# 10/10/07: by Cheng
# convert Affy SNP annotation file to dchip genome information file, and reorder
# SNPs according to cdf file order ("Mapping250K_Sty psi.txt", which can be found in
# the library files containing the CDF file)

#openfile = open("Mapping250K_Sty.na23.annot.csv", "r")
openfile = open("Mapping250K_Nsp.na23.annot.csv", "r")


#outfile = open("Mapping250k_Sty_genome_info_hg18.txt", "w")
outfile = open("Mapping250k_Nsp_genome_info_hg18.txt", "w")

#define a dictionary to store SNP information
info = {}

line_cnt = 0
for line in openfile:
    if not (line[0] == '#' or line[1] == '#'):
        line = line.replace('\"', '')
        words = line.split(",")
        #print words[0:6]
        outline = words[0] + "\t" + words[3]+ "\t" + words[4]+ "\t\t" + \
            words[5] + "\t" + words[2] + "\n"
        info[words[0]] = outline # add snp information

        if line_cnt == 0: #headerline
            outfile.write(outline)

        if (line_cnt % 1000 == 0):
            print line_cnt
        line_cnt += 1

openfile.close()

#openfile = open("Mapping250K_Sty psi.txt", "r")
openfile = open("Mapping250K_Nsp psi.txt", "r")
line_cnt = 0
for line in openfile:
    if line[0] != '#':
        words = line.split("\t")
        if info.has_key(words[1]):
            #print words[1], info[words[1]],
            outfile.write(info[words[1]])

        if (line_cnt % 1000 == 0):
            print line_cnt
        line_cnt += 1

openfile.close()
outfile.close()