def build_subproblems(self):
(alignment, tree) = self.read_alignment_and_tree()
if options().distance != 1:
self.compute_distances(alignment)
assert isinstance(tree, PhylogeneticTree)
assert isinstance(alignment, MutableAlignment)
tree.get_tree().resolve_polytomies()
# Label edges with numbers so that we could assemble things back
# at the end
tree.lable_edges()
''' Make sure size values are set, and are meaningful. '''
self.check_and_set_sizes(alignment.get_num_taxa())
self._create_root_problem(tree, alignment)
''' Decompose the tree based on placement subsets'''
placement_tree_map = PhylogeneticTree(Tree(
tree.den_tree)).decompose_tree(
self.options.placement_size,
strategy=self.strategy,
minSize=self.options.placement_size /
int(self.options.exhaustive.placementminsubsetsizefacotr),
tree_map={},
pdistance=1,
decomp_strategy=self.decomp_strategy,
distances=self.distances,
maxDiam=None)
assert len(placement_tree_map) > 0, (
"Tree could not be decomposed"
" given the following settings; strategy:%s minsubsetsize:%s"
" placement_size:%s" %
(self.strategy, self.minsubsetsize, self.options.placement_size))
_LOG.info("Breaking into %d placement subsets." %
len(placement_tree_map))
''' For placement subsets create a placement subproblem,
and decompose further'''
for (p_key, p_tree) in placement_tree_map.items():
assert isinstance(p_tree, PhylogeneticTree)
placement_problem = SeppProblem(p_tree.leaf_node_names(),
self.root_problem)
placement_problem.subtree = p_tree
placement_problem.label = "P_%s" % str(p_key)
_LOG.debug(
"Placement subset %s has %d nodes" %
(placement_problem.label, len(p_tree.leaf_node_names())))
''' Further decompose to alignment subsets '''
alignment_tree_map = PhylogeneticTree(Tree(
p_tree.den_tree)).decompose_tree(
self.options.alignment_size,
strategy=self.strategy,
minSize=self.minsubsetsize,
tree_map={},
decomp_strategy=self.options.decomp_strategy,
pdistance=options().distance,
distances=self.distances,
maxDiam=self.options.maxDiam)
assert len(alignment_tree_map) > 0, (
"Tree could not be decomposed"
" given the following settings; strategy:%s"
" minsubsetsize:%s alignmet_size:%s" %
(self.strategy, self.minsubsetsize,
self.options.alignment_size))
_LOG.debug("Placement subset %s has %d alignment subsets: %s" %
(placement_problem.label, len(alignment_tree_map),
str(sorted(alignment_tree_map.keys()))))
_LOG.debug("Placement subset %s has %d taxa:" %
(placement_problem.label,
sum([
len(a_tree.leaf_node_names())
for a_tree in alignment_tree_map.values()
])))
for (a_key, a_tree) in alignment_tree_map.items():
assert isinstance(a_tree, PhylogeneticTree)
self.modify_tree(a_tree)
alignment_problem = SeppProblem(a_tree.leaf_node_names(),
placement_problem)
alignment_problem.subtree = a_tree
alignment_problem.label = "A_%s_%s" % (str(p_key), str(a_key))
_LOG.info("Breaking into %d alignment subsets." %
(len(list(self.root_problem.iter_leaves()))))
''' Divide fragments into chunks, to help achieve better parallelism'''
fragment_chunk_files = self.create_fragment_files()
self.root_problem.fragment_chunks = len(fragment_chunk_files)
for alignment_problem in self.root_problem.iter_leaves():
for afc in range(0, self.root_problem.fragment_chunks):
frag_chunk_problem = SeppProblem(alignment_problem.taxa,
alignment_problem)
frag_chunk_problem.subtree = alignment_problem.subtree
frag_chunk_problem.label = alignment_problem.label.replace(
"A_", "FC_") + "_" + str(afc)
frag_chunk_problem.fragments = fragment_chunk_files[afc]
_LOG.info("Breaking each alignment subset into %d fragment chunks." %
self.root_problem.fragment_chunks)
_LOG.debug("Subproblem structure: %s" % str(self.root_problem))
return self.root_problem
def testExtendedAlignment(self):
print "======= starting testExtendedAlignment ========="
subset = [
"SFIF", "SFII", "SCFC", "SGHD", "SDCC", "SBGE", "SFBB", "SDI",
"SCGB", "SJGF", "SGBI", "SCJA", "SGAD", "SHEB", "SFHB", "SDJI",
"SHED", "SJJJ", "SBBE", "SCCH", "SDJB", "SDAC", "SHEH", "SFDC",
"SFEI", "SHHB", "SC", "SIAB", "SDDI", "SBCB", "SJB", "SEBD",
"SFGD", "SHA", "SIDA", "SGHI", "SGIB", "SBFJ", "SFIE", "SCJF",
"SJHJ", "SJBG", "SEJI", "SFFF", "SJ", "SIII", "SJHH", "SEIH",
"SBDC", "SHDJ", "SJDD", "SGDB", "SIHA", "SIBB", "SECC", "SCAD",
"SGBB", "SGIF", "SJHC", "SFCD", "SEAA", "SEFF", "SDFG", "SDJE",
"SCFG", "SFH", "SCJ", "SDDD", "SEGD", "SCIH", "SDAG", "SCJE",
"SFAJ", "SIDJ", "SE", "SHBC", "SJFF", "SCHD", "SBHA", "SEDF",
"SFAF", "SEDD", "SDHD", "SGJD", "SIBH", "SGDF", "SIFA", "SJGA",
"SIJB", "SFI", "SGA", "SBFC", "SBJA", "SFFC", "SFDH", "SFEE",
"SBDF", "SGBJ", "SDHE", "SJIB", "SHHI", "SIDE", "SJII"
]
alg = MutableAlignment()
alg.read_filepath("data/simulated/test.fasta")
alg.delete_all_gap()
tlen = alg.get_length()
frg = MutableAlignment()
frg.read_filepath("data/simulated/test.fas")
#print frg.get_num_taxa()
pp = SeppProblem(alg.keys())
pp.fragments = frg
pp.subalignment = alg
cp1 = SeppProblem(subset, pp)
cp2 = SeppProblem(list(set(alg.keys()) - set(subset)), pp)
cp1.fragments = ReadonlySubalignment(
[k for k in frg.keys() if int(k[-1]) >= 9], frg)
cp2.fragments = ReadonlySubalignment(
[k for k in frg.keys() if int(k[-1]) <= 1], frg)
cp1labels = cp1.write_subalignment_without_allgap_columns(
"data/tmp/cp1.fasta")
cp2labels = cp2.write_subalignment_without_allgap_columns(
"data/tmp/cp2.fasta")
tmp = MutableAlignment().read_filepath("data/tmp/cp1.fasta")
assert all(
[not tmp.is_all_gap(pos) for pos in xrange(0, tmp.get_length())])
tmp = MutableAlignment().read_filepath("data/tmp/cp2.fasta")
assert all(
[not tmp.is_all_gap(pos) for pos in xrange(0, tmp.get_length())])
cp1.fragments.write_to_path("data/tmp/cp1.frags.fas")
cp2.fragments.write_to_path("data/tmp/cp2.frags.fas")
'''We have done the hmmalign before. don't worry about that right now'''
ext1 = ExtendedAlignment(cp1.fragments)
ext1.build_extended_alignment("data/tmp/cp1.fasta",
"data/tmp/cp1.extended.sto")
ext1.relabel_original_columns(cp1labels)
ext2 = ExtendedAlignment(cp2.fragments)
ext2.build_extended_alignment("data/tmp/cp2.fasta",
"data/tmp/cp2.extended.sto")
ext2.relabel_original_columns(cp2labels)
extmerger = ExtendedAlignment([])
extmerger.merge_in(ext1)
mixed = extmerger.merge_in(ext2)
extmerger.write_to_path("data/tmp/extended.merged.fasta")
assert extmerger.is_aligned(), "Merged alignment is not aligned"
in1 = len([x for x in ext1._col_labels if x < 0])
in2 = len([x for x in ext2._col_labels if x < 0])
print "Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d" % (
extmerger.get_length(), in1, in2, tlen)
assert (in1 + in2 + tlen - mixed) == extmerger.get_length(
), "Lengths don't match up after merging. Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d Mixed-insertion: %d" % (
extmerger.get_length(), in1, in2, tlen, mixed)
assert (in1 + in2 - mixed) == len(
list(extmerger.iter_insertion_columns())
), "Columns are not correctly labeled after merging. Merged insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion: %d" % (
len(list(extmerger.iter_insertion_columns())), in1, in1, mixed)
tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment()
tmp.delete_all_gap()
assert tmp.is_aligned(), "merged alignment should be aligned!"
assert tmp.get_length() == tlen, "merged alignment has wrong length"
assert all([alg[k] == s for (k, s) in tmp.items()
]), "merged alignment should match original alignment"
print "======= finished testExtendedAlignment ========="
def _create_root_problem(self, tree, alignment):
''' Create the root problem'''
self.root_problem = SeppProblem(tree.leaf_node_names())
self.root_problem.label = "root"
self.root_problem.subalignment = alignment
self.root_problem.subtree = tree
for dir in dirs:
print "Working on %s\n" % dir
aligned_files = glob.glob('%sFC_*/hmmalign.results.*' % dir)
sequence_files = glob.glob('%sFC_*/hmmalign.frag.*' % dir)
base_alignment_file = glob.glob('%s/*.fasta' % dir)
base_alignment = MutableAlignment()
done = base_alignment.read_filepath(base_alignment_file[0])
subbackbone = original_backbone.get_soft_sub_alignment(base_alignment.get_sequence_names())
frags = MutableAlignment()
sequence_names = []
for file in sequence_files:
seq = MutableAlignment()
done = seq.read_filepath(file)
done = sequence_names.extend(seq.get_sequence_names())
for name, seq in seq.iteritems():
frags[name] = seq.upper()
problem = SeppProblem(sequence_names)
problem.set_subalignment(subbackbone)
mut_subalg = problem.subalignment.get_mutable_alignment()
remaining_cols = mut_subalg.delete_all_gap()
problem.annotations["ref.alignment.columns"] = remaining_cols
problem.fragments = frags
ap_alg = problem.read_extendend_alignment_and_relabel_columns\
(base_alignment_file, aligned_files)
extendedAlignment.merge_in(ap_alg,convert_to_string=False)
extendedAlignment.write_to_path("/projects/sate8/namphuon/ultra_large/1000000/upp_100_10_new/upp.unmasked.fasta")
extendedAlignment.remove_insertion_columns()
extendedAlignment.write_to_path("/projects/sate8/namphuon/ultra_large/1000000/upp_100_10_new/upp.masked.fasta")
def testExtendedAlignment(self):
print "======= starting testExtendedAlignment ========="
subset = ["SFIF","SFII","SCFC","SGHD","SDCC","SBGE","SFBB","SDI","SCGB","SJGF","SGBI","SCJA","SGAD","SHEB","SFHB","SDJI","SHED","SJJJ","SBBE","SCCH","SDJB","SDAC","SHEH","SFDC","SFEI","SHHB","SC","SIAB","SDDI","SBCB","SJB","SEBD","SFGD","SHA","SIDA","SGHI","SGIB","SBFJ","SFIE","SCJF","SJHJ","SJBG","SEJI","SFFF","SJ","SIII","SJHH","SEIH","SBDC","SHDJ","SJDD","SGDB","SIHA","SIBB","SECC","SCAD","SGBB","SGIF","SJHC","SFCD","SEAA","SEFF","SDFG","SDJE","SCFG","SFH","SCJ","SDDD","SEGD","SCIH","SDAG","SCJE","SFAJ","SIDJ","SE","SHBC","SJFF","SCHD","SBHA","SEDF","SFAF","SEDD","SDHD","SGJD","SIBH","SGDF","SIFA","SJGA","SIJB","SFI","SGA","SBFC","SBJA","SFFC","SFDH","SFEE","SBDF","SGBJ","SDHE","SJIB","SHHI","SIDE","SJII"]
alg = MutableAlignment()
alg.read_filepath("data/simulated/test.fasta")
alg.delete_all_gap()
tlen = alg.get_length()
frg = MutableAlignment()
frg.read_filepath("data/simulated/test.fas")
#print frg.get_num_taxa()
pp = SeppProblem(alg.keys())
pp.fragments = frg
pp.subalignment = alg
cp1 = SeppProblem(subset, pp)
cp2 = SeppProblem(list(set(alg.keys()) -set(subset)), pp)
cp1.fragments = ReadonlySubalignment([k for k in frg.keys() if int(k[-1]) >= 9], frg)
cp2.fragments = ReadonlySubalignment([k for k in frg.keys() if int(k[-1]) <= 1], frg)
cp1labels = cp1.write_subalignment_without_allgap_columns("data/tmp/cp1.fasta")
cp2labels = cp2.write_subalignment_without_allgap_columns("data/tmp/cp2.fasta")
tmp = MutableAlignment().read_filepath("data/tmp/cp1.fasta")
assert all([not tmp.is_all_gap(pos) for pos in xrange(0,tmp.get_length())])
tmp = MutableAlignment().read_filepath("data/tmp/cp2.fasta")
assert all([not tmp.is_all_gap(pos) for pos in xrange(0,tmp.get_length())])
cp1.fragments.write_to_path("data/tmp/cp1.frags.fas")
cp2.fragments.write_to_path("data/tmp/cp2.frags.fas")
'''We have done the hmmalign before. don't worry about that right now'''
ext1 = ExtendedAlignment(cp1.fragments)
ext1.build_extended_alignment("data/tmp/cp1.fasta", "data/tmp/cp1.extended.sto")
ext1.relabel_original_columns(cp1labels)
ext2 = ExtendedAlignment(cp2.fragments)
ext2.build_extended_alignment("data/tmp/cp2.fasta", "data/tmp/cp2.extended.sto")
ext2.relabel_original_columns(cp2labels)
extmerger = ExtendedAlignment([])
extmerger.merge_in(ext1)
mixed = extmerger.merge_in(ext2)
extmerger.write_to_path("data/tmp/extended.merged.fasta")
assert extmerger.is_aligned(), "Merged alignment is not aligned"
in1 = len([x for x in ext1._col_labels if x<0])
in2 = len([x for x in ext2._col_labels if x<0])
print "Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d" %(extmerger.get_length(),in1 , in2 , tlen)
assert ( in1 + in2 + tlen - mixed) == extmerger.get_length(), "Lengths don't match up after merging. Merged:%d. Insertion1:%d Insertion2:%d BaseLen:%d Mixed-insertion: %d" %(extmerger.get_length(),in1, in2 , tlen, mixed)
assert ( in1 + in2 - mixed) == len(list(extmerger.iter_insertion_columns())), "Columns are not correctly labeled after merging. Merged insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion: %d" %(len(list(extmerger.iter_insertion_columns())),in1 , in1, mixed)
tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment()
tmp.delete_all_gap()
assert tmp.is_aligned(), "merged alignment should be aligned!"
assert tmp.get_length() == tlen, "merged alignment has wrong length"
assert all([alg[k] == s for (k,s) in tmp.items()]), "merged alignment should match original alignment"
print "======= finished testExtendedAlignment ========="
print("num base alignment seqs: ",
len(base_alignment.get_sequence_names()))
frags = MutableAlignment()
sequence_names = []
for file in sequence_files:
seq = MutableAlignment()
done = seq.read_filepath(file)
print('query sequence names:', seq.get_sequence_names())
print("query sequence length:", seq.get_length())
done = sequence_names.extend(seq.get_sequence_names())
for name, seq in seq.items():
frags[name] = seq.upper()
problem = SeppProblem(sequence_names)
problem.set_subalignment(subbackbone)
# constructs sub-base-alignment from the full alignment, delete all gaps
mut_subalg = problem.subalignment.get_mutable_alignment()
remaining_cols = mut_subalg.delete_all_gap()
problem.annotations["ref.alignment.columns"] = remaining_cols
print("num remaining_cols: ", len(remaining_cols))
problem.fragments = frags
ap_alg = problem.read_extendend_alignment_and_relabel_columns(
base_alignment_file, aligned_files)
extendedAlignment.merge_in(ap_alg, convert_to_string=True)
extendedAlignment.write_to_path(dir + "merged_alignment_unmasked_" + flag +
".fasta")
def build_subproblems(self):
(alignment, tree) = self.read_alignment_and_tree()
assert isinstance(tree, PhylogeneticTree)
assert isinstance(alignment, MutableAlignment)
tree.get_tree().resolve_polytomies()
# Label edges with numbers so that we could assemble things back
# at the end
tree.lable_edges()
''' Make sure size values are set, and are meaningful. '''
self.check_and_set_sizes(alignment.get_num_taxa())
self._create_root_problem(tree, alignment)
''' Decompose the tree based on placement subsets'''
placement_tree_map = PhylogeneticTree(Tree(tree.den_tree)).decompose_tree(
self.options.placement_size,
strategy=self.strategy,
minSize = self.minsubsetsize,
tree_map = {})
assert len(placement_tree_map) > 0, ("Tree could not be decomposed"
" given the following settings; strategy:%s minsubsetsize:%s placement_size:%s"
%(self.strategy, self.minsubsetsize, self.options.placement_size))
_LOG.info("Breaking into %d placement subsets." %len(placement_tree_map))
''' For placement subsets create a placement subproblem, and decompose further'''
for (p_key,p_tree) in placement_tree_map.items():
assert isinstance(p_tree, PhylogeneticTree)
placement_problem = SeppProblem(p_tree.leaf_node_names(), self.root_problem)
placement_problem.subtree = p_tree
placement_problem.label = "P_%s" %str(p_key)
_LOG.debug("Placement subset %s has %d nodes" %(placement_problem.label,len(p_tree.leaf_node_names())))
''' Further decompose to alignment subsets '''
alignment_tree_map = PhylogeneticTree(Tree(p_tree.den_tree)).decompose_tree(
self.options.alignment_size,
strategy=self.strategy,
minSize = self.minsubsetsize,
tree_map = {}, decomp_strategy = self.options.decomp_strategy)
assert len(alignment_tree_map) > 0, ("Tree could not be decomposed"
" given the following settings; strategy:%s minsubsetsize:%s alignmet_size:%s"
%(self.strategy, self.minsubsetsize, self.options.alignment_size))
_LOG.debug("Placement subset %s has %d alignment subsets: %s" %(placement_problem.label,len(alignment_tree_map.keys()),str(sorted(alignment_tree_map.keys()))))
_LOG.debug("Placement subset %s has %d taxa:" %(placement_problem.label,sum([len(a_tree.leaf_node_names()) for a_tree in alignment_tree_map.values()])))
for (a_key, a_tree) in alignment_tree_map.items():
assert isinstance(a_tree, PhylogeneticTree)
self.modify_tree(a_tree)
alignment_problem = SeppProblem(a_tree.leaf_node_names(),
placement_problem)
alignment_problem.subtree = a_tree
alignment_problem.label = "A_%s_%s" %(str(p_key),str(a_key))
''' Divide fragments into chunks, to help achieve better parallelism'''
fragment_chunk_files = self.create_fragment_files()
for alignment_problem in self.root_problem.iter_leaves():
for afc in xrange(0,len(fragment_chunk_files)):
frag_chunk_problem = SeppProblem(alignment_problem.taxa,
alignment_problem)
frag_chunk_problem.subtree = alignment_problem.subtree
frag_chunk_problem.label = alignment_problem.label.replace("A_", "FC_") + "_" +str(afc)
frag_chunk_problem.fragments = fragment_chunk_files[afc]
_LOG.info("Breaking into %d alignment subsets." %(len(list(self.root_problem.iter_leaves()))))
_LOG.info("Breaking each alignment subset into %d fragment chunks." %len(fragment_chunk_files))
_LOG.info("Subproblem structure: %s" %str(self.root_problem))
return self.root_problem
aligned_files = glob.glob('%sFC_*/hmmalign.results.*' % dir)
sequence_files = glob.glob('%sFC_*/hmmalign.frag.*' % dir)
base_alignment_file = glob.glob('%s/*.fasta' % dir)
base_alignment = MutableAlignment()
done = base_alignment.read_filepath(base_alignment_file[0])
subbackbone = original_backbone.get_soft_sub_alignment(
base_alignment.get_sequence_names())
frags = MutableAlignment()
sequence_names = []
for file in sequence_files:
seq = MutableAlignment()
done = seq.read_filepath(file)
done = sequence_names.extend(seq.get_sequence_names())
for name, seq in seq.items():
frags[name] = seq.upper()
problem = SeppProblem(sequence_names)
problem.set_subalignment(subbackbone)
mut_subalg = problem.subalignment.get_mutable_alignment()
remaining_cols = mut_subalg.delete_all_gap()
problem.annotations["ref.alignment.columns"] = remaining_cols
problem.fragments = frags
ap_alg = problem.read_extendend_alignment_and_relabel_columns(
base_alignment_file, aligned_files)
extendedAlignment.merge_in(ap_alg, convert_to_string=False)
extendedAlignment.write_to_path("/projects/sate8/namphuon/ultra_large/1000000/"
"upp_100_10_new/upp.unmasked.fasta")
extendedAlignment.remove_insertion_columns()
extendedAlignment.write_to_path("/projects/sate8/namphuon/ultra_large/1000000/"
"upp_100_10_new/upp.masked.fasta")
