def test_sequences_from_query_string(self):
"""Check correct parsing when input is a string"""
out_tax_dict = sequences_from_query(self.taxonomy_lines, 'Beggiatoa')
self.assertEquals(out_tax_dict, {
'NZ_ABBZ01000843|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01000613|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01002042|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBY01000503|640963012': 'VibrioBeggiatoa sp. SS',
'NZ_ABBZ01000140|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBY01000221|640963012': 'VibrioBeggiatoa sp. SS',
'NZ_ABBZ01006278|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01005870|640963011': 'VibrioBeggiatoa sp. PS'})
out_tax_dict = sequences_from_query(self.taxonomy_lines, 'Rumba')
self.assertEquals(out_tax_dict, {})
def test_sequences_from_query_string(self):
"""Check correct parsing when input is a string"""
out_tax_dict = sequences_from_query(self.taxonomy_lines, 'Beggiatoa')
self.assertEquals(
out_tax_dict, {
'NZ_ABBZ01000843|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01000613|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01002042|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBY01000503|640963012': 'VibrioBeggiatoa sp. SS',
'NZ_ABBZ01000140|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBY01000221|640963012': 'VibrioBeggiatoa sp. SS',
'NZ_ABBZ01006278|640963011': 'VibrioBeggiatoa sp. PS',
'NZ_ABBZ01005870|640963011': 'VibrioBeggiatoa sp. PS'
})
out_tax_dict = sequences_from_query(self.taxonomy_lines, 'Rumba')
self.assertEquals(out_tax_dict, {})
def split_db(tax_fp, seqs_fp, query, output_fp, split_fp):
"""Split a database in parts that match a query and parts that don't
Parameters
----------
tax_fp : str
Tab-delimited file with two columns, name/identifier of the sequence
and the taxonomy. The sequence identifier is the longest string before
a space in the header of the sequence.
seqs_fp : str
Path to a FASTA formatted file to split in interest and rest. Note:
sequence identifiers must match the ones in the taxonomy file.
query : str
The query used to split the database, for example: salmonella. The
query should be an exact match, no wild cards, it can have spaces, and
it is case insensitive
output_fp : str
Output folder path where the results are stored.
split_fp : str
The tab delimited query file, where each line is a different sequence
and the first column is the sequence id.
Raises
------
BadParameter
If the Taxonomy file is empty.
If the query you passed retrieved no results.
"""
if query is not None:
# query the taxonomy file for the required sequence identifiers
try:
interest_taxonomy = sequences_from_query(open(tax_fp, 'U'),
query)
except (PlatypusValueError, PlatypusParseError), e:
raise BadParameter(e.message)
if len(interest_taxonomy) == 0:
raise BadParameter('The query could not retrieve any results, try '
'a different one.')
def split_db(tax_fp, seqs_fp, query, output_fp, split_fp):
"""Split a database in parts that match a query and parts that don't
Parameters
----------
tax_fp : str
Tab-delimited file with two columns, name/identifier of the sequence
and the taxonomy. The sequence identifier is the longest string before
a space in the header of the sequence.
seqs_fp : str
Path to a FASTA formatted file to split in interest and rest. Note:
sequence identifiers must match the ones in the taxonomy file.
query : str
The query used to split the database, for example: salmonella. The
query should be an exact match, no wild cards, it can have spaces, and
it is case insensitive
output_fp : str
Output folder path where the results are stored.
split_fp : str
The tab delimited query file, where each line is a different sequence
and the first column is the sequence id.
Raises
------
BadParameter
If the Taxonomy file is empty.
If the query you passed retrieved no results.
"""
if query is not None:
# query the taxonomy file for the required sequence identifiers
try:
interest_taxonomy = sequences_from_query(open(tax_fp, 'U'), query)
except (PlatypusValueError, PlatypusParseError), e:
raise BadParameter(e.message)
if len(interest_taxonomy) == 0:
raise BadParameter('The query could not retrieve any results, try '
'a different one.')
def split_db(tax_fp, seqs_fp, query, output_fp, split_fp):
"""Split a database in parts that match a query and parts that don't
Parameters
----------
tax_fp : str
Tab-delimited file with two columns, name/identifier of the sequence
and the taxonomy. The sequence identifier is the longest string before
a space in the header of the sequence.
seqs_fp : str
Path to a FASTA formatted file to split in interest and rest. Note:
sequence identifiers must match the ones in the taxonomy file.
query : str
The query used to split the database, for example: salmonella. The
query should be an exact match, no wild cards, it can have spaces, and
it is case insensitive
output_fp : str
Output folder path where the results are stored.
split_fp : str
The tab delimited query file, where each line is a different sequence
and the first column is the sequence id.
Raises
------
BadParameter
If the Taxonomy file is empty.
If the query you passed retrieved no results.
"""
if query is not None:
# query the taxonomy file for the required sequence identifiers
try:
interest_taxonomy = sequences_from_query(open(tax_fp, 'U'), query)
except (PlatypusValueError, PlatypusParseError) as e:
raise BadParameter(e.message)
if len(interest_taxonomy) == 0:
raise BadParameter('The query could not retrieve any results, try '
'a different one.')
else:
interest_taxonomy = {
l.strip().split('\t')[0].strip(): ''
for l in open(split_fp, 'U')
}
if not interest_taxonomy:
raise BadParameter('The split_fp is empty!')
create_dir(output_fp, False)
interest_fp = open(join(output_fp, 'interest.fna'), 'w')
rest_fp = open(join(output_fp, 'rest.fna'), 'w')
for record in read(seqs_fp, format='fasta'):
full_name = record.id
seq = record.sequence
name = full_name.strip().split(' ')[0].strip()
if name in interest_taxonomy:
interest_fp.write(">%s\n%s\n" % (full_name, seq))
else:
rest_fp.write(">%s\n%s\n" % (full_name, seq))
interest_fp.close()
rest_fp.close()
