diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index d0ca3580ed585f2fccb7c99b6b6d3890fd63e154..3ff981c274b7db202d782caa50f2935d6843ed6c 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -20,7 +20,7 @@ unit-test-job: # This job runs in the test stage.
- pip install -r requirements.txt
- pip install -r requirements_dev.txt
- pip install -e .
- - coverage run --source term_frag_sel -m pytest
+ - coverage run --source cdna -m pytest
- coverage report -m
lint-test-job: # This job also runs in the test stage.
@@ -29,6 +29,6 @@ lint-test-job: # This job also runs in the test stage.
- pip install -r requirements.txt
- pip install -r requirements_dev.txt
- pip install -e .
- - flake8 --docstring-convention google term_frag_sel/ tests/
- - pylint term_frag_sel/ tests/
- - mypy term_frag_sel/
\ No newline at end of file
+ - flake8 --docstring-convention google cdna/ tests/
+ - pylint cdna/ tests/
+ - mypy cdna/
\ No newline at end of file
diff --git a/cdna/__init__.py b/cdna/__init__.py
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..bb7d5f3186cb2e516714c06c9a5e8d2b57696586 100644
--- a/cdna/__init__.py
+++ b/cdna/__init__.py
@@ -0,0 +1 @@
+"""Initialise package."""
diff --git a/cdna/cdna.py b/cdna/cdna.py
index d8acd5f05c684854327b61db125edc9b168c3d9a..e6c5720ed4996edd5c785fbd22638a8c61376738 100644
--- a/cdna/cdna.py
+++ b/cdna/cdna.py
@@ -1,5 +1,5 @@
+"""cDNA generator."""
import warnings
-
import pandas as pd
from Bio import SeqIO
from Bio.Seq import Seq
@@ -11,8 +11,8 @@ warnings.filterwarnings(action="ignore", category=FutureWarning)
def complement(res: str) -> str:
- """
- Returns the cDNA complement of a given base pair
+ """Return the cDNA complement of a given base pair.
+
Args:
res: residue code.
@@ -28,9 +28,8 @@ def complement(res: str) -> str:
def seq_complement(sequence: str) -> str or None:
- """
- Returns the corresponding cDNA sequence by finding the complementary
- base pairs and returning the reversed sequence.
+ """Return the corresponding cDNA sequence by finding the complementary \
+ base pairs and returning the reversed sequence.
Args:
sequence: sequence to be converted into cDNA.
@@ -40,16 +39,17 @@ def seq_complement(sequence: str) -> str or None:
"""
if sequence is None:
return None
- _ = "".join([complement(char) for char in str(sequence)])[::-1] # reverse string
+ _ = "".join([complement(char) for char in str(sequence)])[::-1] # reverse string # noqa: E501
return _
class CDNAGen:
- """
- Module that performs the cDNA synthesis.
- """
+ """Perform the cDNA synthesis."""
- def __init__(self, ifasta: str, igtf: str, icpn: str, ofasta: str, ocsv: str):
+ def __init__(
+ self, ifasta: str, igtf: str, icpn: str, ofasta: str, ocsv: str
+ ):
+ """Initialise function."""
# inputs
self.fasta = ifasta
self.gtf = igtf
@@ -65,8 +65,8 @@ class CDNAGen:
self.run()
def run(self) -> None:
- """
- Executes the cDNA workflow.
+ """Execute the cDNA workflow.
+
Returns: None
"""
@@ -80,7 +80,7 @@ class CDNAGen:
self.write_csv()
def add_records(self) -> None:
- """Adds data records to fasta file.
+ """Add data records to fasta file.
Adds the copy number information to the fasta records.
@@ -88,7 +88,7 @@ class CDNAGen:
"""
self.fasta_records = []
- for index, row in self.gtf_df.iterrows():
+ for _, row in self.gtf_df.iterrows():
if row["complement"] is not None:
copy_number = row["Transcript_Copy_Number"]
for _ in range(int(copy_number)):
@@ -101,8 +101,8 @@ class CDNAGen:
self.fasta_records.append(record)
def add_sequences(self) -> None:
- """
- Adds the sequence for a given priming site.
+ """Add the sequence for a given priming site.
+
Returns: None
"""
@@ -112,8 +112,8 @@ class CDNAGen:
)
def add_complement(self) -> None:
- """
- Adds the complementary cDNA sequence.
+ """Add the complementary cDNA sequence.
+
Returns: None
"""
@@ -122,7 +122,7 @@ class CDNAGen:
)
def read_primingsite(self, sequence: str, end: int) -> None:
- """Read a fasta file from a given start character
+ """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.
@@ -151,7 +151,7 @@ class CDNAGen:
self.fasta_dict = {x.name: x for x in records}
def read_csv(self) -> None:
- """Reads a given copy number csv file
+ """Read a given copy number csv file.
Wrapper for Pandas read_csv.
@@ -159,24 +159,27 @@ class CDNAGen:
"""
df_csv = pd.read_csv(self.cpn, index_col=False)
- df_csv = df_csv.reset_index() # make sure indexes pair with number of rows
+ df_csv = df_csv.reset_index() # make sure indexes pair with number of rows # noqa: E501
self.csv_df = df_csv
def read_gtf(self) -> None:
"""Read and process the GTF file.
- Reads a GTF file and determines copy numbers from normalized probabilities.
+ 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
+ # returns GTF with essential columns such as \
+ # "feature", "seqname", "start", "end"
+ # alongside the names of any optional keys \
+ # which appeared in the attribute column
gtf_df = read_gtf(self.gtf)
gtf_df["Binding_Probability"] = pd.to_numeric(
gtf_df["Binding_Probability"]
) # convert to numeric
- df_normalization_bind_probablility = gtf_df.groupby("seqname")[
+ df_norm_bind_prob = gtf_df.groupby("seqname")[
"Binding_Probability"
].sum() # extract binding probability
count = 0
@@ -194,7 +197,7 @@ class CDNAGen:
id_csv = str(row["seqname"]).split("_")[1]
# Calculate Normalized_Binding_Probability and add to GTF dataframe
gtf_df.loc[index, "Normalized_Binding_Probability"] = (
- row["Binding_Probability"] / df_normalization_bind_probablility[id_]
+ row["Binding_Probability"] / df_norm_bind_prob[id_]
)
# Calculate Normalized_Binding_Probability and add to GTF dataframe
csv_transcript_copy_number = self.csv_df.loc[
@@ -211,7 +214,7 @@ class CDNAGen:
self.gtf_df = gtf_df
def write_fasta(self) -> None:
- """Writes cDNA fasta records to file.
+ """Write cDNA fasta records to file.
Wrapper for SeqIO.write.
@@ -222,7 +225,7 @@ class CDNAGen:
print(f"Fasta file successfully written to: {self.output_fasta}")
def write_csv(self) -> None:
- """Writes the copy number information to a csv file.
+ """Write the copy number information to a csv file.
Wrapper for Pandas to_csv.
@@ -232,4 +235,5 @@ class CDNAGen:
self.gtf_df[["cdna_ID", "Transcript_Copy_Number"]].to_csv(
self.output_csv, index=False
)
- print(f"Copy number csv file successfully written to: {self.output_csv}")
+ print(f"Copy number csv file successfully written to: \
+ {self.output_csv}")