def build_tree_from_alignment(aln, moltype, best_tree=False, params={}):
"""Returns a tree from Alignment object aln.
aln: an xxx.Alignment object, or data that can be used to build one.
moltype: cogent.core.moltype.MolType object
best_tree: best_tree suppport is currently not implemented
params: dict of parameters to pass in to the RAxML app controller.
The result will be an xxx.Alignment object, or None if tree fails.
"""
if best_tree:
raise NotImplementedError
if '-m' not in params:
if moltype == DNA or moltype == RNA:
#params["-m"] = 'GTRMIX'
# in version 7.2.3, GTRMIX is no longer supported but says GTRCAT
# behaves like GTRMIX (http://www.phylo.org/tools/raxmlhpc2.html)
params["-m"] = 'GTRGAMMA'
elif moltype == PROTEIN:
params["-m"] = 'PROTGAMMAmatrixName'
else:
raise ValueError("Moltype must be either DNA, RNA, or PROTEIN")
if not hasattr(aln, 'toPhylip'):
aln = Alignment(aln)
seqs, align_map = aln.toPhylip()
# generate temp filename for output
params["-w"] = "/tmp/"
params["-n"] = get_tmp_filename().split("/")[-1]
params["-k"] = True
params["-p"] = randint(1,100000)
params["-x"] = randint(1,100000)
ih = '_input_as_multiline_string'
raxml_app = Raxml(params=params,
InputHandler=ih,
WorkingDir=None,
SuppressStderr=True,
SuppressStdout=True)
raxml_result = raxml_app(seqs)
tree = DndParser(raxml_result['Bootstrap'], constructor=PhyloNode)
for node in tree.tips():
node.Name = align_map[node.Name]
raxml_result.cleanUp()
return tree
def build_tree_from_alignment(aln, moltype, best_tree=False, params={}):
"""Returns a tree from Alignment object aln.
aln: an xxx.Alignment object, or data that can be used to build one.
moltype: cogent.core.moltype.MolType object
best_tree: best_tree suppport is currently not implemented
params: dict of parameters to pass in to the RAxML app controller.
The result will be an xxx.Alignment object, or None if tree fails.
"""
if best_tree:
raise NotImplementedError
if '-m' not in params:
if moltype == DNA or moltype == RNA:
#params["-m"] = 'GTRMIX'
# in version 7.2.3, GTRMIX is no longer supported but says GTRCAT
# behaves like GTRMIX (http://www.phylo.org/tools/raxmlhpc2.html)
params["-m"] = 'GTRGAMMA'
elif moltype == PROTEIN:
params["-m"] = 'PROTGAMMAmatrixName'
else:
raise ValueError("Moltype must be either DNA, RNA, or PROTEIN")
if not hasattr(aln, 'toPhylip'):
aln = Alignment(aln)
seqs, align_map = aln.toPhylip()
# generate temp filename for output
params["-w"] = "/tmp/"
params["-n"] = get_tmp_filename().split("/")[-1]
params["-k"] = True
params["-p"] = randint(1, 100000)
params["-x"] = randint(1, 100000)
ih = '_input_as_multiline_string'
raxml_app = Raxml(params=params,
InputHandler=ih,
WorkingDir=None,
SuppressStderr=True,
SuppressStdout=True)
raxml_result = raxml_app(seqs)
tree = DndParser(raxml_result['Bootstrap'], constructor=PhyloNode)
for node in tree.tips():
node.Name = align_map[node.Name]
raxml_result.cleanUp()
return tree
def test_insert_sequences_into_tree(self):
"""Inserts sequences into Tree using params - test handles tree-insertion"""
# generate temp filename for output
outfname = splitext(get_tmp_filename('/tmp/'))[0]
# create starting tree
outtreefname = outfname + '.tre'
outtree = open(outtreefname, 'w')
outtree.write(REF_TREE)
outtree.close()
# set params for tree-insertion
params = {}
params["-w"] = "/tmp/"
params["-n"] = get_tmp_filename().split("/")[-1]
params["-f"] = 'v'
#params["-G"] = '0.25'
params["-t"] = outtreefname
params["-m"] = 'GTRGAMMA'
aln_ref_query = get_align_for_phylip(
StringIO(PHYLIP_FILE_DNA_REF_QUERY))
aln = Alignment(aln_ref_query)
seqs, align_map = aln.toPhylip()
tree = insert_sequences_into_tree(seqs,
DNA,
params=params,
write_log=False)
for node in tree.tips():
removed_query_str = re.sub('QUERY___', '', str(node.Name))
new_node_name = re.sub('___\d+', '', str(removed_query_str))
if new_node_name in align_map:
node.Name = align_map[new_node_name]
self.assertTrue(isinstance(tree, PhyloNode))
self.assertEqual(tree.getNewick(with_distances=True), RESULT_TREE)
self.assertEqual(len(tree.tips()), 7)
self.assertRaises(NotImplementedError, build_tree_from_alignment, \
self.align1, RNA, True)
remove(outtreefname)
def test_insert_sequences_into_tree(self):
"""Inserts sequences into Tree using params - test handles tree-insertion"""
# generate temp filename for output
outfname=splitext(get_tmp_filename('/tmp/'))[0]
# create starting tree
outtreefname=outfname+'.tre'
outtree=open(outtreefname,'w')
outtree.write(REF_TREE)
outtree.close()
# set params for tree-insertion
params={}
params["-w"]="/tmp/"
params["-n"] = get_tmp_filename().split("/")[-1]
params["-f"] = 'v'
#params["-G"] = '0.25'
params["-t"] = outtreefname
params["-m"] = 'GTRGAMMA'
aln_ref_query=get_align_for_phylip(StringIO(PHYLIP_FILE_DNA_REF_QUERY))
aln = Alignment(aln_ref_query)
seqs, align_map = aln.toPhylip()
tree = insert_sequences_into_tree(seqs, DNA, params=params,
write_log=False)
for node in tree.tips():
removed_query_str=re.sub('QUERY___','',str(node.Name))
new_node_name=re.sub('___\d+','',str(removed_query_str))
if new_node_name in align_map:
node.Name = align_map[new_node_name]
self.assertTrue(isinstance(tree, PhyloNode))
self.assertEqual(tree.getNewick(with_distances=True),RESULT_TREE)
self.assertEqual(len(tree.tips()), 7)
self.assertRaises(NotImplementedError, build_tree_from_alignment, \
self.align1, RNA, True)
remove(outtreefname)
def test_insert_sequences_into_tree(self):
"""Inserts sequences into Tree"""
params={}
# generate temp filename for output
params["-r"] = self.refseq_fname
params["-t"] = self.tree_fname
params["-s"] = self.stats_fname
params["--out-dir"] = "/tmp"
aln_ref_query=MinimalFastaParser(StringIO(QUERY_SEQS))
aln = Alignment(aln_ref_query)
seqs, align_map = aln.toPhylip()
tree = insert_sequences_into_tree(seqs, DNA, params=params,
write_log=False)
# rename tips back to query names
for node in tree.tips():
if node.Name in align_map:
node.Name = align_map[node.Name]
self.assertEqual(tree.getNewick(with_distances=True), RESULT_TREE)
class ParsInsertTests(TestCase):
def setUp(self):
# create a list of files to cleanup
self._paths_to_clean_up = []
self._dirs_to_clean_up = []
# load query seqs
self.seqs = Alignment(MinimalFastaParser(QUERY_SEQS.split()))
# generate temp filename
tmp_dir='/tmp'
self.outfile = get_tmp_filename(tmp_dir)
# create and write out reference sequence file
self.outfasta=splitext(self.outfile)[0]+'.fasta'
fastaout=open(self.outfasta,'w')
fastaout.write(REF_SEQS)
fastaout.close()
self._paths_to_clean_up.append(self.outfasta)
# create and write out starting tree file
self.outtree=splitext(self.outfile)[0]+'.tree'
treeout=open(self.outtree,'w')
treeout.write(REF_TREE)
treeout.close()
self._paths_to_clean_up.append(self.outtree)
def tearDown(self):
"""cleans up all files initially created"""
# remove the tempdir and contents
map(remove,self._paths_to_clean_up)
map(rmdir,self._dirs_to_clean_up)
def test_base_command(self):
"""Base command-calls"""
app = ParsInsert()
self.assertEqual(app.BaseCommand, \
''.join(['cd "',getcwd(),'/"; ','ParsInsert']))
def test_change_working_dir(self):
"""Change working dir"""
app = ParsInsert(WorkingDir='/tmp/ParsInsertTest')
self.assertEqual(app.BaseCommand, \
''.join(['cd "','/tmp/ParsInsertTest',\
'/"; ','ParsInsert']))
rmtree('/tmp/ParsInsertTest')
def test_insert_sequences_into_tree(self):
"""Inserts sequences into Tree"""
# define log fp
log_fp='/tmp/parsinsert.log'
self._paths_to_clean_up.append(log_fp)
# define tax assignment values fp
tax_assign_fp='/tmp/tax_assignments.log'
self._paths_to_clean_up.append(tax_assign_fp)
# set the reference alignment and starting tree
param={
'-t':self.outtree,
'-s':self.outfasta,
'-l':log_fp,
'-o':tax_assign_fp
}
seqs, align_map = self.seqs.toPhylip()
# insert sequences into tree
tree = insert_sequences_into_tree(seqs, DNA, params=param)
# rename tips back to query names
for node in tree.tips():
if node.Name in align_map:
node.Name = align_map[node.Name]
self.assertEqual(tree.getNewick(with_distances=True),exp_tree)
class ParsInsertTests(TestCase):
def setUp(self):
# create a list of files to cleanup
self._paths_to_clean_up = []
self._dirs_to_clean_up = []
# load query seqs
self.seqs = Alignment(MinimalFastaParser(QUERY_SEQS.split()))
# generate temp filename
tmp_dir = '/tmp'
self.outfile = get_tmp_filename(tmp_dir)
# create and write out reference sequence file
self.outfasta = splitext(self.outfile)[0] + '.fasta'
fastaout = open(self.outfasta, 'w')
fastaout.write(REF_SEQS)
fastaout.close()
self._paths_to_clean_up.append(self.outfasta)
# create and write out starting tree file
self.outtree = splitext(self.outfile)[0] + '.tree'
treeout = open(self.outtree, 'w')
treeout.write(REF_TREE)
treeout.close()
self._paths_to_clean_up.append(self.outtree)
def tearDown(self):
"""cleans up all files initially created"""
# remove the tempdir and contents
map(remove, self._paths_to_clean_up)
map(rmdir, self._dirs_to_clean_up)
def test_base_command(self):
"""Base command-calls"""
app = ParsInsert()
self.assertEqual(app.BaseCommand, \
''.join(['cd "',getcwd(),'/"; ','ParsInsert']))
def test_change_working_dir(self):
"""Change working dir"""
app = ParsInsert(WorkingDir='/tmp/ParsInsertTest')
self.assertEqual(app.BaseCommand, \
''.join(['cd "','/tmp/ParsInsertTest',\
'/"; ','ParsInsert']))
rmtree('/tmp/ParsInsertTest')
def test_insert_sequences_into_tree(self):
"""Inserts sequences into Tree"""
# define log fp
log_fp = '/tmp/parsinsert.log'
self._paths_to_clean_up.append(log_fp)
# define tax assignment values fp
tax_assign_fp = '/tmp/tax_assignments.log'
self._paths_to_clean_up.append(tax_assign_fp)
# set the reference alignment and starting tree
param = {
'-t': self.outtree,
'-s': self.outfasta,
'-l': log_fp,
'-o': tax_assign_fp
}
seqs, align_map = self.seqs.toPhylip()
# insert sequences into tree
tree = insert_sequences_into_tree(seqs, DNA, params=param)
# rename tips back to query names
for node in tree.tips():
if node.Name in align_map:
node.Name = align_map[node.Name]
self.assertEqual(tree.getNewick(with_distances=True), exp_tree)
