9 match) - (ice-9 regex) - (transform strings) - (transform sql) - (transform triples) - (transform special-forms)) - - -(define-transformer gn:molecular-trait->gn:dataset - (tables (Tissue)) - (schema-triples - (gnc:molecular_trait a owl:Class) - (gnc:molecular_trait a skos:Concept) - (gnc:molecular_trait rdfs:subClassOf obo:UBERON_0000479) - (gnc:molecular_trait rdfs:label "Molecular Trait. This describes a melecular trait of a given species. We combine the species name and the tissue name in order to differentiate the traits across different inbredset groups.")) - (triples (string->identifier "trait" (field Tissue Short_Name) #:separator "_") - (set rdf:type 'gnc:molecular_trait) - (set skos:prefLabel (field Tissue Name)) - (set skos:altLabel (field Tissue Short_Name)))) - -(define-transformer gnc:molecular_trait->gn:molecular_trait - (tables (Tissue)) - (triples "gnc:molecular_trait" - (set skos:member (string->identifier "trait" (field Tissue Short_Name) #:separator "_")))) - -(define-transformer gn:set->gn:dataset - (tables (Species - (inner-join InbredSet "ON InbredSet.SpeciesId = Species.Id") - (inner-join ProbeFreeze "ON ProbeFreeze.InbredSetId = InbredSet.Id") - (inner-join ProbeSetFreeze "ON ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id") - (inner-join Tissue "ON ProbeFreeze.TissueId = Tissue.Id")) - "WHERE ProbeSetFreeze.public > 0 AND Species.Name != 'monkey' GROUP BY Species.Name, Tissue.Short_Name") - (schema-triples - (gnt:has_probeset_data rdf:type owl:ObjectProperty) - (gnt:has_probeset_data rdfs:label "this resources has this probeset data.") - (gnt:has_probeset_data rdfs:comment "Associates a resource with this probeset data.") - (gnt:has_probeset_data rdfs:domain gnc:set) - (gnt:has_probeset_data rdfs:range gnc:molecular_trait) - (gnt:has_probeset_data rdfs:subPropertyOf dct:relation)) - (triples (string->identifier "set" (field InbredSet Name InbredSetName) #:separator "_") - (multiset gnt:has_probeset_data - (map (cut string->identifier "dataset" <> #:separator "_") - (string-split - (field ("GROUP_CONCAT(ProbeSetFreeze.Name SEPARATOR ',')" - dataset_name)) - #\,))))) - -(define-transformer gn:dataset->metadata - (tables (ProbeSetFreeze - (inner-join ProbeFreeze "ON ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id") - (inner-join InbredSet "ON InbredSet.Id = ProbeFreeze.InbredSetId") - (inner-join Species "ON InbredSet.SpeciesId = Species.Id") - (inner-join Tissue "ON ProbeFreeze.TissueId = Tissue.Id") - (inner-join AvgMethod "ON AvgMethod.AvgMethodId = ProbeSetFreeze.AvgID") - (inner-join InfoFiles "ON InfoFiles.InfoPageName = ProbeSetFreeze.Name") - (inner-join Datasets "ON InfoFiles.DatasetId = Datasets.DatasetId") - (left-join GeneChip "ON GeneChip.Id = InfoFiles.GeneChipId")) - "WHERE ProbeSetFreeze.public > 0 AND Species.Name != 'monkey'") - (schema-triples - (gnt:has_molecular_trait rdf:type owl:ObjectProperty) - (gnt:has_molecular_trait rdfs:domain gnc:set) - (gnt:has_molecular_trait rdfs:range gnc:molecular_trait) - (gnt:has_molecular_trait rdfs:label "has molecular trait") - (gnt:uses_genechip a owl:ObjectProperty) - (gnt:uses_genechip rdfs:domain dcat:Dataset) - (gnt:uses_genechip skos:definition "The Platform this resource uses..") - (gnt:uses_normalization_method rdfs:comment "The normalization method used for the molecular traits in this dataset") - (gnt:uses_normalization_method rdfs:domain dcat:Dataset) - (gnt:uses_normalization_method rdfs:label "Averaging method used for the molecular traits in this dataset.") - (gnt:uses_normalization_method rdfs:range gnc:avg_method)) - (triples (string->identifier "dataset" (field ProbeSetFreeze Name) #:separator "_") - (set dct:created (annotate-field (field ProbeSetFreeze CreateTime) '^^xsd:datetime)) - (set gnt:uses_normalization_method - (string->identifier "avg_method" (field AvgMethod Name AvgMethodName) #:separator "_")) - (set gnt:has_molecular_trait - (string->identifier "trait" (field Tissue Short_Name) #:separator "_")) - (set gnt:uses_genechip - (string->identifier "platform" (field GeneChip Name) #:separator "_")))) - - -(let* ((option-spec - '((settings (single-char #\s) (value #t)) - (output (single-char #\o) (value #t)) - (documentation (single-char #\d) (value #t)))) - (options (getopt-long (command-line) option-spec)) - (settings (option-ref options 'settings #f)) - (output (option-ref options 'output #f)) - (documentation (option-ref options 'documentation #f)) - (%connection-settings - (call-with-input-file settings - read))) - (with-documentation - (name "Molecular Trait Datasets") - (connection %connection-settings) - (table-metadata? #f) - (prefixes - '(("dcat:" "") - ("gn:" "") - ("obo:" "") - ("owl:" "") - ("xsd:" "") - ("dct:" "") - ("xkos:" "") - ("gnt:" "") - ("skos:" "") - ("gnc:" "") - ("rdf:" "") - ("rdfs:" ""))) - (inputs - (list - gn:dataset->metadata - gn:molecular-trait->gn:dataset - gn:set->gn:dataset - gnc:molecular_trait->gn:molecular_trait)) - (outputs - `(#:documentation ,documentation - #:rdf ,output)))) -- cgit 1.4.1