bioinfo/Ensembl: fetch cdna files

pveber · Jun 1, 2018 · 0d7bd46 · 0d7bd46
1 parent b6d9d0f
commit 0d7bd46
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 0 deletions.
diff --git a/lib/bioinfo/ensembl.ml b/lib/bioinfo/ensembl.ml
@@ -63,3 +63,11 @@ let gtf ?(chr_name = `ensembl) ~release ~species =
     | `ucsc -> ucsc_chr_names_gtf
   in
   f @@ Unix_tools.(gunzip (wget url))
+
+let cdna ~release ~species =
+  let url = sprintf "ftp://ftp.ensembl.org/pub/release-%d/fasta/%s/cdna/%s.%s.cdna.all.fa.gz"
+      release (string_of_species species)
+      (String.capitalize (string_of_species species))
+      (lab_label_of_genome (ucsc_reference_genome ~release ~species))
+  in
+  Unix_tools.wget url
diff --git a/lib/bioinfo/ensembl.mli b/lib/bioinfo/ensembl.mli
@@ -10,3 +10,5 @@ val ucsc_reference_genome : release:int -> species:species -> Ucsc_gb.genome
 
 val gff : ?chr_name : [`ensembl | `ucsc] -> release:int -> species:species -> gff workflow
 val gtf : ?chr_name : [`ensembl | `ucsc] -> release:int -> species:species -> gff workflow
+
+val cdna : release:int -> species:species -> fasta gz workflow
Original file line number	Diff line number	Diff line change
Expand Up		@@ -10,3 +10,5 @@ val ucsc_reference_genome : release:int -> species:species -> Ucsc_gb.genome

		val gff : ?chr_name : [`ensembl \| `ucsc] -> release:int -> species:species -> gff workflow
		val gtf : ?chr_name : [`ensembl \| `ucsc] -> release:int -> species:species -> gff workflow

		val cdna : release:int -> species:species -> fasta gz workflow