def testAlignmentReadFasta(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
assert len(alg) == 65, "MutableAlignment length is %s" % len(alg)
assert all([not alg.is_all_gap(i) for i in range(0, alg.get_length())])
def check_options(self):
self.check_outputprefix()
options().info_file = "A_dummy_value"
# Check to see if tree/alignment/fragment file provided, if not,
# generate it from sequence file
if ((not options().tree_file is None)
and (not options().alignment_file is None)
and (not options().sequence_file is None)):
options().fragment_file = options().sequence_file
elif ((options().tree_file is None)
and (options().alignment_file is None)
and (not options().sequence_file is None)):
self.generate_backbone()
else:
_LOG.error(
("Either specify the backbone alignment and tree and query "
"sequences or only the query sequences. Any other "
"combination is invalid"))
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
backbone_size = sequences.get_num_taxa()
if options().backbone_size is None:
options().backbone_size = backbone_size
assert options().backbone_size == backbone_size, (
("Backbone parameter needs to match actual size of backbone; "
"backbone parameter:%s backbone_size:%s") %
(options().backbone_size, backbone_size))
if options().placement_size is None:
options().placement_size = options().backbone_size
return ExhaustiveAlgorithm.check_options(self)
def check_options(self):
options().info_file = "A_dummy_value"
if options().tree_file is None or options().alignment_file is None:
_LOG.error("Specify the backbone alignment and tree and query sequences")
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
return ExhaustiveAlgorithm.check_options(self)
def check_options(self):
options().info_file = "A_dummy_value"
if options().tree_file is None or options().alignment_file is None:
_LOG.error("Specify the backbone alignment and tree and query sequences")
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
return ExhaustiveAlgorithm.check_options(self)
def hmmer_to_markers(input, temp_dir):
global marker_genes
fragments = MutableAlignment()
fragments.read_filepath(input)
reverse = dict([(name+'_rev', reverse_sequence(seq))
for (name, seq) in fragments.items()])
all_frags = MutableAlignment()
all_frags.set_alignment(fragments)
all_frags.set_alignment(reverse)
frag_file = temp_dir+"/frags.fas"
_write_fasta(all_frags, frag_file)
# Now bin the fragments
frag_scores = dict([(name, [-10000, 'NA', 'NA'])
for name in fragments.keys()])
gene_set = marker_genes
align_name = 'sate'
if (options().genes == 'cogs'):
gene_set = cog_genes
align_name = 'pasta'
for gene in gene_set:
# Now run HMMER search
hmmer_search(
frag_file,
os.path.join(
options().__getattribute__('reference').path,
'refpkg/%s.refpkg/%.profile' % (gene, align_name)),
temp_dir + "/%s.out" % gene)
results = read_hmmsearch_results(temp_dir + "/%s.out" % gene)
# Now select best direction for each frag
for name, value in results.items():
bitscore = value[1]
direction = 'forward'
true_name = name
if (name.find('_rev') != -1):
true_name = true_name.replace('_rev', '')
direction = 'reverse'
if frag_scores[true_name][0] < bitscore:
frag_scores[true_name] = [bitscore, gene, direction]
# Now bin the fragments
genes = dict([])
for name, val in frag_scores.items():
if (val[1] not in genes):
genes[val[1]] = {}
if (val[2] == 'forward'):
genes[val[1]][name] = fragments[name]
else:
genes[val[1]][name] = reverse_sequence(fragments[name])
genes.pop("NA", None)
for gene, seq in genes.items():
gene_file = temp_dir + "/%s.frags.fas" % gene
_write_fasta(seq, gene_file + ".fixed")
return genes
def testAlignmentReadFasta(self):
print "====== starting testAlignmentReadFasta =========="
alg = MutableAlignment()
alg.read_filepath("data/mock/pyrg/sate.fasta")
print "Maing alignment is:\n\n", alg
assert len(alg) == 65, "MutableAlignment length is %s" %len(alg)
assert all([not alg.is_all_gap(i) for i in xrange(0,alg.get_length())])
def hmmer_to_markers(input, temp_dir):
global marker_genes
fragments = MutableAlignment()
fragments.read_filepath(input)
reverse = dict([(name + "_rev", reverse_sequence(seq)) for (name, seq) in fragments.items()])
all_frags = MutableAlignment()
all_frags.set_alignment(fragments)
all_frags.set_alignment(reverse)
frag_file = temp_dir + "/frags.fas"
_write_fasta(all_frags, frag_file)
# Now bin the fragments
frag_scores = dict([(name, [-10000, "NA", "NA"]) for name in fragments.keys()])
gene_set = marker_genes
align_name = "sate"
if options().genes == "cogs":
gene_set = cog_genes
align_name = "pasta"
for gene in gene_set:
# Now run HMMER search
hmmer_search(
frag_file,
os.path.join(
options().__getattribute__("reference").path, "refpkg/%s.refpkg/%.profile" % (gene, align_name)
),
temp_dir + "/%s.out" % gene,
)
results = read_hmmsearch_results(temp_dir + "/%s.out" % gene)
# Now select best direction for each frag
for name in results.keys():
bitscore = results[name][1]
direction = "forward"
true_name = name
if name.find("_rev") != -1:
true_name = true_name.replace("_rev", "")
direction = "reverse"
if frag_scores[true_name][0] < bitscore:
frag_scores[true_name] = [bitscore, gene, direction]
# Now bin the fragments
genes = dict([])
for name in frag_scores.keys():
if frag_scores[name][1] not in genes:
genes[frag_scores[name][1]] = {}
if frag_scores[name][2] == "forward":
genes[frag_scores[name][1]][name] = fragments[name]
else:
genes[frag_scores[name][1]][name] = reverse_sequence(fragments[name])
genes.pop("NA", None)
for gene in genes.keys():
gene_file = temp_dir + "/%s.frags.fas" % gene
_write_fasta(genes[gene], gene_file + ".fixed")
return genes
def blast_to_markers(input, temp_dir):
fragments = MutableAlignment()
fragments.read_filepath(input)
if (options().gene is None):
# First blast sequences against all markers
blast_results = temp_dir + "/blast.out"
if (options().blast_file is None):
print("Blasting fragments against marker dataset\n")
blast_fragments(input, blast_results)
else:
blast_results = options().blast_file
# Next bin the blast hits to the best gene
gene_binning = bin_blast_results(blast_results)
else:
gene_binning = {options().gene: list(fragments.keys())}
# Now figure out direction of fragments
binned_fragments = dict([
(gene, dict([(seq_name, fragments[seq_name])
for seq_name in gene_binning[gene]]))
for gene in gene_binning])
print("Finding best orientation of reads\n")
align_name = 'sate'
if (options().genes == 'cogs'):
align_name = 'pasta'
for (gene, frags) in binned_fragments.items():
# Add reverse complement sequence
frags_rev = dict([(name + '_rev', reverse_sequence(seq))
for (name, seq) in frags.items()])
gene_frags = MutableAlignment()
gene_frags.set_alignment(frags)
gene_frags.set_alignment(frags_rev)
gene_file = temp_dir + "/%s.frags.fas" % gene
_write_fasta(gene_frags, gene_file)
# Now run HMMER search
hmmer_search(
gene_file,
os.path.join(
options().__getattribute__('reference').path,
'refpkg/%s.refpkg/%s.hmm' % (gene, align_name)),
temp_dir + "/%s.out" % gene)
results = read_hmmsearch_results(temp_dir + "/%s.out" % gene)
# Now select best direction for each frag
for key in frags:
forward_score = -10000
backward_score = -10000
if (key in results):
forward_score = results[key][1]
if (key+"_rev" in results):
backward_score = results[key + "_rev"][1]
if (backward_score > forward_score):
frags[key] = gene_frags[key + "_rev"]
# Now write to file
_write_fasta(frags, gene_file + ".fixed")
binned_fragments[gene] = frags
return binned_fragments
def read_alignment_and_tree(self):
_LOG.info("Reading input alignment: %s" %(self.options.alignment_file))
alignment = MutableAlignment()
alignment.read_file_object(self.options.alignment_file)
#fragments = MutableAlignment()
#fragments.read_file_object(self.options.fragment_file);
_LOG.info("Reading input tree: %s" %(self.options.tree_file))
tree = PhylogeneticTree( dendropy.Tree(stream=self.options.tree_file,
schema="newick",
preserve_underscores=True))
return (alignment, tree)
def testReadOnlySubAlignment(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
subset = [
'NC_008701_720717_722309', 'NC_013156_149033_150643',
'NC_013887_802739_801129'
]
readonly_subalignment = ReadonlySubalignment(subset, alg)
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert set(readonly_subalignment.keys()) == set(
readonly_subalignment.get_sequence_names()) == set(subset), \
"Subalignment keys not matching given keys %s vs %s" % (
list(readonly_subalignment.keys()), subset)
for (k, s) in list(readonly_subalignment.items()):
assert k in subset, \
"%s not found in subset but returned by subalignment" % k
assert s == alg[k], \
"sequence associated with %s not matching parent alignment" % k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(), \
"alignment length should not change"
assert readonly_subalignment.is_aligned() is True
assert readonly_subalignment.is_all_gap(2) is True, \
"Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(150) is False, \
"Site 100 should not be all gaps"
readonly_subalignment.write_to_path(
self.fp_dummy1) # "mock/pyrg/sate.sub.fasta"
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([
not mutable_subalignment.is_all_gap(i)
for i in range(0, mutable_subalignment.get_length())
])
def read_alignment_and_tree(self):
_LOG.info("Reading input alignment: %s" %
(self.options.alignment_file))
alignment = MutableAlignment()
alignment.read_file_object(self.options.alignment_file)
# fragments = MutableAlignment()
# fragments.read_file_object(self.options.fragment_file);
_LOG.info("Reading input tree: %s" % self.options.tree_file)
tree = PhylogeneticTree(
dendropy.Tree.get_from_stream(self.options.tree_file,
schema="newick",
preserve_underscores=True))
return (alignment, tree)
def main():
args = parse_args()
sequences = MutableAlignment()
assert os.path.isfile(args.input) and os.access(args.input, os.R_OK), "Input file %s does not exist\n" % args.input
sequences.read_file_object(args.input)
frag = MutableAlignment()
full = MutableAlignment()
for (key,seq) in sequences.items():
if (len(seq) <= args.threshold):
frag[key]=seq
else:
full[key]=seq
frag.write_to_path("%s.frag.fas" % args.output)
full.write_to_path("%s.full.fas" % args.output)
def read_and_divide_fragments(self, chunks, extra_frags={}):
max_chunk_size = self.options.max_chunk_size
_LOG.debug(
"start reading fragment files and breaking to at least %s chunks but at most %s sequences "
% (str(chunks), str(max_chunk_size)))
self.root_problem.fragments = MutableAlignment()
self.root_problem.fragments.read_file_object(
self.options.fragment_file)
# test if input fragment names might collide with reference names.
# code contribution by Stefan Janssen (June 13th, 2018)
ids_reference = set(self.root_problem.subalignment.keys())
ids_inputfragments = set(self.root_problem.fragments.keys())
ids_overlap = ids_reference & ids_inputfragments
if len(ids_overlap) > 0:
raise ValueError(
("Your input fragment file contains %i sequences, whose names "
"overlap with names in your reference. Please rename your inp"
"ut fragments and re-start. Duplicate names are:\n '%s'") %
(len(ids_overlap), "'\n '".join(ids_overlap)))
for (k, v) in extra_frags.items():
self.root_problem.fragments[k] = v.replace("-", "")
alg_chunks = self.root_problem.fragments.divide_to_equal_chunks(
chunks, max_chunk_size)
ret = []
for i in range(0, len(alg_chunks)):
temp_file = None
if alg_chunks[i]:
temp_file = get_temp_file("fragment_chunk_%d" % i,
"fragment_chunks", ".fasta")
alg_chunks[i].write_to_path(temp_file)
ret.append(temp_file)
_LOG.debug("fragment files read and divided.")
return ret
def figureout_fragment_subset(self):
''' Figure out which fragment should go to which subproblem'''
# We need to keep and check the following flag because of checkpoining scenarios (join already done before!)
if self.root_problem.annotations.has_key(
"fragments.distribution.done"):
return
bitscores = dict([(name, [])
for name in self.root_problem.fragments.keys()])
for fragment_chunk_problem in self.root_problem.iter_leaves():
align_problem = fragment_chunk_problem.get_parent()
assert isinstance(align_problem, SeppProblem)
'''For each subproblem start with an empty set of fragments,
and add to them as we encounter new best hits for that subproblem'''
if align_problem.fragments is None:
align_problem.fragments = MutableAlignment()
search_res = fragment_chunk_problem.get_job_result_by_name(
"hmmsearch")
for key in search_res.keys():
''' keep a list of all hits, and their bit scores'''
bitscores[key].append((search_res[key][1], align_problem))
for frag, tuplelist in bitscores.iteritems():
''' TODO: what to do with those that are not? For now, only output warning message'''
#TODO: Need to double check and fix the math
if len(tuplelist) == 0:
_LOG.warning("Fragment %s is not scored against any subset" %
str(frag))
continue
''' convert bit scores to probabilities '''
denum = sum(math.pow(2, min(x[0], 1022)) for x in tuplelist)
tuplelist = [((math.pow(2, min(x[0], 1022)) / denum * 1000000),
x[1]) for x in tuplelist]
''' Sort subsets by their probability'''
tuplelist.sort(reverse=True)
''' Find enough subsets to reach the threshold '''
selected = tuplelist[0:max(
1,
reduce(
lambda x, y: (x[0], None) if x[1] is None else
(y[0], x[1] + y[1])
if x[1] < int(1000000 * self.alignment_threshold) else
(y[0], None), enumerate([x[0] for x in tuplelist]))[0])]
''' Renormalize the selected list to add up to 1'''
renorm = 0
for (prob, align_problem) in selected:
renorm = renorm + prob / 1000000
renorm = 1 / renorm
_LOG.debug("Fragment %s assigned to %d subsets" %
(frag, len(selected)))
''' Rename the fragment and assign it to the respective subsets'''
for (prob, align_problem) in selected:
postfix = prob * renorm if options(
).exhaustive.weight_placement_by_alignment.lower(
) == "true" else 1000000
frag_rename = "%s_%s_%d" % (frag, align_problem.label, postfix)
align_problem.fragments[
frag_rename] = self.root_problem.fragments[frag]
self.root_problem.annotations["fragments.distribution.done"] = 1
def read_and_divide_fragments(self, chunks, extra_frags={}):
max_chunk_size = self.options.max_chunk_size
_LOG.debug(
("start reading fragment files and breaking to at least %s chunks"
" but at most %s sequences ") %
(str(chunks), str(max_chunk_size)))
self.root_problem.fragments = MutableAlignment()
self.root_problem.fragments.read_file_object(
self.options.fragment_file)
# test if input fragment names might collide with reference names.
# code contribution by Stefan Janssen (June 13th, 2018)
ids_reference = set(self.root_problem.subalignment.keys())
ids_inputfragments = set(self.root_problem.fragments.keys())
ids_overlap = ids_reference & ids_inputfragments
if len(ids_overlap) > 0 and not self.options.ignore_overlap:
raise ValueError(
("Your input fragment file contains %i sequences, whose names "
"overlap with names in your reference. Please rename your inp"
"ut fragments and re-start. Duplicate names are:\n '%s'") %
(len(ids_overlap), "'\n '".join(ids_overlap)))
elif len(ids_overlap) > 0:
_LOG.debug("Ignoring following %i query sequences present "
"in the backbone: \n '%s'" %
(len(ids_overlap), "' , '".join(ids_overlap)))
self.root_problem.fragments = self.root_problem.fragments.\
get_soft_sub_alignment(ids_inputfragments - ids_reference)
# test if input fragment names contain whitespaces / tabs which would
# cause hmmsearch to fail.
# code contribution by Stefan Janssen (June 22nd, 2018)
ids_inputfragments_spaces = [
id_ for id_ in ids_inputfragments if (' ' in id_) or ('\t' in id_)
]
if len(ids_inputfragments_spaces) > 0:
raise ValueError(
("Your input fragment file contains %i sequences, whose names "
"contain either whitespaces: ' ' or tabulator '\\t' symbols. "
"Please rename your input fragments and re-start. Affected "
"names are:\n '%s'") %
(len(ids_inputfragments_spaces),
"'\n '".join(ids_inputfragments_spaces)))
for (k, v) in extra_frags.items():
self.root_problem.fragments[k] = v.replace("-", "")
alg_chunks = self.root_problem.fragments.divide_to_equal_chunks(
chunks, max_chunk_size)
ret = []
for i in range(0, len(alg_chunks)):
temp_file = None
if alg_chunks[i]:
temp_file = get_temp_file("fragment_chunk_%d" % i,
"fragment_chunks", ".fasta")
alg_chunks[i].write_to_path(temp_file)
ret.append(temp_file)
_LOG.debug("fragment files read and divided.")
return ret
def generate_backbone(self):
_LOG.info("Reading input sequences: %s" %(self.options.sequence_file))
sequences = MutableAlignment()
sequences.read_file_object(self.options.sequence_file)
if (options().backbone_size is None):
options().backbone_size = min(100,int(.20*sequences.get_num_taxa()))
_LOG.info("Backbone size set to: %d" %(options().backbone_size))
backbone_sequences = sequences.get_hard_sub_alignment(random.sample(sequences.keys(), options().backbone_size))
[sequences.pop(i) for i in backbone_sequences.keys()]
_LOG.info("Writing query and backbone set. ")
query = get_temp_file("query", "backbone", ".fas")
backbone = get_temp_file("backbone", "backbone", ".fas")
_write_fasta(sequences, query)
_write_fasta(backbone_sequences, backbone)
_LOG.info("Generating sate backbone alignment and tree. ")
satealignJob = SateAlignJob()
moleculeType = options().molecule
if (options().molecule == 'amino'):
moleculeType = 'protein'
satealignJob.setup(backbone,options().backbone_size,self.options.outdir,moleculeType,options().cpu)
satealignJob.run()
satealignJob.read_results()
options().placement_size = self.options.backbone_size
options().alignment_file = open(self.options.outdir + "/sate.fasta")
options().tree_file = open(self.options.outdir + "/sate.fasttree")
_LOG.info("Backbone alignment written to %s.\nBackbone tree written to %s" % (options().alignment_file, options().tree_file))
options().fragment_file = query
def testReadOnlySubAlignment(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
subset = ['NC_008701_720717_722309', 'NC_013156_149033_150643',
'NC_013887_802739_801129']
readonly_subalignment = ReadonlySubalignment(subset, alg)
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert set(readonly_subalignment.keys()) == set(
readonly_subalignment.get_sequence_names()) == set(subset), \
"Subalignment keys not matching given keys %s vs %s" % (
list(readonly_subalignment.keys()), subset)
for (k, s) in list(readonly_subalignment.items()):
assert k in subset, \
"%s not found in subset but returned by subalignment" % k
assert s == alg[k], \
"sequence associated with %k not matching parent alignment" % k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(), \
"alignment length should not change"
assert readonly_subalignment.is_aligned() is True
assert readonly_subalignment.is_all_gap(2) is True, \
"Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(150) is False, \
"Site 100 should not be all gaps"
readonly_subalignment.write_to_path(
self.fp_dummy1) # "mock/pyrg/sate.sub.fasta"
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([not mutable_subalignment.is_all_gap(i)
for i in range(0, mutable_subalignment.get_length())])
def testAlignmentReadFasta(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
assert len(alg) == 65, "MutableAlignment length is %s" % len(alg)
assert all([not alg.is_all_gap(i) for i in range(0, alg.get_length())])
def testReadOnlySubAlignment(self):
print "======= starting testReadOnlySubAlignment ========="
alg = MutableAlignment()
alg.read_filepath("data/mock/pyrg/sate.fasta")
subset = alg.keys()[9:12]
readonly_subalignment = ReadonlySubalignment(subset, alg)
print "subalignment is:\n\n", readonly_subalignment
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert readonly_subalignment.keys() == readonly_subalignment.get_sequence_names() == subset, "Subalignment keys not matching given keys %s vs %s" %(readonly_subalignment.keys() , subset)
for (k, s) in readonly_subalignment.items():
assert k in subset, "%s not found in subset but returned by subalignment" %k
assert s == alg[k], "sequence associated with %k not matching parent alignment" %k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(), "alignment length should not change"
assert readonly_subalignment.is_aligned() == True
assert readonly_subalignment.is_all_gap(2) == True, "Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(150) == False, "Site 100 should not be all gaps"
readonly_subalignment.write_to_path("data/mock/pyrg/sate.sub.fasta")
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([not mutable_subalignment.is_all_gap(i) for i in xrange(0,mutable_subalignment.get_length())])
print "======= finishing testReadOnlySubAlignment ========="
def check_options(self):
options().info_file = "A_dummy_value"
#Check to see if tree/alignment/fragment file provided, if not, generate it
#from sequence file
if not options().tree_file is None and not options().alignment_file is None and not options().sequence_file is None:
options().fragment_file = options().sequence_file
elif options().tree_file is None and options().alignment_file is None and not options().sequence_file is None:
self.generate_backbone()
else:
_LOG.error("Either specify the backbone alignment and tree and query sequences or only the query sequences. Any other combination is invalid")
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
backbone_size = sequences.get_num_taxa()
if options().backbone_size is None:
options().backbone_size = backbone_size
assert options().backbone_size == backbone_size, ("Backbone parameter needs to match actual size of backbone; backbone parameter:%s backbone_size:%s"
%(options().backbone_size, backbone_size))
if options().placement_size is None:
options().placement_size = options().backbone_size
return ExhaustiveAlgorithm.check_options(self)
def output_results(self):
extended_alignment = self.results
_LOG.info("Generating output. ")
outfilename = self.get_output_filename("alignment.fasta")
extended_alignment.write_to_path(outfilename)
_LOG.info("Unmasked alignment written to %s" % outfilename)
outfilename = self.get_output_filename("insertion_columns.txt")
extended_alignment.write_insertion_column_indexes(outfilename)
_LOG.info("The index of insertion columns written to %s" % outfilename)
if self.options.backtranslation_sequence_file:
outfilename = self.get_output_filename(
"backtranslated_alignment.fasta")
backtranslation_seqs = MutableAlignment()
backtranslation_seqs.read_file_object(
self.options.backtranslation_sequence_file)
try:
extended_backtranslated_alignment = backtranslate(
self.results, backtranslation_seqs)
except Exception as e:
_LOG.warning("Backtranslation failed due "
"to following error: " + str(e) + ".\n"
"No translated DNA sequence will be "
"written to a file.")
pass
else:
extended_backtranslated_alignment.write_to_path(outfilename)
_LOG.info("Backtranslated alignment written to %s" %
outfilename)
extended_backtranslated_alignment.remove_insertion_columns()
outfilename = self.get_output_filename(
"backtranslated_alignment_masked.fasta")
extended_backtranslated_alignment.write_to_path(outfilename)
_LOG.info("Backtranslated masked alignment written "
"to %s" % outfilename)
extended_alignment.remove_insertion_columns()
outfilename = self.get_output_filename("alignment_masked.fasta")
extended_alignment.write_to_path(outfilename)
_LOG.info("Masked alignment written to %s" % outfilename)
def testAlignmentReadFasta(self):
print("====== starting testAlignmentReadFasta ==========")
alg = MutableAlignment()
alg.read_filepath("data/mock/pyrg/sate.fasta")
print("Maing alignment is:\n\n", alg)
assert len(alg) == 65, "MutableAlignment length is %s" % len(alg)
assert all([not alg.is_all_gap(i) for i in range(0, alg.get_length())])
def read_and_divide_fragments(self, chunks, extra_frags={}):
_LOG.debug("start reading fragment files and breaking to chunks: %d" %
chunks)
self.root_problem.fragments = MutableAlignment()
self.root_problem.fragments.read_file_object(
self.options.fragment_file)
for (k, v) in extra_frags.iteritems():
self.root_problem.fragments[k] = v.replace("-", "")
alg_chunks = self.root_problem.fragments.divide_to_equal_chunks(chunks)
ret = []
for i in xrange(0, chunks):
temp_file = get_temp_file("fragment_chunk_%d" % i,
"fragment_chunks", ".fasta")
alg_chunks[i].write_to_path(temp_file)
ret.append(temp_file)
_LOG.debug("fragment files read and divided.")
return ret
def check_options(self):
options().info_file = "A_dummy_value"
#Check to see if tree/alignment/fragment file provided, if not, generate it
#from sequence file
if not options().tree_file is None and not options().alignment_file is None and not options().sequence_file is None:
options().fragment_file = options().sequence_file
elif options().tree_file is None and options().alignment_file is None and not options().sequence_file is None:
self.generate_backbone()
else:
_LOG.error("Either specify the backbone alignment and tree and query sequences or only the query sequences. Any other combination is invalid")
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
backbone_size = sequences.get_num_taxa()
if options().backbone_size is None:
options().backbone_size = backbone_size
assert options().backbone_size == backbone_size, ("Backbone parameter needs to match actual size of backbone; backbone parameter:%s backbone_size:%s"
%(options().backbone_size, backbone_size))
if options().placement_size is None:
options().placement_size = options().backbone_size
if options().alignment_size is None:
_LOG.info("Alignment subset size not given. Calculating subset size. ")
alignment = MutableAlignment()
alignment.read_file_object(open(self.options.alignment_file.name))
if (options().molecule == 'amino'):
_LOG.warning("Automated alignment subset selection not implemented for protein alignment. Setting to 10.")
options().alignment_size = 10
else:
(averagep,maxp) = alignment.get_p_distance()
align_size = 10
if (averagep > .60):
while (align_size*2 < alignment.get_num_taxa()):
align_size = align_size * 2
_LOG.info("Average p-distance of backbone is %f0.2. Alignment subset size set to %d. " % (averagep,align_size))
options().alignment_size = align_size
return ExhaustiveAlgorithm.check_options(self)
def testReadOnlySubAlignment(self):
print("======= starting testReadOnlySubAlignment =========")
alg = MutableAlignment()
alg.read_filepath("data/mock/pyrg/sate.fasta")
subset = list(alg.keys())[9:12]
readonly_subalignment = ReadonlySubalignment(subset, alg)
print("subalignment is:\n\n", readonly_subalignment)
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert set(readonly_subalignment.keys()) == set(
readonly_subalignment.get_sequence_names()) == set(
subset
), "Subalignment keys not matching given keys %s vs %s" % (list(
readonly_subalignment.keys()), subset)
for (k, s) in list(readonly_subalignment.items()):
assert k in subset, "%s not found in subset but returned by subalignment" % k
assert s == alg[
k], "sequence associated with %k not matching parent alignment" % k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(
), "alignment length should not change"
assert readonly_subalignment.is_aligned() == True
assert readonly_subalignment.is_all_gap(
2) == True, "Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(
150) == False, "Site 100 should not be all gaps"
readonly_subalignment.write_to_path("data/mock/pyrg/sate.sub.fasta")
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([
not mutable_subalignment.is_all_gap(i)
for i in range(0, mutable_subalignment.get_length())
])
print("======= finishing testReadOnlySubAlignment =========")
def generate_backbone(self):
_LOG.info("Reading input sequences: %s" % (self.options.sequence_file))
sequences = MutableAlignment()
sequences.read_file_object(self.options.sequence_file)
if (options().backbone_size is None):
options().backbone_size = min(100,
int(.20 * sequences.get_num_taxa()))
_LOG.info("Backbone size set to: %d" % (options().backbone_size))
backbone_sequences = sequences.get_hard_sub_alignment(
random.sample(sequences.keys(),
options().backbone_size))
[sequences.pop(i) for i in backbone_sequences.keys()]
_LOG.info("Writing query and backbone set. ")
query = get_temp_file("query", "backbone", ".fas")
backbone = get_temp_file("backbone", "backbone", ".fas")
_write_fasta(sequences, query)
_write_fasta(backbone_sequences, backbone)
_LOG.info("Generating sate backbone alignment and tree. ")
satealignJob = SateAlignJob()
moleculeType = options().molecule
if (options().molecule == 'amino'):
moleculeType = 'protein'
satealignJob.setup(backbone,
options().backbone_size, self.options.outdir,
moleculeType,
options().cpu)
satealignJob.run()
satealignJob.read_results()
options().placement_size = self.options.backbone_size
options().alignment_file = open(self.options.outdir + "/sate.fasta")
options().tree_file = open(self.options.outdir + "/sate.fasttree")
_LOG.info(
"Backbone alignment written to %s.\nBackbone tree written to %s" %
(options().alignment_file, options().tree_file))
options().fragment_file = query
def hmmer_to_markers(input, temp_dir):
global refpkg
fragments = MutableAlignment()
fragments.read_filepath(input)
reverse = dict([(name + '_rev', reverse_sequence(seq))
for (name, seq) in fragments.items()])
all_frags = MutableAlignment()
all_frags.set_alignment(fragments)
all_frags.set_alignment(reverse)
frag_file = temp_dir + "/frags.fas"
_write_fasta(all_frags, frag_file)
# Now bin the fragments
frag_scores = dict([(name, [-10000, 'NA', 'NA'])
for name in fragments.keys()])
for gene in refpkg["genes"]:
# Now run HMMER search
hmmer_output = temp_dir + '/' + gene + ".out"
hmmer_search(frag_file, refpkg[gene]["hmm"], hmmer_output)
results = read_hmmsearch_results(hmmer_output)
# Now select best direction for each frag
for name, value in results.items():
bitscore = value[1]
direction = 'forward'
true_name = name
if (name.find('_rev') != -1):
true_name = true_name.replace('_rev', '')
direction = 'reverse'
if frag_scores[true_name][0] < bitscore:
frag_scores[true_name] = [bitscore, gene, direction]
# Now bin the fragments
genes = dict([])
for name, val in frag_scores.items():
if (val[1] not in genes):
genes[val[1]] = {}
if (val[2] == 'forward'):
genes[val[1]][name] = fragments[name]
else:
genes[val[1]][name] = reverse_sequence(fragments[name])
genes.pop("NA", None)
for gene, seq in genes.items():
gene_file = temp_dir + '/' + gene + ".frags.fas.fixed"
_write_fasta(seq, gene_file)
binned_fragments = {}
for gene, seq in genes.items():
binned_fragments[gene] = {}
binned_fragments[gene]["file"] = temp_dir + '/' + gene \
+ ".frags.fas.fixed"
binned_fragments[gene]["nfrags"] = len(seq.keys())
return binned_fragments
def generate_backbone(self):
_LOG.info("Reading input sequences: %s" % (self.options.sequence_file))
sequences = MutableAlignment()
sequences.read_file_object(self.options.sequence_file)
sequences.degap()
fragments = MutableAlignment()
if (options().median_full_length is not None):
if (options().median_full_length == -1):
seq_lengths = sorted(
[len(seq) for seq in list(sequences.values())])
lengths = len(seq_lengths)
l2 = int(lengths / 2)
if lengths % 2:
options().median_full_length = (
seq_lengths[l2] + seq_lengths[l2 + 1]) / 2.0
else:
options().median_full_length = seq_lengths[l2]
(min_length, max_length) = (
int(options().median_full_length * (
1 - options().backbone_threshold)),
int(options().median_full_length*(
1 + options().backbone_threshold)))
frag_names = [
name for name in sequences
if len(sequences[name]) > max_length or
len(sequences[name]) < min_length]
if (len(frag_names) > 0):
_LOG.info(
"Detected %d fragmentary sequences" % len(frag_names))
fragments = sequences.get_hard_sub_alignment(frag_names)
[sequences.pop(i) for i in list(fragments.keys())]
if (options().backbone_size is None):
options().backbone_size = min(1000, int(sequences.get_num_taxa()))
_LOG.info("Backbone size set to: %d" % (options().backbone_size))
if (options().backbone_size > len(list(sequences.keys()))):
options().backbone_size = len(list(sequences.keys()))
sample = sorted(random.sample(
sorted(list(sequences.keys())), options().backbone_size))
backbone_sequences = sequences.get_hard_sub_alignment(sample)
_LOG.debug("Backbone: %s" % (sorted(list(backbone_sequences.keys()))))
[sequences.pop(i) for i in list(backbone_sequences.keys())]
_LOG.info("Writing backbone set. ")
backbone = get_temp_file("backbone", "backbone", ".fas")
_write_fasta(backbone_sequences, backbone)
_LOG.info("Generating pasta backbone alignment and tree. ")
pastaalignJob = PastaAlignJob()
moleculeType = options().molecule
if (options().molecule == 'amino'):
moleculeType = 'protein'
pastaalignJob.setup(backbone, options().backbone_size,
moleculeType, options().cpu)
pastaalignJob.run()
(a_file, t_file) = pastaalignJob.read_results()
shutil.copyfile(t_file, self.get_output_filename("pasta.fasttree"))
shutil.copyfile(a_file, self.get_output_filename("pasta.fasta"))
options().placement_size = self.options.backbone_size
options().alignment_file = open(
self.get_output_filename("pasta.fasta"))
options().tree_file = open(self.get_output_filename("pasta.fasttree"))
_LOG.info(
"Backbone alignment written to %s.\nBackbone tree written to %s"
% (options().alignment_file, options().tree_file))
sequences.set_alignment(fragments)
if (len(sequences) == 0):
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
self.results = ExtendedAlignment(fragment_names=[])
self.results.set_alignment(sequences)
_LOG.info(
"No query sequences to align. Final alignment saved as %s"
% self.get_output_filename("alignment.fasta"))
self.output_results()
sys.exit(0)
else:
query = get_temp_file("query", "backbone", ".fas")
options().fragment_file = query
_write_fasta(sequences, query)
def main():
args = parse_args()
sequences = MutableAlignment()
assert os.path.isfile(args.input) and os.access(
args.input, os.R_OK), "Input file %s does not exist\n" % args.input
sequences.read_file_object(args.input)
frag = MutableAlignment()
full = MutableAlignment()
for (key, seq) in sequences.items():
if (len(seq) <= args.threshold):
frag[key] = seq
else:
full[key] = seq
frag.write_to_path("%s.frag.fas" % args.output)
full.write_to_path("%s.full.fas" % args.output)
def check_options(self):
options().info_file = "A_dummy_value"
#Check to see if tree/alignment/fragment file provided, if not, generate it
#from sequence file
if not options().tree_file is None and not options(
).alignment_file is None and not options().sequence_file is None:
options().fragment_file = options().sequence_file
elif options().tree_file is None and options(
).alignment_file is None and not options().sequence_file is None:
self.generate_backbone()
else:
_LOG.error(
"Either specify the backbone alignment and tree and query sequences or only the query sequences. Any other combination is invalid"
)
exit(-1)
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
backbone_size = sequences.get_num_taxa()
if options().backbone_size is None:
options().backbone_size = backbone_size
assert options().backbone_size == backbone_size, (
"Backbone parameter needs to match actual size of backbone; backbone parameter:%s backbone_size:%s"
% (options().backbone_size, backbone_size))
if options().placement_size is None:
options().placement_size = options().backbone_size
if options().alignment_size is None:
_LOG.info(
"Alignment subset size not given. Calculating subset size. ")
alignment = MutableAlignment()
alignment.read_file_object(open(self.options.alignment_file.name))
if (options().molecule == 'amino'):
_LOG.warning(
"Automated alignment subset selection not implemented for protein alignment. Setting to 10."
)
options().alignment_size = 10
else:
(averagep, maxp) = alignment.get_p_distance()
align_size = 10
if (averagep > .60):
while (align_size * 2 < alignment.get_num_taxa()):
align_size = align_size * 2
_LOG.info(
"Average p-distance of backbone is %f0.2. Alignment subset size set to %d. "
% (averagep, align_size))
options().alignment_size = align_size
return ExhaustiveAlgorithm.check_options(self)
# Make sure to do this before the last line relabeling columns, since that's usually the line that errors.
# backbone alignment
original_backbone_file = (
'/Users/gillianchu/warnow/bin/gitrepos/smirarab-sepp-17a33aa/trial/orig_backbone.txt'
)
new_backbone_file = "new_backbone_file.txt"
with open(original_backbone_file, "r") as reader:
with open(new_backbone_file, "w+") as writer:
for line in reader.readlines():
if line[0] == ">":
writer.write(line.upper())
else:
writer.write(line)
original_backbone = MutableAlignment()
done = original_backbone.read_filepath(new_backbone_file)
# all query sequences
original_frag_file = (
'/Users/gillianchu/warnow/bin/gitrepos/smirarab-sepp-17a33aa/trial/all_query.txt'
)
original_frag = MutableAlignment()
done = original_frag.read_filepath(original_frag_file)
# First build extended alignment on entire fragment set
extendedAlignment = ExtendedAlignment(original_frag.get_sequence_names())
dir = '/Users/gillianchu/warnow/bin/gitrepos/smirarab-sepp-17a33aa/trial/'
for a in [1, 2]:
a = str(a)
def blast_to_markers(input, temp_dir):
fragments = MutableAlignment()
fragments.read_filepath(input)
if (options().gene is None):
# First blast sequences against all markers
blast_results = temp_dir + "/blast.out"
if (options().blast_file is None):
print("Blasting fragments against marker dataset\n")
blast_fragments(input, blast_results)
else:
blast_results = options().blast_file
# Next bin the blast hits to the best gene
gene_binning = bin_blast_results(blast_results)
else:
gene_binning = {options().gene: list(fragments.keys())}
# Now figure out direction of fragments
binned_fragments = dict([(gene,
dict([(seq_name, fragments[seq_name])
for seq_name in gene_binning[gene]]))
for gene in gene_binning])
print("Finding best orientation of reads\n")
align_name = 'sate'
if (options().genes == 'cogs'):
align_name = 'pasta'
for (gene, frags) in binned_fragments.items():
# Add reverse complement sequence
frags_rev = dict([(name + '_rev', reverse_sequence(seq))
for (name, seq) in frags.items()])
gene_frags = MutableAlignment()
gene_frags.set_alignment(frags)
gene_frags.set_alignment(frags_rev)
gene_file = temp_dir + "/%s.frags.fas" % gene
_write_fasta(gene_frags, gene_file)
# Now run HMMER search
hmmer_search(
gene_file,
os.path.join(options().__getattribute__('reference').path,
'refpkg/%s.refpkg/%s.hmm' % (gene, align_name)),
temp_dir + "/%s.out" % gene)
results = read_hmmsearch_results(temp_dir + "/%s.out" % gene)
# Now select best direction for each frag
for key in frags:
forward_score = -10000
backward_score = -10000
if (key in results):
forward_score = results[key][1]
if (key + "_rev" in results):
backward_score = results[key + "_rev"][1]
if (backward_score > forward_score):
frags[key] = gene_frags[key + "_rev"]
# Now write to file
_write_fasta(frags, gene_file + ".fixed")
binned_fragments[gene] = frags
return binned_fragments
def hmmer_to_markers(input, temp_dir):
global marker_genes
fragments = MutableAlignment()
fragments.read_filepath(input)
reverse = dict([(name + '_rev', reverse_sequence(seq))
for (name, seq) in fragments.items()])
all_frags = MutableAlignment()
all_frags.set_alignment(fragments)
all_frags.set_alignment(reverse)
frag_file = temp_dir + "/frags.fas"
_write_fasta(all_frags, frag_file)
# Now bin the fragments
frag_scores = dict([(name, [-10000, 'NA', 'NA'])
for name in fragments.keys()])
gene_set = marker_genes
align_name = 'sate'
if (options().genes == 'cogs'):
gene_set = cog_genes
align_name = 'pasta'
for gene in gene_set:
# Now run HMMER search
hmmer_search(
frag_file,
os.path.join(options().__getattribute__('reference').path,
'refpkg/%s.refpkg/%.profile' % (gene, align_name)),
temp_dir + "/%s.out" % gene)
results = read_hmmsearch_results(temp_dir + "/%s.out" % gene)
# Now select best direction for each frag
for name, value in results.items():
bitscore = value[1]
direction = 'forward'
true_name = name
if (name.find('_rev') != -1):
true_name = true_name.replace('_rev', '')
direction = 'reverse'
if frag_scores[true_name][0] < bitscore:
frag_scores[true_name] = [bitscore, gene, direction]
# Now bin the fragments
genes = dict([])
for name, val in frag_scores.items():
if (val[1] not in genes):
genes[val[1]] = {}
if (val[2] == 'forward'):
genes[val[1]][name] = fragments[name]
else:
genes[val[1]][name] = reverse_sequence(fragments[name])
genes.pop("NA", None)
for gene, seq in genes.items():
gene_file = temp_dir + "/%s.frags.fas" % gene
_write_fasta(seq, gene_file + ".fixed")
return genes
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 ========="
from sepp.alignment import MutableAlignment, ExtendedAlignment,_write_fasta
from sepp.exhaustive import JoinAlignJobs, ExhaustiveAlgorithm
from sepp.jobs import PplacerJob,MafftAlignJob,FastTreeJob,PastaAlignJob
from sepp.filemgr import get_temp_file
from sepp.config import options
import sepp.config
from sepp.math_utils import lcm
from sepp.problem import SeppProblem
from sepp.scheduler import JobPool
from multiprocessing import Pool, Manager
from sepp.alignment import ExtendedAlignment
import glob
job_joiner = JoinAlignJobs
original_backbone_file = '/projects/sate8/namphuon/ultra_large/1000000/sate.fasta'
original_backbone = MutableAlignment()
done = original_backbone.read_filepath(original_backbone_file)
original_frag_file = '/projects/sate8/namphuon/ultra_large/1000000/initial.fas.100'
original_frag = MutableAlignment()
done = original_frag.read_filepath(original_frag_file)
#First build extended alignment on entire fragment set
extendedAlignment = ExtendedAlignment(original_frag.get_sequence_names())
dirs = glob.glob('/projects/sate8/namphuon/ultra_large/1000000/upp_100_10_new/temp/upp.1_HNlM/root/P_0/A_0_*/')
dirs.reverse()
for dir in dirs:
print "Working on %s\n" % dir
aligned_files = glob.glob('%sFC_*/hmmalign.results.*' % dir)
def generate_backbone(self):
_LOG.info("Reading input sequences: %s" %(self.options.sequence_file))
sequences = MutableAlignment()
sequences.read_file_object(self.options.sequence_file)
fragments = MutableAlignment()
if (options().median_full_length is not None):
if (options().median_full_length == -1):
seq_lengths = sorted([len(seq) for seq in sequences.values()])
lengths = len(seq_lengths)
if lengths % 2:
options().median_full_length = (seq_lengths[lengths / 2] + seq_lengths[lengths / 2 - 1]) / 2.0
else:
options().median_full_length = seq_lengths[lengths / 2]
(min_length,max_length) = (int(options().median_full_length*(1-options().backbone_threshold)),int(options().median_full_length*(1+options().backbone_threshold)))
frag_names = [name for name in sequences if len(sequences[name]) > max_length or len(sequences[name]) < min_length]
if (len(frag_names) > 0):
fragments = sequences.get_hard_sub_alignment(frag_names)
[sequences.pop(i) for i in fragments.keys()]
if (options().backbone_size is None):
options().backbone_size = min(1000,int(sequences.get_num_taxa()))
_LOG.info("Backbone size set to: %d" %(options().backbone_size))
if (options().backbone_size > len(sequences.keys())):
options().backbone_size = len(sequences.keys())
backbone_sequences = sequences.get_hard_sub_alignment(random.sample(sequences.keys(), options().backbone_size))
[sequences.pop(i) for i in backbone_sequences.keys()]
_LOG.info("Writing backbone set. ")
backbone = get_temp_file("backbone", "backbone", ".fas")
_write_fasta(backbone_sequences, backbone)
_LOG.info("Generating pasta backbone alignment and tree. ")
pastaalignJob = PastaAlignJob()
moleculeType = options().molecule
if (options().molecule == 'amino'):
moleculeType = 'protein'
pastaalignJob.setup(backbone,options().backbone_size,self.options.outdir,moleculeType,options().cpu)
pastaalignJob.run()
pastaalignJob.read_results()
options().placement_size = self.options.backbone_size
options().alignment_file = open(self.options.outdir + "/pasta.fasta")
options().tree_file = open(self.options.outdir + "/pasta.fasttree")
_LOG.info("Backbone alignment written to %s.\nBackbone tree written to %s" % (options().alignment_file, options().tree_file))
sequences.set_alignment(fragments)
if (len(sequences) == 0):
_LOG.info("No query sequences to align. Final alignment saved as %s" % self.get_output_filename("alignment.fasta"))
shutil.copyfile(self.options.outdir + "/pasta.fasta", self.get_output_filename("alignment.fasta"))
sys.exit(0)
else:
query = get_temp_file("query", "backbone", ".fas")
options().fragment_file = query
_write_fasta(sequences, query)
def generate_backbone(self):
_LOG.info("Reading input sequences: %s" % (self.options.sequence_file))
sequences = MutableAlignment()
sequences.read_file_object(self.options.sequence_file)
sequences.degap()
fragments = MutableAlignment()
if (options().median_full_length is not None
or options().full_length_range is not None):
if (options().median_full_length == -1):
seq_lengths = sorted(
[len(seq) for seq in list(sequences.values())])
lengths = len(seq_lengths)
l2 = int(lengths / 2)
if lengths % 2:
options().median_full_length = (seq_lengths[l2] +
seq_lengths[l2 + 1]) / 2.0
else:
options().median_full_length = seq_lengths[l2]
if options().full_length_range is not None:
L = sorted(int(x) for x in options().full_length_range.split())
min_length = L[0]
max_length = L[1]
else:
(min_length,
max_length) = (int(options().median_full_length *
(1 - options().backbone_threshold)),
int(options().median_full_length *
(1 + options().backbone_threshold)))
_LOG.info(
"Full length sequences are set to be from %d to %d character long"
% (min_length, max_length))
frag_names = [
name for name in sequences if len(sequences[name]) > max_length
or len(sequences[name]) < min_length
]
if (len(frag_names) > 0):
_LOG.info("Detected %d fragmentary sequences" %
len(frag_names))
fragments = sequences.get_hard_sub_alignment(frag_names)
[sequences.pop(i) for i in list(fragments.keys())]
if (options().backbone_size is None):
options().backbone_size = min(1000, int(sequences.get_num_taxa()))
_LOG.info("Backbone size set to: %d" % (options().backbone_size))
if (options().backbone_size > len(list(sequences.keys()))):
options().backbone_size = len(list(sequences.keys()))
sample = sorted(
random.sample(sorted(list(sequences.keys())),
options().backbone_size))
backbone_sequences = sequences.get_hard_sub_alignment(sample)
_LOG.debug("Backbone: %s" % (sorted(list(backbone_sequences.keys()))))
[sequences.pop(i) for i in list(backbone_sequences.keys())]
_LOG.info("Writing backbone set. ")
backbone = get_temp_file("backbone", "backbone", ".fas")
_write_fasta(backbone_sequences, backbone)
_LOG.info("Generating pasta backbone alignment and tree. ")
pastaalignJob = PastaAlignJob()
moleculeType = options().molecule
if (options().molecule == 'amino'):
moleculeType = 'protein'
pastaalignJob.setup(backbone,
options().backbone_size, moleculeType,
options().cpu, **vars(options().pasta))
pastaalignJob.run()
(a_file, t_file) = pastaalignJob.read_results()
shutil.copyfile(t_file, self.get_output_filename("pasta.fasttree"))
shutil.copyfile(a_file, self.get_output_filename("pasta.fasta"))
options().placement_size = self.options.backbone_size
options().alignment_file = open(
self.get_output_filename("pasta.fasta"))
options().tree_file = open(self.get_output_filename("pasta.fasttree"))
_LOG.info(
"Backbone alignment written to %s.\nBackbone tree written to %s" %
(options().alignment_file, options().tree_file))
sequences.set_alignment(fragments)
if (len(sequences) == 0):
sequences = MutableAlignment()
sequences.read_file_object(open(self.options.alignment_file.name))
self.results = ExtendedAlignment(fragment_names=[])
self.results.set_alignment(sequences)
_LOG.info(
"No query sequences to align. Final alignment saved as %s" %
self.get_output_filename("alignment.fasta"))
self.output_results()
sys.exit(0)
else:
query = get_temp_file("query", "backbone", ".fas")
options().fragment_file = query
_write_fasta(sequences, query)
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 ========="