Messing with 23andme raw exported data

snp.py

import sys

# Parse an exported raw genome data file from 23andme.com, wihch is basically
# one SNP per line. Each SNP is looked up in a small dictionary of
# "interesting" genes, like the ones related to celiac disease,
# lactointolerance, or obesity.  The first and only arg is the name of the file
# (umcompressed).

db = {'rs2187668': {'geno':
                        {'AA': 'Autoimmune disorder risk (lupus, celiac disease) due to 2 HLA-DRB1*0301 alleles',
                         'AG': 'Somewhat increased autoimmune disorder (lupus, celiac disease) risk; 1 HLA-DRB1*0301 allele',
                         'GG': 'average'},
                    'url':'https://www.snpedia.com/index.php/Rs2187668'},
      'rs3184504': {'geno':
                        {'CC':'normal',
                         'CT':'increased risk for celiac disease',
                         'TT':'increased risk for celiac disease'},
                    'url':'https://www.snpedia.com/index.php/Rs3184504'},
      'rs6822844': {'geno':
                        {'GG': 'increased risk for celiac disease. Common on affy axiom data',
                         'GT': 'n/a',
                         'TT': 'n/a'},
                    'url': 'https://www.snpedia.com/index.php/Rs6822844'},
      'rs4988235': {'geno':
                        {'CC': 'likely to be lactose intolerant as an adult',
                         'CT': 'likely to be able to digest milk as an adult',
                         'TT': 'can digest milk'},
                    'url': 'https://www.snpedia.com/index.php/Rs4988235'},
      'rs182549': {'geno':
                        {'CC': 'possibly lactose intolerant',
                         'CT': 'Can digest milk.',
                         'TT':'Can digest milk.'},
                    'url': 'https://www.snpedia.com/index.php/Rs182549'},
      'rs1799971': {'geno':
                        {'AA': 'normal',
                         'AG': '2.5 stronger cravings for alcohol. if alcoholic, naltrexone treatment 2x more successful',
                         'GG': 'more pain'},
                    'url': 'https://www.snpedia.com/index.php/Rs1799971'},
      'rs9939609': {'geno':
                        {'AA': 'obesity risk and 1.6x risk for Type-2 diabetes',
                         'AT': 'risk for Type-2 diabetes; obesity risk',
                         'TT': 'lower risk of obesity and Type-2 diabetes'},
                    'url': 'https://www.snpedia.com/index.php/Rs1799971'}
      }

infile = sys.argv[1]

print '#%-9s %-10s %-10s' % ('marker','chromosome', 'genotype')

with open(infile) as inf:
    for line in inf:
        if line[0] == '#':
            continue

        rsid, chromosome, position, genotype = line.split()
        if db.has_key(rsid):
            if db[rsid]['geno'].has_key(genotype):
                print '%-10s %-10s %-10s %s (%s)' % (rsid, chromosome, genotype,
                                              db[rsid]['geno'][genotype], db[rsid]['url'])
            else:
                print '%-10s %-10s %-10s %s (%s)' % (rsid, chromosome, genotype, '??', db[rsid]['url'])