From f590a529d6378086cbaa0d97bb8da129facf8c3c Mon Sep 17 00:00:00 2001
From: Laura Urbanska <laura.urbanska@stud.unibas.ch>
Date: Tue, 10 Jan 2023 09:05:45 +0000
Subject: [PATCH] Updated find_representative_transcripts.py by including GTF
writer
---
scripts/find_representative_transcripts.py | 23 ++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/scripts/find_representative_transcripts.py b/scripts/find_representative_transcripts.py
index f1961d6..f378f31 100644
--- a/scripts/find_representative_transcripts.py
+++ b/scripts/find_representative_transcripts.py
@@ -176,6 +176,29 @@ def get_rep_trans(file_name = "test"):
rep_transcripts = _re_format(rep_trans)
return(rep_transcripts )
+def gtf_file_writer (original_file, output_file):
+ """
+ this function writes the output GTF file
+ """
+ output = []
+ rep_transcript_dict = get_rep_trans(original_file)
+
+ with open(original_file, 'r') as f:
+ for entry in f:
+ if entry[0] != '#':
+ attributes = attributs_converter(entry)
+ type_ = attributes[2]
+ if type_ == 'gene':
+ gene_id = find_in_attributs(attributes, 'gene_id')
+ output.append(entry)
+ if type_ != 'gene':
+ transcript_id = find_in_attributs(attributes, 'transcript_id')
+ if rep_transcript_dict[gene_id] == transcript_id:
+ output.append(entry)
+
+ with open(output_file, 'w') as last_file:
+ last_file.write(output)
+
def _test():
"""
This funtion is ment to be run for test
--
GitLab