From 1ea6e2dd7655788e198dc13695c829287132498f Mon Sep 17 00:00:00 2001 From: Munyoki Kilyungi Date: Fri, 15 Dec 2023 21:38:24 +0300 Subject: Preserve gene symbol case when used as an identifer. Genes with varying casing (e.g., Shh, SHH) result in `string->identifier` capitalizing the first letter by default. This creates inconsistencies in gene symbols, leading to different predicates and objects for the same entity, introducing errors. Signed-off-by: Munyoki Kilyungi --- examples/genelist.scm | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'examples/genelist.scm') diff --git a/examples/genelist.scm b/examples/genelist.scm index fbd39c1..b19b30f 100755 --- a/examples/genelist.scm +++ b/examples/genelist.scm @@ -78,10 +78,12 @@ (gnt:hasTargetSeq rdfs:domain gnc:Probeset)) (triples (string->identifier - "gene" (regexp-substitute/global #f "[^A-Za-z0-9:]" - (string-trim-both - (field GeneList GeneSymbol)) - 'pre "_" 'post)) + "gene" (regexp-substitute/global + #f "[^A-Za-z0-9:]" + (string-trim-both + (field GeneList GeneSymbol)) + 'pre "_" 'post) + #:proc (lambda (x) x)) (set rdf:type 'gnc:GeneSymbol) (set rdfs:label (field GeneList GeneSymbol)) (set dct:description (sanitize-rdf-string (field GeneList GeneDescription))) -- cgit v1.2.3