def main():
parser = OptionParser(
usage='%prog [options] alignment_path family_accession')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error('Must supply alignment_path and family_accession')
if not os.path.exists(args[0]):
parser.error('Alignment_path %s not found' % args[0])
alignment_path = args[0]
accession_re = re.compile('bpg\d\d\d\d\d\d\d')
m = accession_re.match(args[1])
if not m or len(m.group(0)) != len(args[1]):
parser.error('%s is not a valid BPG family accession' % args[1])
family_accession = args[1]
if insertMLTree(alignment_path, family_accession):
print "Success: ML tree was inserted."
else:
print "Error: ML tree was NOT inserted!"
def main():
# parse command line options
usage = "%prog [options] bpg_accession"
opt_parser = OptionParser(usage=usage)
(options, args) = opt_parser.parse_args()
if len(args) != 1:
opt_parser.error('Incorrect number of arguments')
if len(args[0]) != 10 or args[0][0:3] != 'bpg':
opt_parser.error('Argument must be a bpg accession like bpg0164198')
bpg_accession = args[0]
try:
family_id = int(bpg_accession[3:])
except ValueError:
opt_parser.error('Argument must be a bpg accession like bpg0164198')
family_dir = '/clusterfs/ohana/bpg/pfacts/%s/%s/%s' % (
bpg_accession[0:4], bpg_accession[0:7], bpg_accession)
if not os.path.exists(family_dir):
opt_parser.error('Family %s not found on the filesystem.' %
bpg_accession)
print "Polishing family %s in %s" % (bpg_accession, family_dir)
os.chdir(family_dir)
overall_starttime = time.time()
if not os.path.exists(bpg_accession + '.alignmentconservation.csv'):
starttime = time.time()
print 'computing alignment conservation and inserting...',
sys.stdout.flush()
errf = open('compute_alignment_conservation.err', 'w')
p = subprocess.Popen(
['compute_alignment_conservation.py', bpg_accession], stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
f = open(bpg_accession + '.hmm')
line = f.readline().strip()
f.close()
if line != 'HMMER3/b [3.0 | March 2010]':
starttime = time.time()
print "Old HMMER3 version line: ", line
print 'Rebuilding the HMM using the production version of HMMER3...',
sys.stdout.flush()
stockholm_fname = glob.glob('*.stockholm')[0]
outf = open('hmmer3build.out', 'w')
errf = open('hmmer3build.err', 'w')
cmd = 'hmm3build -n %s --hand %s.hmm %s' \
% (bpg_accession, bpg_accession, stockholm_fname)
p = subprocess.Popen(shlex.split(cmd), stdout=outf, stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
fasttrees = glob.glob('*fasttree*')
if len(fasttrees) == 0:
print 'No FastTree ML tree found. Will create.'
starttime = time.time()
print 'Reformatting alignment...',
sys.stdout.flush()
errf = open('align_nj_to_align_ml.err', 'w')
p = subprocess.Popen('align_nj_to_align_ml.py', stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Running FastTree...',
sys.stdout.flush()
unrooted_tree_name = 'final_trimmed_mafft_ungapped.fasttree.ml.tre'
outf = open(unrooted_tree_name, 'w')
errf = open('final_trimmed_mafft_ungapped.fasttree.log', 'w')
p = subprocess.Popen(
['FastTree', '-gamma', 'final_trimmed_mafft_ungapped.aln.ml'],
stdout=outf,
stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Rerooting tree at midpoint of the longest span...',
sys.stdout.flush()
outf = open('final_trimmed_mafft_ungapped.fasttree.ml.rooted.tre', 'w')
errf = open('midpoint_reroot.err', 'w')
cmd = 'export PYTHONPATH=/clusterfs/ohana/software/lib/python2.6; ' \
+ 'midpoint_reroot.py %s ' % unrooted_tree_name
p = subprocess.Popen(cmd, shell=True, stdout=outf, stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Inserting ML tree...',
sys.stdout.flush()
status = insertMLTree('final_trimmed_mafft_ungapped.afa',
bpg_accession)
if not status:
sys.stderr.write("Error: ML tree was NOT inserted!\n")
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Running find_orthologs...',
sys.stdout.flush()
outf = open('%s.find_orthologs.ml.out' % bpg_accession, 'w')
errf = open('%s.find_orthologs.ml.err' % bpg_accession, 'w')
cmd = 'find_orthologs --book %s --method ml' % bpg_accession
p = subprocess.Popen(shlex.split(cmd), stdout=outf, stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Running find_thresholded_phogs_django.py...',
sys.stdout.flush()
outf = open('%s.find_thresholded_phogs.ml.out' % bpg_accession, 'w')
errf = open('%s.find_thresholded_phogs.ml.err' % bpg_accession, 'w')
cmd = 'find_thresholded_phogs_django.py -m ml %s' % bpg_accession
p = subprocess.Popen(shlex.split(cmd), stdout=outf, stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
overall_endtime = time.time()
print "Done polishing family %s. Overall: %s" \
% (bpg_accession, getTimeStr(overall_starttime, overall_endtime))
p = subprocess.Popen(['touch', 'polish_family_done'])
status = os.waitpid(p.pid, 0)[1]
def main():
# parse command line options
usage = "%prog [options] bpg_accession"
opt_parser = OptionParser(usage=usage)
(options, args) = opt_parser.parse_args()
if len(args) != 1:
opt_parser.error('Incorrect number of arguments')
if len(args[0]) != 10 or args[0][0:3] != 'bpg':
opt_parser.error('Argument must be a bpg accession like bpg0164198')
bpg_accession = args[0]
try:
family_id = int(bpg_accession[3:])
except ValueError:
opt_parser.error('Argument must be a bpg accession like bpg0164198')
family_dir = '/clusterfs/ohana/bpg/pfacts/%s/%s/%s' % (
bpg_accession[0:4], bpg_accession[0:7], bpg_accession)
if not os.path.exists(family_dir):
opt_parser.error('Family %s not found on the filesystem.' %
bpg_accession)
print "Polishing family %s in %s" % (bpg_accession, family_dir)
os.chdir(family_dir)
overall_starttime = time.time()
unaligned_seqs_file = '%s.seqs.fa' % bpg_accession
blastable_database_index = '%s.pin' % unaligned_seqs_file
if not os.path.exists(blastable_database_index):
print 'No BLASTable database found. Will create.'
starttime = time.time()
print 'Creating file of unaligned sequences from %s.' % bpg_accession
sys.stdout.flush()
p = subprocess.Popen([
'alignedfasta_to_unalignedfasta.py',
'%s.a2m' % bpg_accession,
'%s.seqs.fa' % bpg_accession
],
stderr=subprocess.PIPE)
status = os.waitpid(p.pid, 0)[1]
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Creating BLASTable database of sequences from %s.' % bpg_accession
sys.stdout.flush()
p = subprocess.Popen([
'formatdb', '-o', 'T', '-l', 'formatdb.log', '-i',
'%s.seqs.fa' % bpg_accession
],
stderr=subprocess.PIPE)
status = os.waitpid(p.pid, 0)[1]
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
fasttrees = glob.glob('*fasttree*')
if len(fasttrees) == 0:
print 'No FastTree ML tree found. Will create.'
starttime = time.time()
print 'Reformatting alignment...',
sys.stdout.flush()
errf = open('align_nj_to_align_ml.err', 'w')
p = subprocess.Popen('align_nj_to_align_ml.py', stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Running FastTree...',
sys.stdout.flush()
unrooted_tree_name = 'final_trimmed_mafft_ungapped.fasttree.ml.tre'
outf = open(unrooted_tree_name, 'w')
errf = open('final_trimmed_mafft_ungapped.fasttree.log', 'w')
p = subprocess.Popen(
['FastTree', '-gamma', 'final_trimmed_mafft_ungapped.aln.ml'],
stdout=outf,
stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Rerooting tree at midpoint of the longest span...',
sys.stdout.flush()
outf = open('final_trimmed_mafft_ungapped.fasttree.ml.rooted.tre', 'w')
errf = open('midpoint_reroot.err', 'w')
cmd = 'export PYTHONPATH=/clusterfs/ohana/software/lib/python2.6; ' \
+ 'midpoint_reroot.py %s ' % unrooted_tree_name
p = subprocess.Popen(cmd, shell=True, stdout=outf, stderr=errf)
status = os.waitpid(p.pid, 0)[1]
errf.close()
outf.close()
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
tree_objects = Tree.objects.filter(family__id=family_id, method='ml')
if not tree_objects:
starttime = time.time()
print 'Inserting ML tree...',
sys.stdout.flush()
status = insertMLTree('final_trimmed_mafft_ungapped.afa',
bpg_accession)
if not status:
sys.stderr.write("Error: ML tree was NOT inserted!\n")
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
if not os.path.exists('ml_tree_ordered.a2m'):
print 'Tree-ordered alignment file not found, creating.'
family = Family.objects.get(id=family_id)
aligned_seq_of_seq_header = {}
tree_node_alignment_objects = TreeNodeAlignment.objects.filter(
tree_node=family.canonical_root_node())
starttime = time.time()
print 'Reading alignment from database...',
sys.stdout.flush()
for object in tree_node_alignment_objects:
aligned_seq_of_seq_header[object.sequence_header] \
= object.aligned_sequence
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
tree = Tree.objects.get(family__id=family_id, method='ml')
starttime = time.time()
print 'Reading order from database...',
sys.stdout.flush()
leaves = TreeNode.objects.filter(
tree=tree, sequence_header__isnull=False).order_by('left_id')
endtime = time.time()
print 'done. %s' % getTimeStr(starttime, endtime)
starttime = time.time()
print 'Writing reordered alignment...',
sys.stdout.flush()
f = open('ml_tree_ordered.a2m', 'w')
for leaf in leaves:
f.write('>%s\n' % leaf.sequence_header.header)
f.write('%s\n' %
aligned_seq_of_seq_header[leaf.sequence_header].chars)
f.close()
cmd = 'rm %s.a2m; ln -s ml_tree_ordered.a2m %s.a2m' % (bpg_accession,
bpg_accession)
p = subprocess.Popen(cmd, shell=True)
status = os.waitpid(p.pid, 0)[1]
starttime = time.time()
print 'done...',
sys.stdout.flush()
overall_endtime = time.time()
print "Done polishing family %s. Overall: %s" \
% (bpg_accession, getTimeStr(overall_starttime, overall_endtime))
p = subprocess.Popen(['touch', 'polish_family_20101223_done'])
status = os.waitpid(p.pid, 0)[1]