def write_assembly_statistics(assembly, outdir):
"""
Write assembly statistics
Parameters
----------
assembly : str
Path to assembly fasta file
outdir : str
Path to the output directory
Returns
-------
"""
assembly_lengths = []
assembly = open(assembly, mode='rt') # TODO: newline=None in Python3
fasta_iter = (
g for k, g in itertools_groupby(assembly, lambda x: x.startswith('>')))
for header in fasta_iter:
# _ = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
_ = next(header)[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in next(fasta_iter))
assembly_lengths.append(len(seq))
with open(os.path.join(outdir, 'pilon_assembly_statistics.tab'),
'wt') as writer:
writer.write('#' + '\t'.join(['contigs', 'bp']) + '\n')
writer.write(
'\t'.join(map(str, [len(assembly_lengths),
sum(assembly_lengths)])) + '\n')
def kv_items(self):
if self.key is not None:
for k, v in itertools_groupby(self.sequence, key=self.key):
yield k, self.val_postproc(map(self.val, v))
else:
for i, v in enumerate(self.sequence):
yield i, self.val(v)
def write_assembly_statistics(assembly, outdir):
"""
Write assembly statistics
Parameters
----------
assembly : str
Path to assembly fasta file
outdir : str
Path to the output directory
Returns
-------
"""
assembly_lengths = []
assembly = open(assembly, mode='rt') # TODO: newline=None in Python3
fasta_iter = (g for k, g in itertools_groupby(assembly, lambda x: x.startswith('>')))
for header in fasta_iter:
# _ = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
_ = header.next()[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.next())
assembly_lengths.append(len(seq))
with open(os.path.join(outdir, 'pilon_assembly_statistics.tab'), 'wt') as writer:
writer.write('#' + '\t'.join(['contigs', 'bp']) + '\n')
writer.write('\t'.join(map(str, [len(assembly_lengths), sum(assembly_lengths)])) + '\n')
def get_sequence_information(fasta_file):
headers = {}
sequence_dict = {}
headers_changed = False
sequence_counter = 0
reader = open(fasta_file, mode='rt', newline=None)
fasta_iter = (
g for k, g in itertools_groupby(reader, lambda x: x.startswith('>')))
for header in fasta_iter:
original_header, new_header = clean_header(
header.__next__()[1:].rstrip('\r\n'))
if new_header in headers:
sys.exit('Found duplicated sequence'
' headers: {original_header}'.format(
original_header=original_header))
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__())
sequence_counter += 1
sequence_dict[sequence_counter] = {
'header': new_header,
'sequence': seq,
'length': len(seq)
}
headers[new_header] = str(original_header)
if new_header != original_header:
headers_changed = True
reader.close()
return sequence_dict, headers, headers_changed
def clean_novel_alleles(novel_alleles, scheme_mlst, profile):
"""
Clean the fasta file with the novel alleles produced by mlst
Parameters
----------
novel_alleles : str
Path for fasta file containing the novel alleles
scheme_mlst : str
MLST schema found by mlst
profile : list
List of strings with the profile found
Returns
-------
"""
unknown_genes = []
for gene_allele in profile:
gene = gene_allele.split('(')[0]
try:
allele = gene_allele.split('(')[1].rstrip(')')
if allele.startswith('~'):
unknown_genes.append(gene)
except IndexError as e:
print('WARNING: {}'.format(e))
try:
novel_alleles_keep = {}
if len(unknown_genes) > 0:
reader = open(novel_alleles, mode='rt') # TODO: newline=None in Python3
fasta_iter = (g for k, g in itertools_groupby(reader, lambda x: x.startswith('>')))
for header in fasta_iter:
# header = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
header = header.next()[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.next())
if header.startswith(scheme_mlst):
gene = header.split('.')[1].split('~')[0]
if gene in unknown_genes:
novel_alleles_keep[header] = seq
reader.close()
os.remove(novel_alleles)
if len(novel_alleles_keep) > 0:
with open(novel_alleles, 'wt') as writer:
for header, seq in novel_alleles_keep.items():
writer.write('>{}\n'.format(header))
writer.write('\n'.join(utils.chunkstring(seq, 80)) + '\n')
except OSError as e: # TODO: FileNotFoundError in Python3
print('An unknown ST was found but no novel alleles fasta file was produced by mlst software:\n'
'{}'.format(e))
def clean_novel_alleles(novel_alleles, scheme_mlst, profile):
"""
Clean the fasta file with the novel alleles produced by mlst
Parameters
----------
novel_alleles : str
Path for fasta file containing the novel alleles
scheme_mlst : str
MLST schema found by mlst
profile : list
List of strings with the profile found
Returns
-------
"""
unknown_genes = []
for gene_allele in profile:
gene = gene_allele.split('(')[0]
try:
allele = gene_allele.split('(')[1].rstrip(')')
if allele.startswith('~'):
unknown_genes.append(gene)
except IndexError as e:
print('WARNING: {}'.format(e))
novel_alleles_keep = {}
if len(unknown_genes) > 0:
reader = open(novel_alleles,
mode='rt') # TODO: newline=None in Python3
fasta_iter = (
g
for k, g in itertools_groupby(reader, lambda x: x.startswith('>')))
for header in fasta_iter:
# header = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
header = header.next()[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.next())
if header.startswith(scheme_mlst):
gene = header.split('.')[1].split('~')[0]
if gene in unknown_genes:
novel_alleles_keep[header] = seq
reader.close()
os.remove(novel_alleles)
if len(novel_alleles_keep) > 0:
with open(novel_alleles, 'wt') as writer:
for header, seq in novel_alleles_keep.items():
writer.write('>{}\n'.format(header))
writer.write('\n'.join(utils.chunkstring(seq, 80)) + '\n')
def groupby(inset, keyfunc):
"""groupby on unsorted inset"""
return itertools_groupby(sorted(inset, key=keyfunc), keyfunc)
css=osp.relpath(collection_css, path)
)
with open(path, 'wt', encoding='utf-8') as fp:
fp.write(render(collection_template, view))
# write out an all collections file
with open(osp.join(collection_path, 'ALL'), 'wt', encoding='utf-8') as fp:
fp.write(' '.join(all_collections))
# write the index.htmls
idxtemplate = open("src/book-index.mako").read()
idxpaths = sorted(set(b["path"] for b in ndx))
start = osp.join(CONTENT, "index.html")
back = start
i = 1
for path, group in itertools_groupby(ndx, lambda v: v["path"]):
view = dict(
name="index",
books=group,
back=osp.relpath(back, osp.dirname(path)),
next=osp.relpath(idxpaths[i] if i < len(idxpaths)
else start, osp.dirname(path)),
css=osp.relpath(osp.join(OUT, "index.css"), path),
)
with open(path, "wt", encoding="utf-8") as fp:
fp.write(render(idxtemplate, view))
back = path
i += 1
# write the word indexes
WOUT = osp.join(CONTENT, "index")