template.application_select(['Pfam', 'Panther', 'SignalP'])
template.output_select = 'json'
template.poll_time = 60
template.poll_max = 100
sequence_limit = 20
batch_limit = 5
n_sequence = 0
nskip = 60
s = 0
while fasta.next():
while s < nskip:
s += 1
fasta.next()
if fasta.length() < args.minlen: continue # skip short sequences
if n_sequence >= sequence_limit: break # run up to sequence_limit queries
n_sequence += 1
# copy the template and add the sequence information
ips = template.clone()
ips.sequence = fasta.translate().seq.rstrip('*').format(linelen=60)
ips.jobname = fasta.id
ips.title = 'ORF{}'.format(n_sequence)
joblist[ips] = 'new'
# submit job
if ips.run():
joblist[ips] = 'submitted'
if n_sequence % batch_limit and n_sequence < sequence_limit:
fasta = Fasta()
fasta.fh = cl.fasta_file
trimre = re.compile(trim)
# initialize counters
base_total = 0
base_current = 0
n_out = 0
n_seq = 0
n_current = 0
while fasta.next():
if trimre: fasta.trimDocByRegex(trimre)
if not n_seq or base_current + fasta.length() > maxbases:
# if number of bases would be greater than cutoff after adding the new sequence
# close current output file, open new
# report statistics for old file
# reset current file counters
try:
# prevents error on first pass - file is not yet open
outfile.close()
print(' ', base_current, 'bases/amino acids', end=' ')
print('in', n_current, 'sequences', end=' ')
print('written to', outfilename)
except NameError:
pass
base = base.replace('.seq', '')
sys.stdout.write('\n\tExpanded file: {}\n\tbasename: {}\n'.format(
infilename, base))
outfilename = base + '.fasta'
outfile = None
try:
outfile = open(outfilename, 'w')
except:
sys.stderr.write(
'Unable to open output file ({})\n'.format(outfilename))
exit(2)
# process all sequences in the file
n = 0
for seq in infile:
fasta = Fasta()
fasta.id = base + '_{}'.format(n)
fasta.seq = seq.rstrip().upper()
fasta.doc = 'length={}'.format(fasta.length())
outfile.write(fasta.format(linelen=100))
n += 1
infile.close()
outfile.close()
sys.stdout.write('\t{} sequences written to {}\n'.format(
n, outfilename))
# end of loop over files
exit(0)