From 56f672d11011349f05b00dfd5702bfd6e1ab2a30 Mon Sep 17 00:00:00 2001
From: Larissa Glass <larissa.glass@unibas.ch>
Date: Wed, 9 Nov 2022 15:12:53 +0000
Subject: [PATCH] Add original transcript id to output transcripts
---
tsg/cli.py | 4 ++++
tsg/main.py | 7 ++++++-
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/tsg/cli.py b/tsg/cli.py
index 57b6e0e..1a667d8 100644
--- a/tsg/cli.py
+++ b/tsg/cli.py
@@ -46,6 +46,10 @@ def output_filename(filename: str) -> str:
outfile = "generated_" + filepath.name
else:
raise NotImplementedError()
+
+ if Path(outfile).exists():
+ raise FileExistsError(f"The output file {outfile} already exists.")
+
return outfile
diff --git a/tsg/main.py b/tsg/main.py
index 9f506bf..25bba5f 100644
--- a/tsg/main.py
+++ b/tsg/main.py
@@ -22,6 +22,8 @@ def read_abundances(transcripts_file: str) -> pd.DataFrame:
return pd.read_table(transcripts_file, header=None, names=cols)
elif transcripts_file.endswith(".csv"):
return pd.read_csv(transcripts_file, header=None, names=cols)
+ else:
+ raise ValueError("File type needs to be either csv or tsv")
def filter_df(df: pd.DataFrame, transcripts: list = []) -> pd.DataFrame:
@@ -117,6 +119,9 @@ class Gtf:
def read_file(self, annotations_file: str) -> None:
# for large annotation files, iterate over lines and filter before saving to dataframe
+ if not annotations_file.endswith("gtf"):
+ raise ValueError("File type needs to be gtf")
+
reader = pd.read_table(
annotations_file,
sep="\t",
@@ -260,7 +265,7 @@ class TranscriptGenerator:
ids, inclusions, counts = self._get_unique_inclusions()
with open(filename, "a") as fh:
for transcript_id, transcript_count in zip(ids, counts):
- fh.write(f"{transcript_id},{transcript_count}\n")
+ fh.write(f"{transcript_id},{self.id},{transcript_count}\n")
def generate_annotations(self, filename: str) -> None:
ids, inclusions, counts = self._get_unique_inclusions()
--
GitLab