def parse_glimmer3(file_handle):
"""
Parses an ouput file from glimmer3 and yields the header and prediction
lines. Used to feed the :func:`mgkit.io.gff.from_glimmer3` function.
Arguments:
file_handle (str, file): file name or file handle to read from
Yields:
tuple: first element is the sequence of the predicted gene and the
second is the prediction line
"""
if isinstance(file_handle, str):
file_handle = open_file(file_handle, 'r')
curr_seq = ''
predictions = []
for line in file_handle:
line = line.strip()
if line.startswith('>'):
if len(predictions) > 0:
for prediction in predictions:
yield curr_seq, prediction
curr_seq = line[1:]
predictions = []
else:
if line != '':
predictions.append(line)
else:
if len(predictions) > 0:
for prediction in predictions:
yield curr_seq, prediction
def load_htseq_counts(file_handle, conv_func=int):
"""
.. versionchanged:: 0.1.15
added *conv_func* parameter
Loads an HTSeq-count result file
Arguments:
file_handle (file or str): file handle or string with file name
conv_func (func): function to convert the number from string, defaults
to *int*, but *float* can be used as well
Yields:
tuple: first element is the gene_id and the second is the count
"""
if isinstance(file_handle, str):
file_handle = open_file(file_handle, 'rb')
if getattr(file_handle, 'name', None) is not None:
LOG.info("Loading HTSeq-count file %s", file_handle.name)
for line in file_handle:
line = line.decode('ascii')
gene_id, count = line.rstrip().split('\t')
if line.startswith('__') or (gene_id in SKIP):
continue
yield gene_id, conv_func(count)
def test_Annotation_to_file(gff_file, tmpdir):
ann = gff.from_gff(gff_file[0])
file_name = (tmpdir / 'test-write.gff').strpath
file_handle = open_file(file_name, 'wb')
ann.to_file(file_handle)
file_handle.close()
ann2 = next(gff.parse_gff(file_name))
assert ann == ann2
def test_write_fastq2(fastq_file, tmpdir):
header, seq, qual = next(fastq.load_fastq(fastq_file, num_qual=True))
file_name = (tmpdir / 'test.fq').strpath
file_handle = open_file(file_name, 'w')
fastq.write_fastq_sequence(file_handle, header, seq, qual)
file_handle.close()
headerw, seqw, qualw = next(fastq.load_fastq(file_name, num_qual=True))
assert (header, seq, list(qual)) == (headerw, seqw, list(qualw))
def sample_command(verbose, prefix, number, prob, max_seq, fastq, gzip,
input_file):
mgkit.logger.config_log(level=logging.DEBUG if verbose else logging.INFO)
LOG.info("Sampling %s file (%d) chunks with prefix (%s)",
'FastQ' if fastq else 'Fasta', number, prefix)
if (prob > 1) or (prob <= 0):
utils.exit_script(
"The probability value ({}) is outside the correct range" +
" (0 < p <= 1)", 1)
dist = scipy.stats.binom(1, prob)
LOG.info("Probability of picking a sequence (%.5f), max number of seqs %d",
prob, max_seq)
name_mask = "%s-{0:05}.%s" % (prefix, 'fq' if fastq else 'fa')
if gzip:
name_mask += '.gz'
LOG.info("Output files will be compressed (gzip)")
output_files = [
dict(h=open_file(name_mask.format(i), 'wb'), c=0)
for i in range(number)
]
load_func = load_fastq if fastq else fasta.load_fasta
write_func = write_fastq_sequence if fastq else fasta.write_fasta_sequence
for seq in load_func(input_file):
# reached the maximum number of sequences for all samples
if all(x['c'] == max_seq for x in output_files):
break
for output in output_files:
if output['c'] == max_seq:
continue
if dist.rvs():
write_func(output['h'], *seq)
output['c'] += 1
def add_fields_from_table(verbose, key, attribute, only_edited, skip_rows,
separator, comment, table_file, key_index,
attr_index, input_file, output_file):
logger.config_log(level=logging.DEBUG if verbose else logging.INFO)
LOG.info("Key used is '%s' and attribute '%s'", key, attribute)
LOG.info("N. rows skipped '%d' Key index is '%d' and attribute index '%d'",
skip_rows, key_index, attr_index)
if getattr(table_file, 'name', None) is not None:
LOG.info("Reading values from (%s)", table_file.name)
fields = dict(
text_to_dict(open_file(table_file),
skip_lines=skip_rows,
sep=separator,
key_index=key_index,
value_index=attr_index,
encoding='ascii',
skip_empty=True,
skip_comment=comment))
changed = 0
for annotation in gff.parse_gff(input_file):
try:
key_ann_value = annotation.get_attr(key)
except gff.AttributeNotFound:
if only_edited:
continue
try:
annotation.set_attr(attribute, fields[key_ann_value])
changed += 1
except KeyError:
if only_edited:
continue
annotation.to_file(output_file)
LOG.info('Changed %d annotations', changed)
def snpdat_reader(f_handle):
"""
Simple SNPDat reader.
f_handle: file handle or string for the SNPDat result file
:return: generator of SNPDatRow instances
"""
if isinstance(f_handle, str):
f_handle = open_file(f_handle, 'r')
LOG.info("Reading from file %s", f_handle.name)
f_handle.readline() # skips header line
for line in f_handle:
line = line.decode('ascii')
try:
yield SNPDatRow(line)
except ValueError:
LOG.critical(line)
LOG.exception("Error reading line")
raise ValueError
def keggmod_file(shared_datadir):
return open_file(str(shared_datadir / 'kmod-entry1.txt'), 'rb').readlines()
def glimmer_file(shared_datadir):
return open_file(str(shared_datadir / 'glimmer3.txt'), 'rb').readlines()
def hmmer_file(shared_datadir):
return open_file(str(shared_datadir / 'test-hmmer-dom.txt'), 'rb').readlines()
def gff_file(shared_datadir):
return open_file(str(shared_datadir / 'test.gff'), 'rb').readlines()
