From 0db28afa685a4047050960946baad1aa251dbffc Mon Sep 17 00:00:00 2001
From: Eric Boittier <ericdavid.boittier@unibas.ch>
Date: Mon, 12 Dec 2022 15:37:25 +0100
Subject: [PATCH] setup.py uses requirements.txt
---
Dockerfile | 10 +++++
cdna/cdna.py | 112 +++++++++++++++++++++++++++++++++++++----------
requirements.txt | 3 +-
setup.py | 5 ++-
4 files changed, 104 insertions(+), 26 deletions(-)
create mode 100644 Dockerfile
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..e71e517
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,10 @@
+FROM python:3.8-slim-buster
+
+MAINTAINER EricBoittier
+
+ENV PATH=$PATH:/usr/games/
+
+COPY . .
+
+
+
diff --git a/cdna/cdna.py b/cdna/cdna.py
index 4a1b912..c5f6d31 100644
--- a/cdna/cdna.py
+++ b/cdna/cdna.py
@@ -13,10 +13,12 @@ warnings.filterwarnings(action="ignore", category=FutureWarning)
def compliment(res: str) -> str:
"""
- Returns the compliment of a given DNA residue.
-
- :param res: DNA residue
- :return:
+ Returns the cDNA compliment of a given base pair
+ Args:
+ res: residue code.
+
+ Returns: corresponding cDNA residue.
+
"""
translate_dict = {"A": "T", "T": "A", "U": "A", "G": "C", "C": "G"}
if res not in translate_dict.keys():
@@ -27,11 +29,14 @@ def compliment(res: str) -> str:
def seq_compliment(sequence: str) -> str:
"""
- Returns the corresponding cDNA sequence for a given input by finding the
- corresponding compliment base pair and reversing the input.
+ Returns the corresponding cDNA sequence by finding the complimentary
+ base pairs and returning the reversed sequence.
+
+ Args:
+ sequence: sequence to be converted into cDNA.
+
+ Returns: corresponding cDNA sequence.
- :param sequence: DNA sequence
- :return: cDNA sequence
"""
if sequence is None:
return "None"
@@ -51,21 +56,26 @@ class CDNAGen:
# variables
self.fasta_dict = None
self.fasta_records = None
-
+ self.df_input_GTF = None
self.run()
- def run(self):
+ def run(self) -> None:
+ """
+ Executes the cDNA workflow.
+ Returns: None
+
+ """
self.read_csv()
self.read_fasta()
self.read_gtf()
self.add_sequences()
self.add_compliment()
self.add_records()
- print()
+ print() # blank line for pretty printing
self.write_fasta()
self.write_csv()
- def add_records(self):
+ def add_records(self) -> None:
self.fasta_records = []
for index, row in self.df_input_GTF.iterrows():
if row["compliment"] is not None:
@@ -78,36 +88,79 @@ class CDNAGen:
)
self.fasta_records.append(record)
- def add_sequences(self):
+ def add_sequences(self) -> None:
+ """
+ Adds the sequence for a given priming site.
+ Returns: None
+
+ """
self.df_input_GTF["priming_site"] = self.df_input_GTF.apply(
lambda row: self.read_primingsite(row["seqname"], row["start"]),
axis=1,
)
- def add_compliment(self):
+ def add_compliment(self) -> None:
+ """
+ Adds the complimentary cDNA sequence.
+ Returns: None
+
+ """
self.df_input_GTF["compliment"] = self.df_input_GTF["priming_site"].apply(
lambda x: seq_compliment(x)
)
- def read_primingsite(self, sequence, start):
+ def read_primingsite(self, sequence: str, start: int) -> None:
+ """Read a fasta file from a given start character
+
+ Reads a fasta sequence with ID (sequence) and returns the
+ sequence starting from the index start.
+
+ Args:
+ sequence: sequence ID to be read.
+ start: start of the sequence.
+
+ Returns: None
+
+ """
if sequence not in self.fasta_dict.keys():
return None
_ = self.fasta_dict[sequence].seq[start:]
return _
- def read_fasta(self):
+ def read_fasta(self) -> None:
+ """Read a given fasta file.
+
+ Wrapper for SeqIO.parse.
+
+ Returns: None
+
+ """
record = SeqIO.parse(self.fasta, "fasta")
records = list(record)
self.fasta_dict = {x.name: x for x in records}
- def read_csv(self):
+ def read_csv(self) -> None:
+ """ Reads a given copy number csv file
+
+ Wrapper for Pandas read_csv.
+
+ Returns: None
+
+ """
df_input_CSV = pd.read_csv(self.cpn, index_col=False)
df_input_CSV = (
df_input_CSV.reset_index()
) # make sure indexes pair with number of rows
self.df_input_CSV = df_input_CSV
- def read_gtf(self):
+ def read_gtf(self) -> None:
+ """Read and process the GTF file.
+
+ Reads a GTF file and determines copy numbers from normalized probabilities.
+
+ Returns: None
+
+ """
# returns GTF with essential columns such as "feature", "seqname", "start", "end"
# alongside the names of any optional keys which appeared in the attribute column
df_input_GTF = read_gtf(self.gtf)
@@ -132,7 +185,7 @@ class CDNAGen:
id_CSV = str(row["seqname"]).split("_")[1]
# Calculate Normalized_Binding_Probability and add to GTF dataframe
df_input_GTF.loc[index, "Normalized_Binding_Probability"] = (
- row["Binding_Probability"] / df_normalization_bind_probablility[id_GTF]
+ row["Binding_Probability"] / df_normalization_bind_probablility[id_GTF]
)
# Calculate Normalized_Binding_Probability and add to GTF dataframe
csv_transcript_copy_number = self.df_input_CSV.loc[
@@ -148,15 +201,26 @@ class CDNAGen:
self.df_input_GTF = df_input_GTF
- def write_fasta(self):
+ def write_fasta(self) -> None:
+ """Writes cDNA fasta records to file.
+
+ Wrapper for SeqIO.write.
+
+ Returns: None
+
+ """
SeqIO.write(self.fasta_records, self.output_fasta, "fasta")
print(f"Fasta file successfully written to: {self.output_fasta}")
- def write_csv(self):
+ def write_csv(self) -> None:
+ """Writes the copy number information to a csv file.
+
+ Wrapper for Pandas to_csv.
+
+ Returns: None
+
+ """
self.df_input_GTF[["cdna_ID", "Transcript_Copy_Number"]].to_csv(
self.output_csv, index=False
)
print(f"Copy number csv file successfully written to: {self.output_csv}")
-
-
-
diff --git a/requirements.txt b/requirements.txt
index 3abd004..d9abb6b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,3 @@
gtfparse
-biopython
\ No newline at end of file
+biopython
+pandas
diff --git a/setup.py b/setup.py
index 96ecc09..73e2bfd 100644
--- a/setup.py
+++ b/setup.py
@@ -1,5 +1,8 @@
from setuptools import setup, find_packages
+with open('requirements.txt') as f:
+ required = f.read().splitlines()
+
setup(
name='cdna',
url='https://gitlab.com/my_user_name/my_package.git',
@@ -9,5 +12,5 @@ setup(
license='MIT',
version='1.0.0',
packages=find_packages(), # this will autodetect Python packages from the directory tree, e.g., in `code/`
- install_requires=[], # add here packages that are required for your package to run, including version or range of versions
+ install_requires=required, # add here packages that are required for your package to run, including version or range of versions
)
--
GitLab