Skip to content

Updates to network file parser #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bcdaniels wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Updates to network file parser #5

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a002e4a
Added _ if statements
Nov 8, 2024
812485d
Got it working rejecting everything besides letters and #'s
Nov 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 50 additions & 23 deletions Code/singleic_ip/network_modifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,14 +5,13 @@
def remove_space_after_tab(line):
parts = line.split("\t")
if len(parts) > 1:
parts[1] = parts[1].strip() # Remove trailing whitespace
parts[1] = parts[1].strip() # Remove trailing whitespace
return "\t".join(parts)
else:
return line

# Function to get the directory of an additional file named "external.txt"
def get_directory_of_extra_file(input_file):

# Get the directory of the input file
file_directory = os.path.dirname(os.path.abspath(input_file))

Expand All @@ -27,83 +26,110 @@ def get_directory_of_extra_file(input_file):

# Function to modify the network rules in the input file and create a new file with modified rules
def network_modifier(input_file):

# Read the input file
with open(input_file, 'r') as f:
lines = f.readlines()
first_line = lines[0].strip() # Get the first line of the file
first_line = lines[0].strip() # Get the first line of the file

# Get the path of the additional gene network file
ext = get_directory_of_extra_file(input_file)

# If the additional file exists
if ext != "nothing":
with open(ext, 'r') as f:
ext_lines = f.readlines() # Read lines from the additional file

# Write modified network rules to a new file named "allowed_file.txt"
with open('allowed_file.txt', 'w') as f:

# Write header for the new file
f.write("Gene\tRule\n")

if first_line.startswith("Gene"):

# Iterate through lines in the input file, excluding the header
for line in lines[1:]:
words = line.split()

# Check if '_' in gene name, and if so, combine them
gene_name = words[0]
gene_name = "".join(ch for ch in gene_name if ch.isalnum())

words = line.split()

# Modify the line by removing '=' and replacing 'AND', 'OR', 'NOT'
modified_line = words[0] + '\t' + ' '.join(words[1:]).replace('=','')
modified_line = gene_name + '\t' + ' '.join(words[1:]).replace('=', '')

if 'AND' in modified_line:
modified_line = modified_line.replace('AND', 'and')
if 'OR' in modified_line:
modified_line = modified_line.replace('OR', 'or')
if 'NOT' in modified_line:
modified_line = modified_line.replace('NOT', 'not')

if '_' in modified_line:
modified_line = modified_line.replace('_', '')
if '-' in modified_line:
modified_line = modified_line.replace('-', '')


#modified_line = "".join(ch for ch in modified_line if ch.isalnum())
modified_line = remove_space_after_tab(modified_line)

# Write the modified line to the new file
f.write(modified_line + '\n')

# If the additional file exists
if ext != "nothing":
for gene in ext_lines:

words = gene.split()

# Check if '_' in gene name, and if so, combine them
gene_name = words[0]
gene_name = "".join(ch for ch in gene_name if ch.isalnum())

# Create a new line by enclosing the gene name in parentheses
extra_gene = words[0] + '\t' + '( ' + words[0] + ' )'
extra_gene = gene_name + '\t' + '( ' + gene_name + ' )'
f.write(extra_gene + '\n')

# If the first line does not start with "Gene"
else:

for line in lines:

words = line.split()

modified_line = words[0] + '\t' + ' '.join(words[1:]).replace('=','')
# Check if '_' in gene name, and if so, combine them
gene_name = words[0]
gene_name = "".join(ch for ch in gene_name if ch.isalnum())

# Modify the line by removing '=' and replacing 'AND', 'OR', 'NOT'
modified_line = gene_name + '\t' + ' '.join(words[1:]).replace('=', '')

if 'AND' in modified_line:
modified_line = modified_line.replace('AND', 'and')
if 'OR' in modified_line:
modified_line = modified_line.replace('OR', 'or')
if 'NOT' in modified_line:
modified_line = modified_line.replace('NOT', 'not')
if '_' in modified_line:
modified_line = modified_line.replace('_', '')
if '-' in modified_line:
modified_line = modified_line.replace('-', '')



#modified_line = "".join(ch for ch in modified_line if (ch.isalnum() or ch == " " or ch == ")" or ch == "("))
#modified_line = "".join(ch for ch in modified_line if ch.isalnum())
modified_line = remove_space_after_tab(modified_line)


# Write the modified line to the new file
f.write(modified_line + '\n')

if ext != "nothing":
for gene in ext_lines:

words = gene.split()

extra_gene = words[0] + '\t' + '( ' + words[0] + ' )'

# Check if '_' in gene name, and if so, combine them
gene_name = words[0]
gene_name = "".join(ch for ch in gene_name if ch.isalnum())

# Create a new line by enclosing the gene name in parentheses
extra_gene = gene_name + '\t' + '( ' + gene_name + ' )'
f.write(extra_gene + '\n')

# Return the path of the new file
Expand All @@ -116,3 +142,4 @@ def network_modifier(input_file):

# Print the path of the modified file
print(modified_file)