diff --git a/tsg/main.py b/tsg/main.py index e53a5ab99606df3e7b3bdddba4ae25b3cc9d4904..f85a8c6898f95b1b1605f8704dc310a95fb0fc98 100644 --- a/tsg/main.py +++ b/tsg/main.py @@ -58,9 +58,9 @@ def filter_df(gtf_df: pd.DataFrame, transcripts: list) -> pd.DataFrame: & (gtf_df["free_text"].str.contains('transcript_support_level "1"')) ] if len(transcripts) > 0: - df_filter = df_filter["free_text"].str.contains( + df_filter = df_filter[df_filter["free_text"].str.contains( "|".join(transcripts), regex=True - ) + )] return df_filter @@ -159,7 +159,6 @@ def write_gtf(gtf_df: pd.DataFrame, filename: str) -> None: sep="\t", header=False, index=False, - quoting=None, quotechar="'", mode="a", ) @@ -226,7 +225,7 @@ class Gtf: annotations_file, sep="\t", comment="#", - names=self.dtypes.keys(), + names=list(self.dtypes.keys()), dtype=self.dtypes, chunksize=100000, iterator=True, @@ -515,15 +514,15 @@ def sample_transcripts( transcript_count = row["count"] transcript_df = annotations.pick_transcript(transcript_id) - transcripts = TranscriptGenerator( + transcript_generator = TranscriptGenerator( transcript_id, transcript_count, transcript_df, prob_inclusion=prob_inclusion, ) try: - transcripts.write_annotations(output_annotations_file) - transcripts.write_sequences(output_transcripts_file) + transcript_generator.write_annotations(output_annotations_file) + transcript_generator.write_sequences(output_transcripts_file) except AttributeError: pass LOG.info("Done.")