#!/usr/bin/env python
#
# Copyright 2009 Illumina, Inc.
#
# This software is covered by the "Illumina Genome Analyzer Software
# License Agreement" and the "Illumina Source Code License Agreement",
# and certain third party copyright/licenses, and any user of this
# source file is bound by the terms therein (see accompanying files
# Illumina_Genome_Analyzer_Software_License_Agreement.pdf and
# Illumina_Source_Code_License_Agreement.pdf and third party
# copyright/license notices).
#
# \author Chris Saunders
#
"""
usage: lsnp_summary.py < blt_output > extended_lsnp_output

Provides extended information on lsnp calls from the blt snp-caller,
in addition to the original output, this script lists the reference
allele frequency, the highest frequency allele and the second highest
frequency allele.
"""


import sys

refindex = {'A':0,'C':1,'G':2,'T':3}
refbase = ['A','C','G','T']

infp=sys.stdin
outfp=sys.stdout

for line in infp :
    w=line.strip().split()
    if w[0] != "LSNP" :
        outfp.write(line)
        continue
    ref=w[4]
    ri=refindex[ref]
    ref_freq=w[8+2*ri]
    freqs = []
    for a in range(4) :
        freqs.append((float(w[8+2*a]),refbase[a]))
    freqs.sort()
    freqs.reverse()

    outfp.write("%s freq(ref): %s max_allele: %s freq(max_allele): %.8f max2_allele: %s freq(max2_allele): %.8f\n"
                % (line.strip(),ref_freq,freqs[0][1],freqs[0][0],freqs[1][1],freqs[1][0]))