def gather_and_stitch(seq, tfile):
total_data = []
in_file = str(seq) + "_tophits.gzip"
if os.path.isfile(in_file):
print "Extracting data from non_refined file:", in_file
tasks = io.readGzipPickle(in_file)
for entry in tasks:
total_data.append(entry)
else:
print "Something is wrong in the datafile: ", in_file
refined_data = combine_data()
if refined_data:
for entry in refined_data:
total_data.append(entry)
else:
pass
from ranking.NoeStageRank import rank_assembly_with_clustering
ranked_data = rank_assembly_with_clustering(total_data, args.numhits)
io.dumpGzipPickle(str(tfile), ranked_data)
# delete files
try:
print "Deleting old rtx_* files!"
rm_files = "rm rtx_*.gzip"
os.system(rm_files)
except NameError:
print "No rtx_* files exist!"
return True
def combine_data():
hits = []
file_list = glob.glob("rtx_*.gzip")
if file_list:
pass
else:
return False
for f in file_list:
print "Extracting data from file..", f
t_hits = io.readGzipPickle(f)
for t_hit in t_hits:
hits.append(t_hit)
return hits
def makeTopPickle2Old(previous_smotif_index, num_hits, stage):
"""
Concatenate data from all of the threads, organize, remove redundancies, rank
and extract top hits as defined
:param previous_smotif_index:
:param num_hits:
:param stage:
:return:
"""
hits = []
# regex = str(previous_smotif_index) + "_*_*.pickle"
regex = str(previous_smotif_index) + "_*_*.gzip"
file_list = glob.glob(regex)
for f in file_list:
t_hits = io.readGzipPickle(f)
for t_hit in t_hits:
hits.append(t_hit)
"""
identifiers: smotif, smotif_def, seq_filter, contacts_filter, PCS_filter, qcp_rmsd, Evofilter
RDC_filter, NOE_filter
"""
new_dict = collections.defaultdict(list)
for hit in hits:
# thread_data contains data from each search and filter thread.
if hit[4][0] == 'NOE_filter':
no_of_noes = hit[4][2]
new_dict[no_of_noes].append(hit)
keys = new_dict.keys()
keys.sort()
keys.reverse()
# Rank based on NOE energy
non_redundant = collections.defaultdict(list)
reduced_dump_log = []
seqs = []
count_hits = 0
for i in range(len(keys)):
entries = new_dict[keys[i]]
if len(
entries
) == 1: # There is only one entry in this no_of_noes bin just check of existing sequences and move on
smotif_seq = entries[0][3][1]
if smotif_seq not in seqs:
seqs.append(smotif_seq)
reduced_dump_log.append(entries[0])
print "final sele", entries[0][0][1][0][0], keys[i]
count_hits += 1
else:
t_log = collections.defaultdict(list)
for hit in entries: # filter on noe_energy
if hit[4][0] == 'NOE_filter':
noe_energy = hit[4][3]
noe_energy = round(noe_energy, 2)
t_log[noe_energy].append(hit)
noe_energy_bins = t_log.keys()
noe_energy_bins.sort()
for j in range(len(noe_energy_bins)): # filter on RDC score
t2_log = collections.defaultdict(list)
hits = t_log[noe_energy_bins[j]]
for hit in hits:
if hit[5][0] == 'RDC_filter':
rdc_tensors = hit[5][1]
rdc_score = 0
for tensor in rdc_tensors:
rdc_score = rdc_score + tensor[0]
t2_log[rdc_score].append(hit)
rdc_score_bins = t2_log.keys()
rdc_score_bins.sort()
for k in range(len(rdc_score_bins)):
hits = t2_log[rdc_score_bins[k]]
for hit in hits:
smotif_seq = hit[3][1]
if smotif_seq not in seqs:
seqs.append(smotif_seq)
reduced_dump_log.append(hit)
print "final sele", hit[0][1][0][0], keys[
i], noe_energy_bins[j], rdc_score_bins[k]
count_hits += 1
if count_hits >= num_hits:
break
if count_hits >= num_hits:
break
if count_hits >= num_hits:
pass
else:
print "could only extract ", len(reduced_dump_log), count_hits
# io.dumpPickle(str(previous_smotif_index) + "_tophits.pickle", dump_pickle)
io.dumpGzipPickle(
str(previous_smotif_index) + "_tophits.gzip", reduced_dump_log)
print "actual number in top hits ", len(reduced_dump_log)
return range(len(reduced_dump_log))
def makeTopPickle2(previous_smotif_index, num_hits, stage):
"""
Concatenate data from all of the threads, organize, remove redundancies, rank
and extract top hits as defined
:param previous_smotif_index:
:param num_hits:
:param stage:
:return:
"""
hits = []
# regex = str(previous_smotif_index) + "_*_*.pickle"
regex = str(previous_smotif_index) + "_*_*.gzip"
file_list = glob.glob(regex)
for f in file_list:
t_hits = io.readGzipPickle(f)
for t_hit in t_hits:
hits.append(t_hit)
"""
identifiers: smotif, smotif_def, seq_filter, contacts_filter, PCS_filter, qcp_rmsd, Evofilter
RDC_filter, NOE_filter
"""
new_dict = collections.defaultdict(list)
for hit in hits:
# thread_data contains data from each search and filter thread.
noe_energy = hit[5][3]
noe_energy = round(noe_energy, 4)
new_dict[noe_energy].append(hit)
keys = new_dict.keys()
keys.sort()
# Rank based on NOE energy
reduced_dump_log = []
seqs = []
count_hits = 0
for i in range(len(keys)):
entries = new_dict[keys[i]]
if count_hits >= num_hits:
break
if len(entries) == 1:
smotif_seq = entries[0][4][1]
if smotif_seq not in seqs:
seqs.append(smotif_seq)
reduced_dump_log.append(entries[0])
print "final sele", entries[0][0][1][0][0], keys[i]
count_hits += 1
if count_hits >= num_hits:
break
else:
t2_log = collections.defaultdict(list)
if hit[6][0] == 'RDC_filter':
for hit in entries:
# if hit[5][0] == 'RDC_filter':
rdc_tensors = hit[6][1]
rdc_score = 0
for tensor in rdc_tensors:
rdc_score = rdc_score + tensor[0]
t2_log[rdc_score].append(hit)
rdc_score_bins = t2_log.keys()
rdc_score_bins.sort()
elif hit[6][0] == 'PCS_filter':
print "Working on PCS filter instead of RDC"
for hit in entries:
# if hit[5][0] == 'RDC_filter':
rdc_tensors = hit[6][1]
rdc_score = 0
for tensor in rdc_tensors:
rdc_score = rdc_score + tensor[1]
t2_log[rdc_score].append(hit)
rdc_score_bins = t2_log.keys()
rdc_score_bins.sort()
else:
print "Something is wrong with your PCS logic"
for k in range(len(rdc_score_bins)):
hits = t2_log[rdc_score_bins[k]]
for hit in hits:
smotif_seq = hit[4][1]
if smotif_seq not in seqs:
seqs.append(smotif_seq)
reduced_dump_log.append(hit)
count_hits += 1
print "final sele", hit[0][1][0][0], keys[
i], rdc_score_bins[k]
if count_hits >= num_hits:
break
if count_hits >= num_hits:
break
if count_hits >= num_hits:
break
else:
pass
if count_hits >= num_hits:
pass
else:
print "could only extract ", len(reduced_dump_log), count_hits
io.dumpGzipPickle(
str(previous_smotif_index) + "_tophits.gzip", reduced_dump_log)
print "actual number in top hits ", len(reduced_dump_log)
return range(len(reduced_dump_log))
def makeTopPickle(previous_smotif_index, num_hits, stage):
"""
Concatenate data from all of the threads, organize, remove redundancies, rank
and extract top hits as defined
:param previous_smotif_index:
:param num_hits:
:param stage:
:return:
"""
hits = []
# regex = str(previous_smotif_index) + "_*_*.pickle"
regex = str(previous_smotif_index) + "_*_*.gzip"
file_list = glob.glob(regex)
for f in file_list:
t_hits = io.readGzipPickle(f)
for t_hit in t_hits:
hits.append(t_hit)
"""
identifiers: smotif, smotif_def, seq_filter, contacts_filter, PCS_filter, qcp_rmsd, Evofilter
RDC_filter, NOE_filter
"""
new_dict = collections.defaultdict(list)
rdc_constant = 0.0
for hit in hits:
# thread_data contains data from each search and filter thread.
# initialize total score array
total_score = {}
for data_filter in hit:
if data_filter[0] == 'PCS_filter':
pcs_data = data_filter
pcsscore = getNchiSum(pcs_data, stage)
total_score['pcs_score'] = pcsscore
if data_filter[0] == 'Ref_RMSD':
total_score['rmsd_score'] = data_filter[1]
if data_filter[0] == 'RDC_filter':
rdc_data = data_filter
#Nchi = rdcSumChi(rdc_data, stage)
log_likelihood = data_filter[2]
rdc_tensors = data_filter[1]
for tensor in rdc_tensors:
rdc_constant = rdc_constant + tensor[0]
rdc_constant = rdc_constant * 1e-10
total_score['rdc_score'] = log_likelihood
if data_filter[0] == 'NOE_filter':
noe_probability = data_filter[1]
log_likelihood = -1 * (math.log(noe_probability))
total_score['noe_score'] = log_likelihood
# calculate the total score and append the hit
if total_score:
keys = total_score.keys()
keys = ['noe_score', 'rdc_score']
#keys = ['rmsd_score']
tscore = 0
for key in keys:
tscore = tscore + total_score[key]
tscore = tscore + rdc_constant
if tscore < 999.999:
new_dict[tscore].append(hit)
# ************************************************
# Exclude the redundant entries and rank top hits
# ************************************************
keys = new_dict.keys()
keys.sort()
# Exclude the redundant data.
# non_redundant = {}
non_redundant = collections.defaultdict(list)
seqs = []
smotif_seq = ''
count_hits = 0
for i in range(0, len(keys)):
entries = new_dict[keys[i]]
for entry in entries:
for ent in entry:
if ent[0] == 'seq_filter':
seq_filter = ent
smotif_seq = seq_filter[1]
if smotif_seq not in seqs:
seqs.append(smotif_seq)
non_redundant[keys[i]].append(entry)
count_hits += 1
if count_hits >= num_hits:
break
# Rank top hits and dump the data
keys = non_redundant.keys()
keys.sort()
dump_pickle = []
print "Dumping data to disk"
count_top_hits = 0
while (True):
for key in keys:
entries = non_redundant[key]
for entry in entries:
dump_pickle.append(entry)
# print "final selected Smotif: ", entry[0][1][0][0], "with score: ", key
print "final sele", entry[0][1][0][0], key
count_top_hits += 1
if count_top_hits >= num_hits:
break
if count_top_hits >= num_hits:
break
else:
print "could only extract ", count_top_hits
break
# io.dumpPickle(str(previous_smotif_index) + "_tophits.pickle", dump_pickle)
io.dumpGzipPickle(
str(previous_smotif_index) + "_tophits.gzip", dump_pickle)
print "actual number in top hits ", len(dump_pickle)
return range(count_top_hits)
import sys, os, copy
sys.path.append('../../main/')
__author__ = 'kalabharath'
import utility.io_util as io
seq = int(sys.argv[1])
top_result = []
t_file = str(seq) + "_refined_tophits.gzip"
if os.path.isfile(t_file):
top_result = io.readGzipPickle(t_file)
else:
t_file = str(seq) + "_tophits.gzip"
if os.path.isfile(t_file):
top_result = io.readGzipPickle(t_file)
else:
print "Somethis is terrribly wrong !"
exit()
for p in range(0, len(top_result)):
print 'model_', p,
top_struct = top_result[p]
top_struct = copy.copy(top_struct)
for entry in top_struct:
if entry[0] == 'cathcodes':
help='Top number of hits to be selected')
args = parser.parse_args()
# ********************* Define cmd line argument parser *********************
# Rank '0' specifies the master process
if rank == 0:
# ********************* Extract top hits *********************
in_file = str(args.infile) + "_tophits.gzip"
print "infile ", in_file
try:
tasks = io.readGzipPickle(in_file)
print "len of tasks", len(tasks)
except:
traceback.print_exc()
print "There are no entries in the tophits file, nothing to refine"
killall(size)
exit()
# ********************* Generate and distribute job index array *********************
stime = time.time()
try:
if len(tasks):
pass
except:
