def test_find_exec(self):
cmd = "ls"
path = Seq.find_exec(cmd)
self.assertTrue(path)
if path:
out = subprocess.call([path], stdout=open(os.devnull, "w"))
self.assertTrue(out == 0)
import sys
import os
import unittest
import logging
import config
import Seq
log = logging
module_name = os.path.split(sys.argv[0])[1].rstrip('.py')
outputdir = config.outputdir
datadir = config.datadir
clustalw_path = Seq.find_exec('clustalw')
class TestClustalwInstalled(unittest.TestCase):
def test1(self):
if not clustalw_path:
log.error('clustalw could not be found - skipping tests in this module')
if clustalw_path is not None:
class TestRunClustalw(unittest.TestCase):
def setUp(self):
self.file1 = os.path.join(datadir, '10patients.fasta')
self.funcname = '_'.join(self.id().split('.')[-2:])
self.outfile = os.path.join(outputdir,self.funcname)
def test1(self):
import sys
import os
import unittest
import logging
import config
import Seq
log = logging
module_name = os.path.split(sys.argv[0])[1].rstrip('.py')
outputdir = config.outputdir
datadir = config.datadir
hmmbuild_path = Seq.find_exec('hmmbuild')
class TestHmmerInstalled(unittest.TestCase):
def test1(self):
if hmmbuild_path is None:
log.error('hmmer software could not be found - skipping tests in this module')
if hmmbuild_path is not None:
class TestRunHmmer(unittest.TestCase):
def setUp(self):
self.file1 = os.path.join(datadir, 's_trimmed.aln')
self.funcname = '_'.join(self.id().split('.')[-2:])
self.outfile = os.path.join(outputdir,self.funcname)
def test1(self):
import os
import unittest
import logging
import pprint
import config
import Seq
log = logging
module_name = os.path.split(sys.argv[0])[1].rstrip('.py')
outputdir = config.outputdir
datadir = config.datadir
fasta_path = Seq.find_exec('fasta35')
class TestFastaInstalled(unittest.TestCase):
def test1(self):
if fasta_path is None:
log.error('fasta35 could not be found - skipping tests in this module')
if fasta_path is not None:
class TestRunFasta(unittest.TestCase):
def setUp(self):
self.file1 = os.path.join(datadir, '10patients.fasta')
self.funcname = '_'.join(self.id().split('.')[-2:])
self.outfile = os.path.join(outputdir,self.funcname)
def run(query, target, e_val=10, outfile=None,
fastapath=None, format=10, cleanup=True):
"""Returns a dict keyed by (seqname1,seqname2) pairs containing
alignment data.
* query - Seq object or filename of fasta format sequences
* target - list of Seq objects or filename of fasta format sequences
* e_val - (see FASTA3* documentation)
* outfile - name of output file
* outdir - directory to write fasta output
* fastapath - name of directory containing fasta3* executable
* format - (see FASTA3* documentation)
* cleanup - if True, delete fasta output file
"""
# see http://helix.nih.gov/apps/bioinfo/fasta3x.txt
# format = 10 for machine-readable alignments, 0 for traditional aligns
if outfile:
outdir = os.path.abspath(os.path.split(outfile)[0])
else:
outdir = TEMPDIR
outfile = os.path.join(outdir, randomname(12)+ALIGN_SUFFIX)
query_file, query_is_file = get_path_or_write_file(query, outdir)
target_file, target_is_file = get_path_or_write_file(target, outdir)
fasta_prog = Seq.find_exec('fasta35', fastapath)
if fasta_prog is None:
raise OSError('fasta35 could not be found')
# -A Force Smith-Waterman alignment
# -H Omit Histogram
# -q Quiet - does not prompt for any input.
# -m format
# -z 0 estimates the significance of the match from the mean and standard deviation of the library scores, without correcting for library sequence length.
# -d number of sequences to display
# -E maximum expect value to display
fastacmd = ' '.join("""
%(fasta_prog)s
-A
-H
-q
-z 0
-m %(format)s
-O %(outfile)s
%(query_file)s
%(target_file)s""".split())
cmd = fastacmd % locals()
log.info( cmd )
cmd_output = commands.getoutput(cmd)
log.debug(cmd_output)
# check for successful execution
if not os.access(outfile,os.F_OK):
log.critical('The following command failed:')
log.critical(cmd)
log.critical('...with output:')
log.critical(cmd_output)
raise Seq.ExecutionError(cmd_output)
# parse the data
data = parseFasta(open(outfile).read())
if cleanup:
if not query_is_file:
os.remove(query_file)
if not target_is_file:
os.remove(target_file)
os.remove(outfile)
query_file = target_file = outfile = None
for k in data.keys():
data[k]['file_q'] = query_file
data[k]['file_t'] = target_file
data[k]['file_out'] = outfile
return data
import os
import unittest
import logging
import pprint
import config
import Seq
log = logging
module_name = os.path.split(sys.argv[0])[1].rstrip('.py')
outputdir = config.outputdir
datadir = config.datadir
cmbuild_path = Seq.find_exec('cmbuild')
class TestInfernalInstalled(unittest.TestCase):
def test1(self):
if not cmbuild_path:
log.error('Infernal software could not be found - skipping tests in this module')
class Test_Run(unittest.TestCase):
def setUp(self):
self.funcname = '_'.join(self.id().split('.')[-2:])
self.outfile = os.path.join(outputdir,self.funcname)
self.has_space = os.path.join(outputdir,'name with spaces')
self.no_space = os.path.join(outputdir,'nameWithoutSpaces')
os.system('echo `date` has space > "%s"' % self.has_space)
