def test_dory_multifasta_query(location):
copy_dory_head()
copy_dory_catlas()
copy_dory_sig()
# make k-mer search index - FIXTURE
args = '-k 21 dory_k21_r1'.split()
index_contigs_by_kmer.main(args)
# index by multifasta
os.mkdir('dory_k21_r1_multifasta')
args = 'dory_k21_r1 dory_k21_r1_multifasta/multifasta.pickle --query dory-head.fa -k 21'
index_cdbg_by_multifasta.main(args.split())
args = '-k 21 --scaled 100 dory_k21_r1/contigs.fa.gz dory_k21_r1_multifasta/hashval.pickle'
index_cdbg_by_minhash.main(args.split())
args = '--hashvals dory_k21_r1_multifasta/hashval.pickle --multi-idx dory_k21_r1_multifasta/multifasta.pickle --query-sig dory-subset.fq.sig --output dory_k21_r1_multifasta/query-results.csv -k 21 --scaled 100'
query_multifasta_by_sig.main(args.split())
args = '--multi-idx dory_k21_r1_multifasta/multifasta.pickle --output dory_k21_r1_multifasta/multifasta.cdbg_by_record.csv --info-csv dory_k21_r1/contigs.fa.gz.info.csv'
extract_cdbg_by_multifasta.main(args.split())
assert os.path.exists(
'dory_k21_r1_multifasta/multifasta.cdbg_by_record.csv')
assert os.path.exists('dory_k21_r1_multifasta/query-results.csv')
def test_dory_query_workflow(location):
from spacegraphcats.cdbg import bcalm_to_gxt
copy_dory_head()
copy_dory_subset()
# make the output directory
try:
os.mkdir('dory_k21_r1')
except FileExistsError:
pass
# convert the bcalm file to gxt
args = ['-k', '21', '-P',
relative_file('dory/bcalm.dory.k21.unitigs.fa'),
'dory_k21_r1/cdbg.gxt',
'dory_k21_r1/contigs.fa.gz']
bcalm_to_gxt.main(args)
# build catlas
args = pytest_utils.Args()
args.no_checkpoint = True
args.level = 0
args.radius = 1
args.project = 'dory_k21_r1'
print('** running catlas')
catlas.main(args)
# make k-mer search index
args = '-k 21 dory_k21_r1'.split()
print('** running index_contigs_by_kmer')
index_contigs_by_kmer.main(args)
# do search!!
args='dory_k21_r1 dory_k21_r1_search_oh0 --query dory-head.fa -k 21'.split()
try:
query_by_sequence.main(args)
except SystemExit as e:
assert e.code == 0, str(e)
# check output!
output_path = 'dory_k21_r1_search_oh0/'
assert os.path.exists(output_path + 'command.txt')
assert os.path.exists(output_path + 'dory-head.fa.frontier.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.cdbg_ids.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.response.txt')
assert os.path.exists(output_path + 'dory-head.fa.contigs.sig')
assert os.path.exists(output_path + 'results.csv')
with open(output_path + 'results.csv') as fp:
lines = fp.readlines()
assert len(lines) == 2
last_line = lines[-1].strip()
assert last_line == 'dory-head.fa,1.0,1.0,1671,2,21,1631,1.0,0.0,0.0,dory_k21_r1'
def test_dory_extract_unassembled_nodes(location):
copy_dory_catlas()
copy_dory_head()
# make k-mer search index - FIXTURE
args = '-k 21 dory_k21_r1'.split()
index_contigs_by_kmer.main(args)
# run extract_unassembled_regions
args = 'dory_k21_r1 dory-head.fa dory.regions -k 21'.split()
extract_unassembled_nodes.main(args)
def test_dory_estimate_query_abundance(location):
copy_dory_catlas()
copy_dory_head()
# make k-mer search index - FIXTURE
args = '-k 21 dory_k21_r1'.split()
index_contigs_by_kmer.main(args)
# calculate query abundances
args = 'dory_k21_r1 dory-head.fa -o abundances.csv -k 21'.split()
print('** running estimate_query_abundance')
estimate_query_abundance.main(args)
abunds = open('abundances.csv', 'rt').read()
def test_dory_search_nomatch(location):
# test situations where zero k-mers match - should not fail.
copy_dory_catlas()
testdata = relative_file('data/random-query-nomatch.fa')
shutil.copyfile(testdata, 'random-query.fa')
# make k-mer search index
args = '-k 21 dory_k21_r1'.split()
print('** running index_contigs_by_kmer')
index_contigs_by_kmer.main(args)
# do search!!
args='dory_k21_r1 dory_k21_r1_search_oh0 --query random-query.fa -k 21'.split()
try:
query_by_sequence.main(args)
except SystemExit as e:
assert e.code == 0, str(e)
def test_dory():
with TempDirectory() as location:
from spacegraphcats.cdbg import bcalm_to_gxt
# make the output directory
try:
os.mkdir('dory_k21_r1')
except FileExistsError:
pass
# convert the bcalm file to gxt
args = [
'-k', '-21', '-P',
relative_filename('dory/bcalm.dory.k21.unitigs.fa'),
'dory_k21_r1/cdbg.gxt', 'dory_k21_r1/contigs.fa.gz'
]
bcalm_to_gxt.main(args)
# build catlas
args = Args()
args.no_checkpoint = True
args.level = 0
args.radius = 1
args.project = 'dory_k21_r1'
catlas.main(args)
# make k-mer search index
args = '-k 21 dory_k21_r1'.split()
index_contigs_by_kmer.main(args)
# do search!!
extract_nodes_by_query
args = 'dory_k21_r1 dory_k21_r1_search_oh0 --query data/dory-head.fa -k 21 --overhead=0.0'.split(
)
try:
extract_nodes_by_query.main(args)
except SystemExit as e:
assert e.code == 0, str(e)
# check output!
output_path = 'dory_k21_r1_search_oh0/'
assert os.path.exists(output_path + 'command.txt')
assert os.path.exists(output_path + 'dory-head.fa.frontier.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.cdbg_ids.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.response.txt')
assert os.path.exists(output_path + 'dory-head.fa.contigs.sig')
assert os.path.exists(output_path + 'results.csv')
with open(output_path + 'results.csv') as fp:
lines = fp.readlines()
assert len(lines) == 2
last_line = lines[-1].strip()
assert last_line == 'data/dory-head.fa,1.0,1.0,1671,2,21,1631,1.0,0.0,0.0'
# run characterize_catlas_regions
args = 'dory_k21_r1 dory_k1_r1.vec'.split()
characterize_catlas_regions.main(args)
# run extract_unassembled_regions
args = 'dory_k21_r1 data/dory-head.fa dory.regions -k 21'.split()
extract_unassembled_nodes.main(args)
# run catlas info
catlas_info.main(['dory_k21_r1'])
# run extract_contigs
args = [
'dory_k21_r1',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.txt.gz', '-o',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.contigs.fa.gz'
]
extract_contigs.main(args)
assert os.path.exists(
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.contigs.fa.gz')
# run make_bgzf
args = ['data/dory-subset.fa', '-o', 'dory/dory.reads.bgz']
make_bgzf.main(args)
# run label_cdbg
args = [
'dory_k21_r1', 'dory/dory.reads.bgz',
'dory_k21_r1/reads.bgz.labels'
]
label_cdbg.main(args)
# run extract_reads
args = [
'dory/dory.reads.bgz', 'dory_k21_r1/reads.bgz.labels',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.txt.gz', '-o',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.reads.fa.gz'
]
extract_reads.main(args)
def test_dory():
with TempDirectory() as location:
from spacegraphcats.cdbg import bcalm_to_gxt
# make the output directory
try:
os.mkdir('dory_k21_r1')
except FileExistsError:
pass
# convert the bcalm file to gxt
args = ['-k', '-21', '-P',
relative_filename('dory/bcalm.dory.k21.unitigs.fa'),
'dory_k21_r1/cdbg.gxt',
'dory_k21_r1/contigs.fa.gz']
bcalm_to_gxt.main(args)
# build catlas
args = Args()
args.no_checkpoint = True
args.level = 0
args.radius = 1
args.project = 'dory_k21_r1'
catlas.main(args)
# make k-mer search index
args = '-k 21 dory_k21_r1'.split()
index_contigs_by_kmer.main(args)
# do search!!
args='dory_k21_r1 dory_k21_r1_search_oh0 --query data/dory-head.fa -k 21 --overhead=0.0'.split()
try:
extract_nodes_by_query.main(args)
except SystemExit as e:
assert e.code == 0, str(e)
# check output!
output_path = 'dory_k21_r1_search_oh0/'
assert os.path.exists(output_path + 'command.txt')
assert os.path.exists(output_path + 'dory-head.fa.frontier.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.cdbg_ids.txt.gz')
assert os.path.exists(output_path + 'dory-head.fa.response.txt')
assert os.path.exists(output_path + 'dory-head.fa.contigs.sig')
assert os.path.exists(output_path + 'results.csv')
with open(output_path + 'results.csv') as fp:
lines = fp.readlines()
assert len(lines) == 2
last_line = lines[-1].strip()
assert last_line == 'data/dory-head.fa,1.0,1.0,1671,2,21,1631,1.0,0.0,0.0'
# run characterize_catlas_regions
args = 'dory_k21_r1 dory_k1_r1.vec'.split()
characterize_catlas_regions.main(args)
# run extract_unassembled_regions
args = 'dory_k21_r1 data/dory-head.fa dory.regions -k 21'.split()
extract_unassembled_nodes.main(args)
# run catlas info
catlas_info.main(['dory_k21_r1'])
# run extract_contigs
args = ['dory_k21_r1',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.txt.gz',
'-o',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.contigs.fa.gz']
extract_contigs.main(args)
assert os.path.exists('dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.contigs.fa.gz')
# run make_bgzf
args = ['data/dory-subset.fa', '-o', 'dory/dory.reads.bgz']
make_bgzf.main(args)
# run label_cdbg
args = ['dory_k21_r1',
'dory/dory.reads.bgz', 'dory_k21_r1/reads.bgz.labels']
label_cdbg.main(args)
# run extract_reads
args = ['dory/dory.reads.bgz',
'dory_k21_r1/reads.bgz.labels',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.txt.gz',
'-o',
'dory_k21_r1_search_oh0/dory-head.fa.cdbg_ids.reads.fa.gz']
extract_reads.main(args)
# calculate query abundances
args = 'dory_k21_r1 data/dory-head.fa -o abundances.csv -k 21'.split()
estimate_query_abundance.main(args)
abunds = open('abundances.csv', 'rt').read()
assert 'data/dory-head.fa,1.0,1.05' in abunds