def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
# get cmd-line options
fasta_fp=opts.input_fasta_fp
qual_fp=opts.input_qual_fp
output_dir=opts.output_dir
# create output dir
create_dir(output_dir)
output_fps={}
# open sequence files
sequences=MinimalFastaParser(open(fasta_fp,'U'))
qual_sequences=MinimalFastaParser(open(qual_fp,'U'))
# iterate over seqs
for seq_name,seq in sequences:
# iterate over qual
qual_seq_name,qual_seq=qual_sequences.next()
# verify headers from seq and qual match
if seq_name==qual_seq_name:
# get the SampleID
samp_id='_'.join(seq_name.split()[0].split('_')[:-1])
samp_filename='seqs_%s' % (str(samp_id))
# open files for output
if not output_fps.has_key(str(samp_filename)):
output_fps[str(samp_filename)] = open(join(output_dir,
'%s.fastq' % (str(samp_filename))),'w')
# write out the fastq format for seqs
output_fps[str(samp_filename)].write('@%s\n%s\n+\n%s\n' % \
(seq_name,seq,qual_seq))
else:
print seq_name
# close the files
for s_id in output_fps:
output_fps[str(s_id)].close()
def generate_full_split_lib_fastq(study, study_input_dir, zip_fname,
files_to_remove,output_dir):
""" Generate the full split-library fastq file """
# define sequence output file
seq_fname='study_%s_split_library_seqs.fastq.gz' % (str(study))
fna_fname='study_%s_split_library_seqs.fna.gz' % (str(study))
output_seq_fp=join(output_dir,seq_fname)
output_fna_fp=join(output_dir,fna_fname)
# add to list of files to remove
files_to_remove.append(output_seq_fp)
files_to_remove.append(output_fna_fp)
output_seqs=gzip.open(output_seq_fp,'w')
output_fna=gzip.open(output_fna_fp,'w')
iterator=0
# get a list of all files in study_dir
processed_folders=listdir(study_input_dir)
samples={}
biom_files=[]
for processed_folder in processed_folders:
# determine if the file startswith the word "processed"
if processed_folder.startswith('processed'):
# define split-lib seq fp
split_lib_seqs=join(study_input_dir,processed_folder,
'split_libraries','seqs.fna')
# open sequence files
seqs=MinimalFastaParser(open(split_lib_seqs,'U'))
try:
# for illumina
split_lib_qual=join(study_input_dir,processed_folder,
'split_libraries','seqs.qual')
# open sequence files
qual_sequences=MinimalFastaParser(open(split_lib_qual,'U'))
except:
# for 454
split_lib_qual=join(study_input_dir,processed_folder,
'split_libraries','seqs_filtered.qual')
# open sequence files
qual_sequences=MinimalFastaParser(open(split_lib_qual,'U'))
# open split-lib seq fp
seqs=MinimalFastaParser(open(split_lib_seqs,'U'))
# iterate over sequences
for seq_name,seq in seqs:
# update sequence numbers since they may cause issues across
# multiple split-lib runs
qual_seq_name,qual_seq=qual_sequences.next()
if seq_name==qual_seq_name:
full_seq_name_list=seq_name.split()
seq_name_prefix='_'.join(full_seq_name_list[0].split('_')[:-1])
# get per sample sequence counts
if seq_name_prefix in samples:
samples[seq_name_prefix]=samples[seq_name_prefix]+1
else:
samples[seq_name_prefix]=1
# update the sequence name, but retain barcode info
updated_seq_name=seq_name_prefix + '_' + str(iterator) + \
' ' + ' '.join(full_seq_name_list[1:])
# write the sequence out in FASTA format
output_seqs.write('@%s\n%s\n+\n%s\n' % \
(str(updated_seq_name), str(seq), str(qual_seq)))
# write the sequence out in FASTA format
output_fna.write('>%s\n%s\n' % (str(updated_seq_name),
str(seq)))
iterator=iterator+1
else:
print seq_name
# get list of biom files
gg_biom_fp=join(study_input_dir,processed_folder,
'gg_97_otus','exact_uclust_ref_otu_table.biom')
if exists(gg_biom_fp) and getsize(gg_biom_fp)>0:
biom_files.append(gg_biom_fp)
output_seqs.close()
output_fna.close()
# zip the full split-library sequence file
#cmd_call='cd %s; tar rzvf %s %s' % (study_input_dir,zip_fname,seq_fname)
#cmd_call='cd %s; tar rzvf %s %s' % (study_input_dir,zip_fname,fna_fname)
#system(cmd_call)
return files_to_remove, biom_files, samples
