filename = '/Users/t/dev/2012-scripps/python/25k.fq.gz'

import screed
for record in screed.open('/Users/t/dev/2012-scripps/python/25k.fq.gz'):
   print record.name
   print record.sequence
   print record.accuracy
   break

for record in screed.open(filename):
   if record.name == '@895:1:4:1596:8538/2':
      break
        
        
print record

list_of_names = ['895:1:4:1596:8538/2', '895:1:4:1596:6003/2']
list_of_records = []

for record in screed.open(filename):
    if record.name in list_of_names:
        list_of_records.append(record)

list_of_records

%%file list-of-seqs.txt
895:1:4:1596:8538/2
895:1:4:1596:6003/2

x = []
for line in open('list-of-seqs.txt'):
    line = line.strip()
    x.append(line)
x

list_of_names = x
list_of_records = []

for record in screed.open(filename):
    if record.name in list_of_names:
        list_of_records.append(record)

list_of_records

n = 0.0
m = 0.0
for record in screed.open(filename):
   n += len(record.sequence) - record.sequence.count('N')
   m += record.sequence.count('G') + record.sequence.count('C')

print '%g G/C content from %d and %d' % (m / n, m, n)  # string interpolation in Python
print '%g G/C content' % (m / n,)  # string interpolation in Python

print m/n, 'G/C content'

outfp = open('/tmp/out.fa', 'w')
for record in screed.open(filename):
   outfp.write('>%s\n%s\n' % (record.name, record.sequence))

pwd