From 3d7543859bef5ebb6c9e7b90881979fe6b668b15 Mon Sep 17 00:00:00 2001
From: Samuel Mondal <mondal0000@bz-rgab01-pdm02.bioz.unibas.ch>
Date: Tue, 13 Dec 2022 17:12:04 +0100
Subject: [PATCH] minor changes based on pylint
---
gtf_processing/pre_bedtools.py | 9 ++++-----
sequence_extractor/cli.py | 11 ++++++++++-
sequence_extractor/exon_concatenation.py | 19 ++++++++++---------
sequence_extractor/poly_a.py | 15 ++++++++-------
4 files changed, 32 insertions(+), 22 deletions(-)
diff --git a/gtf_processing/pre_bedtools.py b/gtf_processing/pre_bedtools.py
index 57be294..2088947 100644
--- a/gtf_processing/pre_bedtools.py
+++ b/gtf_processing/pre_bedtools.py
@@ -1,7 +1,3 @@
-import pandas as pd
-import argparse
-from gtfparse import read_gtf
-
"""This script defines a BED from exon annotation in a GTF, to get exon coordinates for use in bedtools. It also ensures that the concatenation happens in the correct order, regardless of the strandedness of the transcript.
Args:
@@ -11,6 +7,10 @@ from gtfparse import read_gtf
BED file with the format: chr, start, end, transcript_id, score, strand, gene_id
"""
+import argparse
+import pandas as pd
+from gtfparse import read_gtf
+
parser = argparse.ArgumentParser(
prog = 'pre_bedtools',
description = 'extracts ordered information from gtf file and for transcripts in the negative strand, flips the order in which exons are ordered.')
@@ -31,4 +31,3 @@ gtf_df_pos = gtf_exons[gtf_exons["strand"] == "+"]
gtf_df_pos = gtf_df_pos.sort_values(['transcript_id','start'],ascending=True).groupby('transcript_id').head(len(gtf_df_pos. transcript_id))
pd.concat([gtf_df_pos, gtf_df_neg]).to_csv(args.output_bed_file,sep="\t",index=False) #gtf_df_pos and gtf_df_neg must be dataframes
-
diff --git a/sequence_extractor/cli.py b/sequence_extractor/cli.py
index 2e05f55..73062da 100644
--- a/sequence_extractor/cli.py
+++ b/sequence_extractor/cli.py
@@ -1,3 +1,4 @@
+""" command line script to be run on output fasta file from bedtools getfasta """
import argparse
import logging
from exon_concatenation import exon_concatenation
@@ -14,10 +15,18 @@ parser.add_argument('--output_file_name',
args = parser.parse_args()
def main():
+ """Runs on the output from bedtools and concatenates the exons together and adds a polyA tail and outputs a fasta file.
+
+ Args:
+ None: this will run on its own by taking the information from argparse
+
+ Returns:
+ A fasta file with a single entry for each transcript ID with polyA tail being added onto the sequence at 3'end
+ """
LOG.info("sequence_extractor begins")
fasta_list = exon_concatenation(args.input_fasta_file)
final_list = poly_a_addition_to_fasta_list(fasta_list)
- with open(args.output_file_name, 'w') as fasta_out:
+ with open(args.output_file_name, 'w', encoding="utf-8") as fasta_out:
fasta_out.write('\n'.join('%s\n%s' % x for x in final_list))
LOG.info("sequence_extractor ends")
diff --git a/sequence_extractor/exon_concatenation.py b/sequence_extractor/exon_concatenation.py
index 4a4b1c0..d9f3266 100644
--- a/sequence_extractor/exon_concatenation.py
+++ b/sequence_extractor/exon_concatenation.py
@@ -1,18 +1,19 @@
+"""Script containing the function to concatenate exons and output the results in a list of tuples"""
def exon_concatenation(
- post_bedtools_fasta: str
+ post_bedtools_fasta: str,
) -> list:
- """Concatenate all sequences starting with identical transcripit ID and outputs it as a list with sequence header (Transcript ID) and concatenated sequences as tuples.
+ """Concatenate all sequences starting with identical transcripit ID and outputs it as a list with sequence header (Transcript ID) and concatenated sequences as tuples.
- Args:
- post_bedtools_fasta: The name of the fasta file obtained after bedtools has been run
+ Args:
+ post_bedtools_fasta: The name of the fasta file obtained after bedtools has been run
- Returns:
- A list containing transcript ID and concatenated exons in tuples.
- """
- with open(post_bedtools_fasta,'r') as fa:
+ Returns:
+ A list containing transcript ID and concatenated exons in tuples.
+ """
+ with open(post_bedtools_fasta,'r', encoding="utf-8") as fasta:
annotation = []
fasta_format_list = []
- for line1,line2 in zip(fa,fa):
+ for line1,line2 in zip(fasta,fasta):
if len(annotation) == 0:
annotation.append(line1[0:16])
read = line2[:-1]
diff --git a/sequence_extractor/poly_a.py b/sequence_extractor/poly_a.py
index 28a9679..60b2997 100644
--- a/sequence_extractor/poly_a.py
+++ b/sequence_extractor/poly_a.py
@@ -1,9 +1,10 @@
+""" This script contains two functions and the first function is called by the second function and used to add poly A tail to the concatenated exon"""
import numpy as np
# To do: Taking probabilities of nucleotides from user and raising error if sum != 1
def poly_a_generator(
exon: str,
) -> str:
- """Adds a PolyA tail to an exon sequence input into the function.
+ """Adds a PolyA tail to an exon sequence input into the function.
Args:
exon: RNA sequence, obtained from concatenation of exons, that needs polyA to be added to its 3' end.
@@ -11,14 +12,14 @@ def poly_a_generator(
Returns:
RNA with polyA tail added to its 3' end.
"""
- listA = ['A','T','G','C']
- polyA = ''.join(np.random.choice(listA,250,p=[0.914,0.028,0.025,0.033]))
- return (exon+polyA)
+ list_of_nucleotides = ['A','T','G','C']
+ poly_a_string = ''.join(np.random.choice(list_of_nucleotides,250,p=[0.914,0.028,0.025,0.033]))
+ return exon+poly_a_string
def poly_a_addition_to_fasta_list(
fasta_list: list,
) -> list:
- """Takes in a list of tuples with annotations and exons and outputs a list where polyA tail has been added to all the exon 3' ends.
+ """Takes in a list of tuples with annotations and exons and outputs a list where polyA tail has been added to all the exon 3' ends.
Args:
fasta_list: List contaning tuples of annotations and exons
@@ -26,5 +27,5 @@ def poly_a_addition_to_fasta_list(
Returns:
A list like the initial list, this time with polyA tail added onto it.
"""
- mature_rna_list = [(i[0],poly_a_generator(i[1])) for i in fasta_list]
- return mature_rna_list
+ mature_rna_list = [(i[0],poly_a_generator(i[1])) for i in fasta_list]
+ return mature_rna_list
--
GitLab