def wig_pipe(infile, outfile):
''' (infile, outfile)
Reads in a .bedfile formatted alignment file and returns a .wig formatted data file.
'''
import wig_scripts
bedfile = wig_scripts.read_tab_data(infile)
read_pos = wig_scripts.bedfile_to_read_pos(bedfile)
data = wig_scripts.count_reads(read_pos)
wig_scripts.wig_out(outfile, data)
def process_bedfile_for_HMM(infile1, infile2, outfile1):
''' (total_TA_pos.wig, TnSeq_read_pos.bedfile, tnseq_data.wig) -> write to tnseq_data.wig
This program reads in a .wig file of the 'TA' positions in the Rlv3841 replicon in question,
a bedfile of all reads from a TnSeq alignment, and combines the positon data from the bedfile
with the .wig list. It then prints out a file with the TnSeq data in a format useable by
the
'''
import wig_scripts
output = []
processed = 0
total_ta_pos = []
total_tnseq_pos = []
TA_in = wig_scripts.read_space_data(infile1)
TnSeq_in = wig_scripts.read_tab_data(infile2)
read_counts = wig_scripts.bedfile_to_read_pos(TnSeq_in)
header = TA_in.pop(0)
### Takes the position of every 'TA' and pushes it into a list in int format
for pos in TA_in:
ta = int(pos[0])
total_ta_pos.append(ta)
for read in read_counts:
value = int(read)
total_tnseq_pos.append(value)
for ta_site in total_ta_pos:
read_number = total_tnseq_pos.count(ta_site)
items =[]
items = [ta_site, read_number]
output.append(items)
processed = processed+1
outfile1.write(header[0] + ' ' + header[1] + '\n')
for result in output:
position = str(result[0])
count = str(result[1])
outfile1.write(position)
outfile1.write(' ')
outfile1.write(count)
outfile1.write('\n')
outfile1.close()
infile1.close()
infile2.close()