From f8aefb8283986d1d02be9ad6cf3e10a9c2b3dc8d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?M=C3=A1t=C3=A9=20Balajti?= <mate.balajti@unibas.ch>
Date: Mon, 4 Sep 2023 16:50:44 +0200
Subject: [PATCH] refactor: update main.py with TSL support
---
setup.py | 2 +-
tsg/main.py | 13 ++++++-------
2 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/setup.py b/setup.py
index 7ebb48d..638df50 100644
--- a/setup.py
+++ b/setup.py
@@ -12,7 +12,7 @@ URL = ('https://git.scicore.unibas.ch/zavolan_group/'
setup(
name='transcript-structure-generator',
- version='0.1.0',
+ version='0.2.0',
url=URL,
license='MIT',
author='Larissa Glass, Michael Zimmermann, Andri Fraenkl',
diff --git a/tsg/main.py b/tsg/main.py
index c86c741..8307b79 100644
--- a/tsg/main.py
+++ b/tsg/main.py
@@ -55,7 +55,7 @@ def filter_df(gtf_df: pd.DataFrame, transcripts: list) -> pd.DataFrame:
transcripts = []
df_filter = gtf_df[
(gtf_df["feature"] == "exon")
- & (gtf_df["free_text"].str.contains('transcript_support_level "1"'))
+ & (gtf_df["free_text"].str.contains('transcript_support_level "1'))
]
if len(transcripts) > 0:
df_filter = df_filter[df_filter["free_text"].str.contains(
@@ -316,16 +316,15 @@ class TranscriptGenerator:
strands = transcript_df["strand"].unique()
if len(transcript_df) == 0:
LOG.warning(
- "Transcript %s can't be sampled. \
- Annotation is missing", transcript_id
+ "Transcript %s can't be sampled. "
+ "Annotation is missing or TSL is not 1.", transcript_id
)
instance = None
elif len(strands) > 1:
LOG.warning(
- "Transcript %s can't be sampled. Transcript generator \
- is not implemented for transcripts with \
- exons annotated on different strands",
- transcript_id,
+ "Transcript %s can't be sampled. Transcript generator is "
+ "not implemented for transcripts with exons annotated on "
+ "different strands", transcript_id,
)
instance = None
else:
--
GitLab