comparison allele-counts.py @ 2:318fdf77aa54

Current version, from another toolshed Includes change in header line

1:49bb46c3a1af

#!/usr/bin/python
# This parses the output of Dan's "Naive Variant Detector" (previously,
# "BAM Coverage"). It was forked from the code of "bam-coverage.py".
#
# New in this version: default to stdin and stdout, override by using -i and -o
#   to specify filenames
#
# TODO:
# - test handling of -c 0 (and -f 0?)
# - should it technically handle data lines that start with a '#'?
import os
import sys
from optparse import OptionParser

COLUMNS = ['sample', 'chr', 'pos', 'A', 'C', 'G', 'T', 'coverage', 'alleles',
  'major', 'minor', 'freq'] #, 'bias']
CANONICAL_VARIANTS = ['A', 'C', 'G', 'T']
USAGE = """Usage: cat variants.vcf | %prog [options] > alleles.csv
       %prog [options] -i variants.vcf -o alleles.csv"""
OPT_DEFAULTS = {'infile':'-', 'outfile':'-', 'freq_thres':1.0, 'covg_thres':100,
  'print_header':False, 'stdin':False}

  # set outfile_handle to either stdout or the output file
  if outfile == OPT_DEFAULTS.get('outfile'):
    outfile_handle = sys.stdout
  else:
    if os.path.exists(outfile):
      fail('Error: The given output filename '+outfile+' already exists.')
    else:
      outfile_handle = open(outfile, 'w')

  if print_header:
    outfile_handle.write('#'+'\t'.join(COLUMNS)+"\n")

  # main loop: process and print one line at a time
  sample_names = []
  for line in infile_handle:
    line = line.rstrip('\r\n')

        continue
      if variant[0] != '-' and variant[0] != '+':
        fail("Error in input VCF: variant data not strand-specific. "
          +"Failed on line:\n"+line)
      try:
        variant_counts[variant] = int(reads)
      except ValueError, e:
        continue

    sample_counts[sample_names[i]] = variant_counts

  site['samples'] = sample_counts

      sample['major']  = ranked_bases[0][0]
    except IndexError, e:
      sample['major']  = '.'
    try:
      sample['minor']  = ranked_bases[1][0]
      sample['freq']   = ranked_bases[1][1] / float(coverage)
    except IndexError, e:
      sample['minor']  = '.'
      sample['freq']   = 0.0

    site_summary.append(sample)

2:318fdf77aa54

#!/usr/bin/python
# This parses the output of Dan's "Naive Variant Detector" (previously,
# "BAM Coverage"). It was forked from the code of "bam-coverage.py".
#
# New in this version:
#   Made header line customizable
#     - separate from internal column labels, which are used as dict keys
#
# TODO:
# - test handling of -c 0 (and -f 0?)
# - should it technically handle data lines that start with a '#'?
import os
import sys
from optparse import OptionParser

COLUMNS = ['sample', 'chr', 'pos', 'A', 'C', 'G', 'T', 'coverage', 'alleles', 'major', 'minor', 'freq'] #, 'bias']
COLUMN_LABELS = ['SAMPLE', 'CHR',  'POS', 'A', 'C', 'G', 'T', 'CVRG', 'ALLELES', 'MAJOR', 'MINOR', 'MINOR.FREQ.PERC.'] #, 'STRAND.BIAS']
CANONICAL_VARIANTS = ['A', 'C', 'G', 'T']
USAGE = """Usage: cat variants.vcf | %prog [options] > alleles.csv
       %prog [options] -i variants.vcf -o alleles.csv"""
OPT_DEFAULTS = {'infile':'-', 'outfile':'-', 'freq_thres':1.0, 'covg_thres':100,
  'print_header':False, 'stdin':False}

  # set outfile_handle to either stdout or the output file
  if outfile == OPT_DEFAULTS.get('outfile'):
    outfile_handle = sys.stdout
  else:
    try:
      outfile_handle = open(outfile, 'w')
    except IOError, e:
      fail('Error: The given output filename '+outfile+' could not be opened.')

  if len(COLUMNS) != len(COLUMN_LABELS):
    fail('Error: Internal column names do not match column labels.')
  if print_header:
    outfile_handle.write('#'+'\t'.join(COLUMN_LABELS)+"\n")

  # main loop: process and print one line at a time
  sample_names = []
  for line in infile_handle:
    line = line.rstrip('\r\n')

        continue
      if variant[0] != '-' and variant[0] != '+':
        fail("Error in input VCF: variant data not strand-specific. "
          +"Failed on line:\n"+line)
      try:
        variant_counts[variant] = int(float(reads))
      except ValueError, e:
        fail("Error in input VCF: Variant count not a valid number. Failed on variant count string '"+reads+"'\nIn the following line:\n"+line)

    sample_counts[sample_names[i]] = variant_counts

  site['samples'] = sample_counts

      sample['major']  = ranked_bases[0][0]
    except IndexError, e:
      sample['major']  = '.'
    try:
      sample['minor']  = ranked_bases[1][0]
      sample['freq']   = round(ranked_bases[1][1]/float(coverage), 5)
    except IndexError, e:
      sample['minor']  = '.'
      sample['freq']   = 0.0

    site_summary.append(sample)