added "_" separation in the third gtf-column in response to #29

loosolab · Jan 3, 2019 · 6016c18 · 6016c18
1 parent 39cdf16
commit 6016c18
Showing 2 changed files with 2 additions and 3 deletions.
diff --git a/bin/3.1_create_gtf/Modules/Ensembl/GTFGen.py b/bin/3.1_create_gtf/Modules/Ensembl/GTFGen.py
@@ -51,7 +51,7 @@ def reformat_to_gff(self, activity, release):
             # Add RegBuild_ + release
             templist.append("RegBuild_"+release)
             # Add Description from Description in last ; separated segment
-            templist.append(splitted_additional[4].split("=")[1].lower())
+            templist.append(splitted_additional[4].split("=")[1].lower().replace(' ', '_'))
             # Add Start / End Data from original
             templist.extend(splitted[3:5])
             # Add Score, Strand and Frame Data
@@ -68,7 +68,6 @@ def reformat_to_gff(self, activity, release):
     @staticmethod
     def generate_additional_information(gene_id, activity):
         # helper method to concat activity information to string
-        print(gene_id)
         if gene_id.startswith("ID=regulatory_region:"):
             gene_id = 'gene_id "'+gene_id.split(':')[1]+'"'
         elif gene_id.startswith("ID=E"):

diff --git a/bin/3.1_create_gtf/Modules/ucsc/ucsc.py b/bin/3.1_create_gtf/Modules/ucsc/ucsc.py
@@ -41,7 +41,7 @@ def read_gff_to_gtf(self):
                 sequence = []
                 sequence.append(row[0])
                 sequence.append("UCSC")
-                sequence.append(row[3].lower())
+                sequence.append(row[3].lower().replace(' ', '_'))
                 sequence.append(row[1])
                 sequence.append(row[2])
                 sequence.append(".")