def test_dna_strange_character_replace(self):
create = Create(prerequisites)
seqs = [Sequence('namer', 'ATGC')]
create._mask_strange_sequence_letters(seqs,
Create._NUCLEOTIDE_PACKAGE_TYPE)
self.assertEqual(1, len(seqs))
self.assertEqual('ATGC', str(seqs[0].seq))
seqs = [Sequence('namer', 'ATGCRTWU')]
create._mask_strange_sequence_letters(seqs,
Create._NUCLEOTIDE_PACKAGE_TYPE)
self.assertEqual(1, len(seqs))
self.assertEqual('ATGCNTNT', str(seqs[0].seq))
def test_strange_character_replace(self):
create = Create(prerequisites)
seqs = [Sequence('namer', 'SEQWENCE')]
create._mask_strange_sequence_letters(seqs,
Create._PROTEIN_PACKAGE_TYPE)
self.assertEqual(1, len(seqs))
self.assertEqual('SEQWENCE', str(seqs[0].seq))
seqs = [Sequence('namer', 'SEQUENCE')]
create._mask_strange_sequence_letters(seqs,
Create._PROTEIN_PACKAGE_TYPE)
self.assertEqual(1, len(seqs))
self.assertEqual('SEQXENCE', str(seqs[0].seq))
def extract_and_read(self, reads_to_extract, database_fasta_file):
'''Extract the reads_to_extract from the database_fasta_file and return them.
Parameters
----------
reads_to_extract: Iterable of str
IDs of reads to be extracted
database_fasta_file: str
path the fasta file that containing the reads
Returns
-------
An array of graftm.sequence_io.Sequence objects'''
cmd = "fxtract -XH -f /dev/stdin '%s'" % database_fasta_file
process = subprocess.Popen(["bash", "-c", cmd],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
output, error = process.communicate('\n'.join(reads_to_extract))
if process.returncode != 0:
raise Exception(
"Extraction command '%s' failed with exitstatus %i" %
(cmd, process.returncode))
seqs = []
for name, seq, _ in SequenceIO().each(StringIO(output)):
seqs.append(Sequence(name, seq))
return seqs
def s(self, seqs):
to_return = []
current_seq = None
for bit in split(seqs, ' '):
if current_seq:
current_seq.seq = bit
to_return.append(current_seq)
current_seq = None
else:
current_seq = Sequence(bit, '')
return to_return
def extract_and_read(self, reads_to_extract, database_fasta_file):
'''Extract the reads_to_extract from the database_fasta_file and return them.
Parameters
----------
reads_to_extract: Iterable of str
IDs of reads to be extracted
database_fasta_file: str
path the fasta file that containing the reads
Returns
-------
An array of graftm.sequence_io.Sequence objects'''
cmd = "mfqe --output-uncompressed --fasta-read-name-lists /dev/stdin --input-fasta '{}' --output-fasta-files /dev/stdout".format(
database_fasta_file)
# Retrieve each sequence exactly once so mfqe does not croak
output = extern.run(cmd, stdin='\n'.join(set(reads_to_extract)))
seqs = []
for name, seq, _ in SequenceIO().each(StringIO(output)):
seqs.append(Sequence(name, seq))
return seqs
def test_basic_split(self):
input_alias_hash = {'0': {'place': []}, '1': {'place': []}}
expected_placement = [
'p__Proteobacteria', 'k__Bacteria', 'p__Proteobacteria'
]
mock_cluster_hash = {
'0': {
"test_read1": [Sequence("test_read1", "SEQUENCE")]
},
'1': {
"test_read2": [Sequence("test_read2", "SEQUENCE")]
}
}
test_json = {
"fields": [
"classification", "distal_length", "edge_num",
"like_weight_ratio", "likelihood", "pendant_length"
],
"tree":
"((696036:0.2205{0},229854:0.20827{1})1.000:0.14379{2},3190878:0.23845{3},2107103:0.32104{4}){5};",
"placements": [{
"p": [[
"p__Proteobacteria", 0.107586583111, 1, 0.970420466541,
-614.032176075, 0.22226616471
],
[
"k__Bacteria", 0.220493270874, 0, 0.0147918928965,
-618.21582627, 0.248671444337
],
[
"p__Proteobacteria", 8.77624511719e-06, 2,
0.0147876405626, -618.216113788, 0.248672441848
]],
"nm": [["test_read1_0", 1], ["test_read2_1", 1]]
}],
"version":
3,
"metadata": {
"invocation":
"pplacer -c test_16S.gpkg\/test_16S.gpkg.refpkg\/ GraftM_output\/combined_alignment.aln.fa"
}
}
pplacer = Pplacer("refpkg_decoy")
observed_placement = pplacer.jplace_split(test_json, mock_cluster_hash)
expected_placement = {
'0': [{
"p": [[
"p__Proteobacteria", 0.107586583111, 1, 0.970420466541,
-614.032176075, 0.22226616471
],
[
"k__Bacteria", 0.220493270874, 0, 0.0147918928965,
-618.21582627, 0.248671444337
],
[
"p__Proteobacteria", 8.77624511719e-06, 2,
0.0147876405626, -618.216113788, 0.248672441848
]],
"nm": [["test_read1", 1]]
}],
'1': [{
"p": [[
"p__Proteobacteria", 0.107586583111, 1, 0.970420466541,
-614.032176075, 0.22226616471
],
[
"k__Bacteria", 0.220493270874, 0, 0.0147918928965,
-618.21582627, 0.248671444337
],
[
"p__Proteobacteria", 8.77624511719e-06, 2,
0.0147876405626, -618.216113788, 0.248672441848
]],
"nm": [["test_read2", 1]]
}]
}
self.assertEqual(expected_placement, observed_placement)