diff --git a/tests/test_transcript_structure.py b/tests/test_transcript_structure.py
index 877112cd23e3f31a91f6559467309debf56d8117..3535d8fcc228f0f79687f05ffdb2f72af5ae8622 100644
--- a/tests/test_transcript_structure.py
+++ b/tests/test_transcript_structure.py
@@ -22,7 +22,7 @@ P_INTRON_1: float = 1
)
def test_csv_2_dict(test_input):
builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
- builder.csv_2_dict()
+ builder.__csv_2_dict()
with open(TEST_CSV_TITLE) as csv:
csv_lines = csv.readlines()
first_line = csv_lines[0].split(',')
@@ -38,7 +38,7 @@ def test_csv_2_dict(test_input):
def test_gtf_2_dict():
builder = Gts.BuildTranscriptStructure(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0)
- builder.gtf_2_dict()
+ builder.__gtf_2_dict()
assert len(builder.gene_sequences_dict) == 2 # Two genes read in the dictionary.
assert len(builder.gene_sequences_dict[GENE_KEYS[0]]) == 5
assert len(builder.gene_sequences_dict[GENE_KEYS[1]]) == 5
@@ -63,9 +63,9 @@ def test_gtf_2_dict():
)
def test_make_new_transcripts(test_input):
builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
- builder.csv_2_dict() # Generates dictionary from gene count csv file.
- builder.gtf_2_dict() # Generates dictionary from gtf file.
- builder.make_new_transcripts() # Generates the differently spliced transcripts.
+ builder.__csv_2_dict() # Generates dictionary from gene count csv file.
+ builder.__gtf_2_dict() # Generates dictionary from gtf file.
+ builder.__make_new_transcripts() # Generates the differently spliced transcripts.
numb_trans_dict = 0
numb_trans_csv = 10
@@ -86,10 +86,10 @@ def test_make_new_transcripts(test_input):
)
def test_make_gtf_lines(test_input):
builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
- builder.csv_2_dict() # Generates dictionary from gene count csv file.
- builder.gtf_2_dict() # Generates dictionary from gtf file.
- builder.make_new_transcripts() # Generates the differently spliced transcripts.
- builder.make_gtf_info()
+ builder.__csv_2_dict() # Generates dictionary from gene count csv file.
+ builder.__gtf_2_dict() # Generates dictionary from gtf file.
+ builder.__make_new_transcripts() # Generates the differently spliced transcripts.
+ builder.__make_gtf_info()
for line in builder.gtf_lines:
columns = line.split('\t')
assert columns[3] < columns[4] # Tests that the coordinates are increasing.
@@ -104,10 +104,10 @@ def test_make_gtf_lines(test_input):
)
def test_sort_gtf_lines(test_input):
builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
- builder.csv_2_dict() # Generates dictionary from gene count csv file.
- builder.gtf_2_dict() # Generates dictionary from gtf file.
- builder.make_new_transcripts() # Generates the differently spliced transcripts.
- builder.make_gtf_info()
+ builder.__csv_2_dict() # Generates dictionary from gene count csv file.
+ builder.__gtf_2_dict() # Generates dictionary from gtf file.
+ builder.__make_new_transcripts() # Generates the differently spliced transcripts.
+ builder.__make_gtf_info()
starts_before = [] # Verifies that the function actually has to sort.
for line in builder.gtf_lines:
@@ -116,9 +116,9 @@ def test_sort_gtf_lines(test_input):
starts_before.append(columns[3])
for ii in range(len(starts_before)-1):
assert starts_before[ii] > starts_before[ii+1]
- builder.sort_gtf_lines()
+ builder.__sort_gtf_lines()
- builder.sort_gtf_lines()
+ builder.__sort_gtf_lines()
starts_after = [] # Verifies that the function sorted.
for line in builder.gtf_lines:
columns = line.split('\t')
@@ -126,7 +126,7 @@ def test_sort_gtf_lines(test_input):
starts_after.append(columns[3])
for ii in range(len(starts_before)-1):
assert starts_after[ii] < starts_after[ii+1]
- builder.sort_gtf_lines()
+ builder.__sort_gtf_lines()
def test_write_gtf():
diff --git a/transcript_structure/Generate_transcript_structure.py b/transcript_structure/Generate_transcript_structure.py
index 82558f451126c67bcc0a20f27c85fecf22b8be3f..bf491701edc078cd4a630c53d6726742f2e6b27e 100644
--- a/transcript_structure/Generate_transcript_structure.py
+++ b/transcript_structure/Generate_transcript_structure.py
@@ -32,6 +32,7 @@ class BuildTranscriptStructure:
E.g. '01' means the intron between original (fully spliced) exon 1 and exon 2 was spliced away,
but the intron between exon 2 and exon 3 is included in the transcript.
gtf_lines(list): List with all newly created gtf lines.
+ _transcripts_generated(bool): Indicates whether splicing was conducted or not yet.
"""
def __init__(self,
@@ -47,16 +48,18 @@ class BuildTranscriptStructure:
self.gene_sequences_dict = {}
self.gene_transcript_dict = {}
self.gtf_lines = []
+ self._transcripts_generated = False
def generate_transcript_structure(self):
"""Computes distribution and gene coordinates of differently spliced mRNA."""
- self.csv_2_dict() # Generates dictionary from gene count csv file.
- self.gtf_2_dict() # Generates dictionary from gtf file.
- self.make_new_transcripts() # Generates the differently spliced transcripts.
- self.make_gtf_info() # Builds the gtf file of all newly created transcripts.
- self.sort_gtf_lines() # Sorts the gtf file by gene occurrence in sequence.
-
- def csv_2_dict(self) -> None:
+ self.__csv_2_dict() # Generates dictionary from gene count csv file.
+ self.__gtf_2_dict() # Generates dictionary from gtf file.
+ self.__make_new_transcripts() # Generates the differently spliced transcripts.
+ self.__make_gtf_info() # Builds the gtf file of all newly created transcripts.
+ self.__sort_gtf_lines() # Sorts the gtf file by gene occurrence in sequence.
+ self._transcripts_generated = True # Adapts state variable.
+
+ def __csv_2_dict(self) -> None:
"""Converts the csv file with gene count into a dictionary."""
with open(self.gene_count) as g_c:
lines = g_c.readlines()
@@ -69,7 +72,7 @@ class BuildTranscriptStructure:
line_entries = line.split(',')
self.gene_count_dict[line_entries[0]] = int(line_entries[1])
- def gtf_2_dict(self) -> None:
+ def __gtf_2_dict(self) -> None:
"""Converts the gtf file into a nested dictionary."""
with open(self.input_coords) as c_g: # Reads coordinates from .gtf file.
lines = c_g.readlines()
@@ -106,7 +109,7 @@ class BuildTranscriptStructure:
gene_info['exon_seq'] = coordinates
self.gene_sequences_dict[gene_name] = gene_info
- def make_new_transcripts(self) -> None:
+ def __make_new_transcripts(self) -> None:
""" Generates the differently spliced transcripts."""
for gene in self.gene_count_dict:
@@ -132,24 +135,7 @@ class BuildTranscriptStructure:
self.gene_transcript_dict[gene] = transcript_numbers
- def write_csv(self,
- output_transcript_count: str
- ) -> None:
-
- """ Writes a csv file containing the number of differently spliced transcripts.
-
- Args:
- output_transcript_count(str): Path and name of the output cvs file: "transcript_ID", "gene_ID", count.
- """
-
- with open(output_transcript_count, 'w', newline='') as file:
- writer = csv.writer(file)
- writer.writerow(['Transcript_ID', 'Gene_ID', 'count'])
- for gene in self.gene_transcript_dict:
- for transcript_ID in self.gene_transcript_dict[gene]:
- writer.writerow([transcript_ID, gene, self.gene_transcript_dict[gene][transcript_ID]])
-
- def make_gtf_info(self) -> None:
+ def __make_gtf_info(self) -> None:
""" Writes the lines of the new gtf file for the differently spliced transcripts."""
for gene in self.gene_transcript_dict: # Iterates over all genes required.
self.gtf_lines.append(self.gene_sequences_dict[gene]['gene_line']) # Add gene line to list.
@@ -202,7 +188,7 @@ class BuildTranscriptStructure:
exon_lines.reverse()
self.gtf_lines.extend(exon_lines)
- def sort_gtf_lines(self) -> None:
+ def __sort_gtf_lines(self) -> None:
""" Sorts the gtf lines by the position of the genes (increasing) and returns it."""
@@ -225,16 +211,33 @@ class BuildTranscriptStructure:
self.gtf_lines = sorted_gtf_lines
+ def write_csv(self,
+ csv_output: str
+ ) -> None:
+
+ """ Writes a csv file containing the number of differently spliced transcripts.
+
+ Args:
+ csv_output(str): Path and name of the output cvs file: "transcript_ID", "gene_ID", count.
+ """
+
+ with open(csv_output, 'w', newline='') as file:
+ writer = csv.writer(file)
+ writer.writerow(['Transcript_ID', 'Gene_ID', 'count'])
+ for gene in self.gene_transcript_dict:
+ for transcript_ID in self.gene_transcript_dict[gene]:
+ writer.writerow([transcript_ID, gene, self.gene_transcript_dict[gene][transcript_ID]])
+
def write_gtf(self,
- output_coords: str
+ gtf_output: str
) -> None:
""" Writes a gtf file with the information about the differently spliced transcripts.
Args:
- output_coords(str): Path and name of the output gtf file with the information of all relevant transcripts.
+ gtf_output(str): Path and name of the output gtf file with the information of all relevant transcripts.
"""
- with open(output_coords, 'w') as gtf_file:
+ with open(gtf_output, 'w') as gtf_file:
gtf_file.writelines(self.gtf_lines)
@@ -254,11 +257,7 @@ def main():
random.seed(10) # Initializes seed for random functions for reproducibility.
bts = BuildTranscriptStructure(gene_count, coordinates_genes, p_intron)
- bts.csv_2_dict() # Generates dictionary from gene count csv file.
- bts.gtf_2_dict() # Generates dictionary from gtf file.
- bts.make_new_transcripts() # Generates the differently spliced transcripts.
- bts.make_gtf_info() # Builds the gtf file of all newly created transcripts.
- bts.sort_gtf_lines() # Sorts the gtf file by gene occurrence in sequence.
+ bts.generate_transcript_structure() # Creates the transcript structures.
bts.write_gtf(name_gtf_output) # Writes the new gtf file.
bts.write_csv(name_csv_output) # Writes the new csv file with the count of the transcripts.