def test_file_reader_fasta(self):
'''file_reader should iterate through a fasta file correctly'''
reader = fastn.file_reader('fastn_unittest.fa')
counter = 1
for seq in reader:
self.assertEqual(seq, fastn.Fasta(str(counter), 'ACGTA'))
counter += 1
def get_gaps_and_lengths(infile):
seq_reader = fastn.file_reader(infile)
lengths = {}
gaps = {}
for seq in seq_reader:
assert seq.id not in lengths
lengths[seq.id] = len(seq)
gaps[seq.id] = seq.gaps()
return lengths, gaps
def test_print_line_length(self):
'''__str__ should be formatted correctly with the right number of chars per line of sequence'''
line_lengths = [0, 3]
correct_files = [
'fastn_unittest_one-per-line.fa', 'fastn_unittest_3-per-line.fa'
]
for i in range(len(line_lengths)):
seq_reader = fastn.file_reader('fastn_unittest_one-per-line.fa')
fastn.Fasta.line_length = line_lengths[i]
tmp_out = 'tmp.line_length_test.fa'
f = utils.open_file_write(tmp_out)
for s in seq_reader:
print(s, file=f)
utils.close(f)
self.assertTrue(filecmp.cmp(correct_files[i], tmp_out))
os.unlink(tmp_out)
fastn.Fasta.line_length = 60
#!/usr/bin/env python3.3
import argparse
import fastn
import utils
parser = argparse.ArgumentParser(
description='Gets all IDs from a fasta or fastq file',
usage='%(prog)s <infile> <outfile>')
parser.add_argument('infile', help='Name of fasta/q file to be read')
parser.add_argument('outfile', help='Name of output file')
options = parser.parse_args()
seq_reader = fastn.file_reader(options.infile)
f_out = utils.open_file_write(options.outfile)
for seq in seq_reader:
print(seq.id, file=f_out)
utils.close(f_out)
if sam_record.cigar.operations[0].operator == 'S':
hit_start = sam_record.cigar.operations[0].number
if sam_record.cigar.operations[-1].operator == 'S':
hit_end = len(sam_record.seq) - sam_record.cigar.operations[-1].number
if sam_record.id not in read_hit_coords:
read_hit_coords[sam_record.id] = []
read_hit_coords[sam_record.id].append(genome_intervals.Interval(hit_start - 1, hit_end - 1))
external_progs.bwa_index_clean(bwa_index)
os.unlink(bwa_sam)
seq_reader = fastn.file_reader(options.reads_in)
f_fa = utils.open_file_write(options.outprefix + '.fq')
f_log = utils.open_file_write(options.outprefix + '.log')
for seq in seq_reader:
if seq.id not in read_hit_coords:
print(seq, file=f_fa)
print(seq.id, 'no hit', sep='\t', file=f_log)
else:
hits = read_hit_coords[seq.id]
genome_intervals.merge_overlapping_in_list(hits)
i = 0
while i < len(hits) - 1:
if hits[i+1].start - hits[i].end <= options.join_distance:
hits[i] = hits[i].union_fill_gap(hits[i+1])
for id in clusters[i]:
seq = all_seqs[id]
if strands[id] == '-':
seq = copy.copy(all_seqs[id])
seq.revcomp()
else:
seq = all_seqs[id]
print(seq, file=f)
utils.close(f)
utils.syscall('cap3 ' + reads_file)
singlet_count = fastn.count_sequences(reads_file + '.cap.singlets')
contig_count = fastn.count_sequences(reads_file + '.cap.contigs')
if singlet_count == 0 and contig_count == 1:
seq_reader = fastn.file_reader(reads_file + '.cap.contigs')
for seq in seq_reader:
seq.id = 'cluster.' + str(i + 1) + '.contig'
assembled_seqs.append(copy.copy(seq))
for e in [
'ace', 'contigs.links', 'contigs.qual', 'info', 'singlets',
'contigs'
]:
os.unlink(reads_file + '.cap.' + e)
os.unlink(reads_file)
else:
print('Got',
singlet_count,
'singlets and',
contig_count,
def test_file_reader_fastq(self):
'''file_reader should iterate through a fastq file correctly'''
reader = fastn.file_reader('fastn_unittest_good_file.fq')
for seq in reader:
self.assertEqual(seq, fastn.Fastq('ID', 'ACGTA', 'IIIII'))
parser = argparse.ArgumentParser(
description=
'Given a nucmer coords file, reports the regions of the query that have no nucmer hit. Doesn'
't report gaps - i.e. assumes that all gaps had a hit.',
usage='%(prog)s [options] <nucmer.coords> <query.fasta/q> <outfile>')
parser.add_argument('nucmer_coords',
help='Name of nucmer coords file',
metavar='nucmer.coords')
parser.add_argument('query_file',
help='Name of query fasta or fastq file',
metavar='query.fasta/q')
parser.add_argument('outfile', help='Name of output file')
options = parser.parse_args()
seq_reader = fastn.file_reader(options.query_file)
seq_lengths = {} # id -> sequence length
covered_regions = {} # id -> list of covered regions
# get query sequence lengths and gap positions - add each gap coord to the
# list of covered positions for each sequence
for seq in seq_reader:
assert seq.id not in seq_lengths
seq_lengths[seq.id] = len(seq)
covered_regions[seq.id] = seq.gaps()
nucmer_reader = nucmer.file_reader(options.nucmer_coords)
for hit in nucmer_reader:
assert hit.qry_name in seq_lengths
#!/usr/bin/env python3.3
import argparse
import fastn
import utils
parser = argparse.ArgumentParser(
description = 'Converts a fastq file to fasta + qual file',
usage = '%(prog)s [options] <fastq_in> <fasta_out>')
parser.add_argument('fastq_in', help='Name of input fastq file')
parser.add_argument('fasta_out', help='Name of output fasta (fasta_out.qual will also be created)')
options = parser.parse_args()
seq_reader = fastn.file_reader(options.fastq_in)
fasta_out = utils.open_file_write(options.fasta_out)
qual_out = utils.open_file_write(options.fasta_out + '.qual')
fastn.Fasta.line_length = 0
for seq in seq_reader:
fa, qual = seq.to_Fasta_and_qual()
print(fa, file=fasta_out)
print('>' + fa.id, ' '.join([str(x) for x in qual]), sep='\n', file=qual_out)
utils.close(fasta_out)
utils.close(qual_out)
parser = argparse.ArgumentParser(
description=
'Takes a random subset of reads from a fasta/q file and optionally the corresponding read '
+ 'from a mates file. Ouptut is interleaved if mates file given',
usage=
'%(prog)s [options] <fasta/q in> <outfile> <percent reads wanted in [0,100]>'
)
parser.add_argument('--mate_file', help='Name of fasta/q mates file')
parser.add_argument('infile', help='Name of fasta/q file to be read')
parser.add_argument('outfile', help='Name of fasta/q output file')
parser.add_argument('read_percent',
type=int,
help='percent of reads to take from input file')
options = parser.parse_args()
seq_reader = fastn.file_reader(options.infile)
fout = utils.open_file_write(options.outfile)
counter_in = 0
counter_out = 0
if options.mate_file:
mate_seq_reader = fastn.file_reader(options.mate_file)
for seq in seq_reader:
counter_in += 1
if options.mate_file:
try:
mate_seq = next(mate_seq_reader)
except StopIteration:
print('Error! Didn\'t get mate for read', seq.id, file=sys.stderr)
sys.exit(1)
