Add transcript ID to annotation

nf-core · Jan 31, 2024 · 8afed2c · 8afed2c
1 parent 191a5b8
commit 8afed2c
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/modules/local/annotation/annotation/main.nf b/modules/local/annotation/annotation/main.nf
@@ -31,7 +31,7 @@ process ANNOTATION {
         13: 'overlap'
     }
 
-    attributes = ['gene_id']
+    attributes = ['gene_id', 'transcript_id']
 
     df = pd.read_csv('$intersection', sep='\\t', header=None, usecols=columns.keys())
     df = df.rename(columns=columns)
@@ -52,6 +52,7 @@ process ANNOTATION {
     df = df.drop(['overlap', 'length'], axis=1)
     # Kee only unique gene_ids
     df['gene_id'] = df['gene_id'].apply(lambda row: ','.join(row))
+    df['transcript_id'] = df['transcript_id'].apply(lambda row: ','.join(row))
 
     # If 'perfect': circRNA, else EIciRNA
     df['type'] = df['perfect'].apply(lambda perfect: 'circRNA' if perfect else 'EIciRNA')

diff --git a/subworkflows/local/circrna_discovery.nf b/subworkflows/local/circrna_discovery.nf
@@ -276,7 +276,7 @@ workflow CIRCRNA_DISCOVERY {
     // FASTA WORKFLOW:
     //
 
-    FASTA( ANNOTATION.out.bed, fasta )
+    FASTA( KEEP_FOUR_COLUMNS.out.output, fasta )
 
     ch_versions = ch_versions.mix(FASTA.out.versions)