Add GeneList metadata RDF transform.

Signed-off-by: Munyoki Kilyungi <me@bonfacemunyoki.com>

1 files changed, 193 insertions, 0 deletions

diff --git a/examples/genelist.scm b/examples/genelist.scm
new file mode 100755
index 0000000..8097610
--- /dev/null
+++ b/examples/genelist.scm
@@ -0,0 +1,193 @@
+#! /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 genelist
+  (tables (GeneList
+           (left-join Species "USING (SpeciesId)"))
+          "GROUP BY BINARY GeneSymbol, GeneId, chromosome, txStart, txEnd")
+  (schema-triples
+   (gnt:gene rdfs:domain gnc:GeneSymbol)
+   (gnt:belongsToSpecies rdfs:domain gnc:GeneSymbol)
+   (gnc:GeneSymbol a rdfs:Class)
+   (gnc:GeneSymbol rdfs:label "Gene Symbol")
+   (gnc:transcript rdfs:domain gnc:GeneSymbol)
+   (gnt:transcript a owl:ObjectProperty)
+   (gnc:transcript rdfs:comments "The gene transcript of this resource")
+   (gnc:hasKgID rdfs:domain gnc:GeneSymbol)
+   (gnt:hasKgID a owl:ObjectProperty)
+   (gnc:hasKgID rdfs:comments "The kgID of this resource")
+   (gnc:hasUnigenID rdfs:domain gnc:GeneSymbol)
+   (gnt:hasUnigenID a owl:ObjectProperty)
+   (gnc:hasUnigenID rdfs:comments "The UnigenID of this resource")
+   (gnc:hasProteinID rdfs:domain gnc:GeneSymbol)
+   (gnt:hasProteinID a owl:ObjectProperty)
+   (gnc:hasProteinID rdfs:comments "The ProteinID of this resource")
+   (gnc:hasAlignID rdfs:domain gnc:GeneSymbol)
+   (gnt:hasAlignID a owl:ObjectProperty)
+   (gnc:hasAlignID rdfs:comments "The AlignID of this resource")
+   (gnt:TxEnd rdfs:range xsd:double)
+   (gnt:TxStart rdfs:range xsd:double)
+   (gnt:hasTargetSeq rdfs:domain gnc:Probeset))
+  (triples
+      (string->identifier
+       "gene" (regexp-substitute/global #f "[^A-Za-z0-9:]"
+                                    (field GeneList GeneSymbol)
+                                    'pre "_" 'post))
+    (set rdf:type 'gnc:GeneSymbol)
+    (set rdfs:label (field GeneList GeneSymbol))
+    (set dct:description (sanitize-rdf-string (field GeneList GeneDescription)))
+    (set gnt:gene (ontology 'gene: (field GeneList GeneId)))
+    (set gnt:chromosome (field GeneList Chromosome))
+    (set gnt:TxStart (annotate-field
+                      (field GeneList TxStart)
+                      '^^xsd:double))
+    (set gnt:TxEnd (annotate-field
+                    (field GeneList TxEnd)
+                    '^^xsd:double))
+    (set gnt:Strand (string-trim-both (field GeneList Strand)))
+    (multiset
+     gnt:belongsToSpecies
+     (map
+      (lambda (species)
+        (string->identifier
+         ""
+         (remap-species-identifiers
+          (string-trim-both species))
+         #:separator ""
+         #:proc string-capitalize-first))
+      (string-split
+       (sanitize-rdf-string
+        (field ("GROUP_CONCAT( DISTINCT Species.Name )" SpeciesName)))
+       #\,)))
+    (multiset
+     gnt:transcript
+     (map
+      (lambda (transcript)
+        (ontology 'transcript:
+                  (string-trim-both transcript)))
+      (string-split
+       (sanitize-rdf-string
+        (field ("GROUP_CONCAT( DISTINCT NM_ID )" NMID)))
+       #\,)))
+    (multiset
+     gnt:hasKgID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT kgID )" kgID)))
+           #\,)))
+    (multiset
+     gnt:hasUnigenID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT UnigenID )" UnigenID)))
+           #\,)))
+    (multiset
+     gnt:hasProteinID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT ProteinID )" ProteinID)))
+           #\,)))
+    (multiset
+     gnt:hasAlignID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT AlignID )" AlignID)))
+           #\,)))
+    (multiset
+     gnt:hasRgdID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT RGD_ID )" RgdID)))
+           #\,)))))
+
+(define-transformer genelist-rn33
+  (tables (GeneList_rn33)
+          "GROUP BY BINARY GeneSymbol, chromosome, txStart, txEnd")
+  (triples
+      (string->identifier
+       "gene" (regexp-substitute/global #f "[^A-Za-z0-9:]"
+                                    (field GeneList_rn33 geneSymbol)
+                                    'pre "_" 'post))
+    (set rdf:type 'gnc:GeneSymbol)
+    (set rdfs:label (field GeneList_rn33 geneSymbol))
+    (set gnt:chromosome (field GeneList_rn33 chromosome))
+    (set gnt:TxStart (annotate-field
+                      (field GeneList_rn33 txStart)
+                      '^^xsd:double))
+    (set gnt:TxEnd (annotate-field
+                    (field GeneList_rn33 txEnd)
+                    '^^xsd:double))
+    (set gnt:Strand (string-trim-both (field GeneList_rn33 strand)))
+    (set gnt:belongsToSpecies 'gn:Rattus_norvegicus)
+    (multiset
+     gnt:transcript
+     (map
+      (lambda (transcript)
+        (ontology 'transcript:
+                  (string-trim-both transcript)))
+      (string-split
+       (sanitize-rdf-string
+        (field ("GROUP_CONCAT( DISTINCT NM_ID )" NMID)))
+       #\,)))
+    (multiset
+     gnt:hasKgID
+     (map string-trim-both
+          (string-split
+           (sanitize-rdf-string
+            (field ("GROUP_CONCAT( DISTINCT kgID )" kgID)))
+           #\,)))))
+
+
+
+(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 "Gene Metadata")
+   (connection %connection-settings)
+   (table-metadata? #f)
+   (prefixes
+    '(("gn:" "<http://genenetwork.org/id/>")
+      ("probeset:" "<http://genenetwork.org/probeset/>")
+      ("gnc:" "<http://genenetwork.org/category/>")
+      ("gnt:" "<http://genenetwork.org/term/>")
+      ("rdf:" "<http://www.w3.org/1999/02/22-rdf-syntax-ns#>")
+      ("rdfs:" "<http://www.w3.org/2000/01/rdf-schema#>")
+      ("dct:" "<http://purl.org/dc/terms/>")
+      ("owl:" "<http://www.w3.org/2002/07/owl#>")
+      ("xsd:" "<http://www.w3.org/2001/XMLSchema#>")
+      ("qb:" "<http://purl.org/linked-data/cube#>")
+      ("gene:" "<http://www.ncbi.nlm.nih.gov/gene?cmd=Retrieve&dopt=Graphics&list_uids=>")
+      ("sdmx-measure:" "<http://purl.org/linked-data/sdmx/2009/measure#>")
+      ("transcript:" "<https://portals.broadinstitute.org/gpp/public/trans/details?transName=>")
+      ("skos:" "<http://www.w3.org/2004/02/skos/core#>")))
+   (inputs
+    (list genelist-rn33
+          genelist))
+   (outputs
+    `(#:documentation ,documentation
+      #:rdf ,output))))