#! /usr/bin/env python
"""
This program takes one DNA sequence as an argument, prints the reverse-complement.
Weronika Patena, nov2008
"""
import complement
### The actual reverse-complement function:
def reverse_complement(input_sequence,input_type=''):
# use the complement function from the complement module
complement_seq = complement.complement(input_sequence,input_type)
# easy reverse method: full list slice with a step of -1
reverse_complement_seq = complement_seq[::-1]
return reverse_complement_seq
### If called directly:
# try reading the argument; if none given, read from stdin (which is what makes it work with pipes (echo ctcgag | script.py) and when called on a selection in vi and such).
if __name__ == '__main__':
import read_input,transform_sequence_input,parse_fasta
# check if input is a list of files (i.e. if first arg is a valid filename - good enough)
input = read_input.read_input()
# transform_sequence_input takes an input AND the function to apply to it - in this case rev-compl
for line in transform_sequence_input.transform_sequence_input(input,reverse_complement):
parse_fasta.print_seq(line)
for seq_type in DNA, RNA:
complement_table[seq_type] = string.maketrans(
original_bases[seq_type], complement_bases[seq_type])
return complement_table
# When called/imported, always set up the complement table
complement_table = complement_table_setup()
### The actual complement function
def complement(input_sequence, input=''):
# if input type isn't given, detect RNA/DNA sequence type (default to DNA)
if input == 'DNA': input_type = DNA
elif input == 'RNA': input_type = RNA
else:
if input_sequence.count('U') > 0: input_type = RNA
elif input_sequence.count('u') > 0: input_type = RNA
else: input_type = DNA
complement_seq = input_sequence.translate(complement_table[input_type])
return complement_seq
### If called directly, read, parse and complement the input.
if __name__ == '__main__':
import read_input, transform_sequence_input, parse_fasta
input = read_input.read_input()
for line in transform_sequence_input.transform_sequence_input(
input, complement):
parse_fasta.print_seq(line)
# as an argument), process them, and keep the remaining content.
# Otherwise just transform each line.
def transform_sequence_input(full_input, transform_function):
output = []
# check whether the input is fasta-formatted or just sequence
# full_input is a list of lines, so convert it to string or this won't work
if str(full_input).count('>')>0: fasta = True
else: fasta = False
if debug: print '\n\t### INPUT:\n%s\t### END_INPUT\n'%full_input
if fasta:
for (header,seq) in parse_fasta.parse_fasta(full_input):
output.append((header,transform_function(seq)))
else:
for line in full_input:
output.append(transform_function(line))
if debug: print '\n\t######### FINAL OUTPUT: #########'%output
return output
### Just a basic swapcase function to test the transform_sequence_input function
def swap_case(line):
return line.swapcase()
### If called directly, test everything
if __name__ == '__main__':
input = read_input()
# use nice printing for fasta (header,seq) tuples, or normal for text lines
try:
for (header,seq) in transform_sequence_input(input,swap_case): parse_fasta.print_seq(header,seq)
except ValueError:
for line in transform_sequence_input(input,swap_case): print line