def illumina_chimera_after_cluster(runobj):
mychimera = Chimera(runobj)
mychimera.illumina_rm_size_files()
start = time.time()
mychimera.illumina_size_to_freq_in_chimer()
elapsed = (time.time() - start)
logger.debug("illumina_size_to_freq_in_chimer time: %s" % elapsed)
# start = time.time()
# logger.debug("Check chimeric statistics. If ref > 15% and ratio ref to de-novo > 2 use only de-novo")
# mychimera.check_chimeric_stats()
# elapsed = (time.time() - start)
# logger.debug("check_chimeric_stats time: %s" % elapsed)
start = time.time()
logger.debug("Creating nonchimeric files in %s" % mychimera.indir)
mychimera.move_out_chimeric()
elapsed = (time.time() - start)
logger.debug("move_out_chimeric time: %s" % elapsed)
logger.debug("illumina_chimera_after_cluster time = %s" % str(elapsed))
def illumina_chimera_after_cluster(runobj):
mychimera = Chimera(runobj)
mychimera.illumina_rm_size_files()
start = time.time()
mychimera.illumina_size_to_freq_in_chimer()
elapsed = (time.time() - start)
print "illumina_size_to_freq_in_chimer time: %s" % elapsed
# start = time.time()
# print "Check chimeric statistics. If ref > 15% and ratio ref to de-novo > 2 use only de-novo"
# mychimera.check_chimeric_stats()
# elapsed = (time.time() - start)
# print "check_chimeric_stats time: %s" % elapsed
start = time.time()
print "Creating nonchimeric files in %s" % mychimera.indir
mychimera.move_out_chimeric()
elapsed = (time.time() - start)
print "move_out_chimeric time: %s" % elapsed
print "illumina_chimera_after_cluster time = %s" % str(elapsed)
def chimera(runobj):
chimera_cluster_ids = []
logger.debug("Starting Chimera Checker")
# lets read the trim status file out here and keep those details out of the Chimera code
idx_keys = get_keys(runobj)
#new_lane_keys = convert_unicode_dictionary_to_str(json.loads(open(runobj.trim_status_file_name,"r").read()))["new_lane_keys"]
mychimera = Chimera(runobj)
c_den = mychimera.chimera_denovo(idx_keys)
if c_den[0] == 'SUCCESS':
chimera_cluster_ids += c_den[2]
chimera_code='PASS'
elif c_den[0] == 'NOREGION':
chimera_code='NOREGION'
elif c_den[0] == 'FAIL':
chimera_code = 'FAIL'
else:
chimera_code='FAIL'
c_ref = mychimera.chimera_reference(idx_keys)
if c_ref[0] == 'SUCCESS':
chimera_cluster_ids += c_ref[2]
chimera_code='PASS'
elif c_ref[0] == 'NOREGION':
chimera_code = 'NOREGION'
elif c_ref[0] == 'FAIL':
chimera_code='FAIL'
else:
chimera_code='FAIL'
#print chimera_cluster_ids
runobj.chimera_status_file_h = open(runobj.chimera_status_file_name,"w")
if chimera_code == 'PASS':
chimera_cluster_code = wait_for_cluster_to_finish(chimera_cluster_ids)
if chimera_cluster_code[0] == 'SUCCESS':
logger.info("Chimera checking finished successfully")
runobj.chimera_status_file_h.write("CHIMERA SUCCESS\n")
runobj.run_status_file_h.write("CHIMERA SUCCESS\n")
else:
logger.info("3-Chimera checking Failed")
runobj.chimera_status_file_h.write("3-CHIMERA ERROR: "+str(chimera_cluster_code[1])+" "+str(chimera_cluster_code[2])+"\n")
runobj.run_status_file_h.write("3-CHIMERA ERROR: "+str(chimera_cluster_code[1])+" "+str(chimera_cluster_code[2])+"\n")
sys.exit("3-Chimera checking Failed")
elif chimera_code == 'NOREGION':
logger.info("No regions found that need chimera checking")
runobj.chimera_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
runobj.run_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
elif chimera_code == 'FAIL':
logger.info("1-Chimera checking Failed")
runobj.chimera_status_file_h.write("1-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("1-CHIMERA ERROR: \n")
sys.exit("1-Chimera Failed")
else:
logger.info("2-Chimera checking Failed")
runobj.chimera_status_file_h.write("2-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("2-CHIMERA ERROR: \n")
sys.exit("2-Chimera checking Failed")
sleep(2)
if chimera_code == 'PASS' and chimera_cluster_code[0] == 'SUCCESS':
mychimera.write_chimeras_to_deleted_file(idx_keys)
# should also recreate fasta
# then read chimera files and place (or replace) any chimeric read_id
# into the deleted file.
mymblutils = MBLPipelineFastaUtils(idx_keys, mychimera.outdir)
# write new cleaned files that remove chimera if apropriate
# these are in fasta_mbl_pipeline.py
# the cleaned file are renamed to the original name:
# lane_key.unique.fa
# lane_key.trimmed.fa
# lane_key.names --
# lane_key.abund.fa -- this file is for the uclust chimera script
# lane_key.deleted.txt -- no change in this file
# THE ORDER IS IMPORTANT HERE:
mymblutils.write_clean_fasta_file()
mymblutils.write_clean_names_file()
mymblutils.write_clean_uniques_file()
mymblutils.write_clean_abundance_file()
# write keys file for each lane_key - same fields as db table? for easy writing
# write primers file for each lane_key
# Write new clean files to the database
# rawseq table not used
# trimseq
# runkeys
# primers
# run primers
mymblutils.write_clean_files_to_database()
def illumina_chimera(runobj):
utils = PipelneUtils()
start = time.time()
mychimera = Chimera(runobj)
# elapsed = (time.time() - start)
# print elapsed
print "Preparing input files (replacing \"frequency:\" with \";size=\" and capitalize reads)"
# start = time.time()
# mychimera.illumina_freq_to_size_in_chg()
# elapsed = (time.time() - start)
# print "1a) illumina_freq_to_size_in_chg time: %s" % elapsed
start = time.time()
mychimera.call_illumina_sed("from_frequency_to_size")
elapsed = (time.time() - start)
print "call_illumina_sed from_frequency_to_size time: %s" % elapsed
#
print "START chimera checking"
# c_den =
mychimera.chimera_checking("denovo")
# # print "c_den - check denovo res: %s" % c_den
# print c_den
# c_den =
mychimera.chimera_checking("ref")
# print c_den
# todo: use run_until_done_on_cluster from utils
"""run after cluster is done with it work:"""
start = time.time()
time_before = utils.get_time_now()
print "time_before = %s" % time_before
print "Waiting for the cluster..."
while True:
if utils.is_local():
sleep(1)
else:
sleep(120)
cluster_done = mychimera.check_if_cluster_is_done(time_before)
print "cluster_done = %s" % cluster_done
if (cluster_done):
break
elapsed = (time.time() - start)
print "Cluster is done with both chimera checkings in: %s" % elapsed
mychimera.check_if_chimera_dir_empty()
mychimera.illumina_rm_size_files()
# start = time.time()
# mychimera.illumina_size_to_freq_in_chimer()
# elapsed = (time.time() - start)
# print "2a) illumina_size_to_freq_in_chimer time: %s" % elapsed
start = time.time()
mychimera.call_illumina_sed("from_size_to_frequency")
elapsed = (time.time() - start)
print "call_illumina_sed from_size_to_frequency time: %s" % elapsed
# start = time.time()
# print "Check chimeric statistics. If ref > 15% and ratio ref to de-novo > 2 use only de-novo"
# mychimera.check_chimeric_stats()
# elapsed = (time.time() - start)
# print "check_chimeric_stats time: %s" % elapsed
start = time.time()
print "Creating nonchimeric files in %s" % mychimera.indir
mychimera.move_out_chimeric()
elapsed = (time.time() - start)
print "move_out_chimeric time: %s" % elapsed
def chimera(runobj):
chimera_cluster_ids = []
logger.debug("Starting Chimera Checker")
# lets read the trim status file out here and keep those details out of the Chimera code
idx_keys = get_keys(runobj)
#new_lane_keys = convert_unicode_dictionary_to_str(json.loads(open(runobj.trim_status_file_name,"r").read()))["new_lane_keys"]
# Open run STATUS File here.
# open in append mode because we may start the run in the middle
# say at the gast stage and don't want to over write.
# if we re-run trimming we'll get two trim status reports
runobj.run_status_file_h = open(runobj.run_status_file_name, "a")
mychimera = Chimera(runobj)
logger.debug("\nStarting DeNovo Chimera")
c_den = mychimera.chimera_denovo()
logger.debug("Ending DeNovo Chimera")
if c_den[0] == 'SUCCESS':
chimera_cluster_ids += c_den[2] # add a list to a list
logger.debug("chimera_cluster_ids: "+' '.join(chimera_cluster_ids))
chimera_code='PASS'
elif c_den[0] == 'NOREGION':
chimera_code='NOREGION'
elif c_den[0] == 'FAIL':
chimera_code = 'FAIL'
else:
chimera_code='FAIL'
logger.debug("Chimera DeNovo Code: "+chimera_code)
logger.debug("\nStarting Reference Chimera")
c_ref = mychimera.chimera_reference()
if c_ref[0] == 'SUCCESS':
chimera_cluster_ids += c_ref[2]
chimera_code='PASS'
elif c_ref[0] == 'NOREGION':
chimera_code = 'NOREGION'
elif c_ref[0] == 'FAIL':
chimera_code='FAIL'
else:
chimera_code='FAIL'
#print chimera_cluster_ids
runobj.chimera_status_file_h = open(runobj.chimera_status_file_name,"w")
if chimera_code == 'PASS':
if runobj.use_cluster:
chimera_cluster_code = wait_for_cluster_to_finish(chimera_cluster_ids)
if chimera_cluster_code[0] == 'SUCCESS':
logger.info("Chimera checking finished successfully")
runobj.chimera_status_file_h.write("CHIMERA SUCCESS\n")
runobj.run_status_file_h.write("CHIMERA SUCCESS\n")
else:
logger.info("3-Chimera checking Failed")
runobj.chimera_status_file_h.write("3-CHIMERA ERROR: "+str(chimera_cluster_code[1])+" "+str(chimera_cluster_code[2])+"\n")
runobj.run_status_file_h.write("3-CHIMERA ERROR: "+str(chimera_cluster_code[1])+" "+str(chimera_cluster_code[2])+"\n")
sys.exit("3-Chimera checking Failed")
else:
chimera_cluster_code = ['SUCCESS','Not using cluster']
logger.info("Chimera checking finished without using cluster")
runobj.chimera_status_file_h.write("CHIMERA SUCCESS--no cluster\n")
runobj.run_status_file_h.write("CHIMERA SUCCESS--no cluster\n")
elif chimera_code == 'NOREGION':
logger.info("No regions found that need chimera checking")
runobj.chimera_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
runobj.run_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
elif chimera_code == 'FAIL':
logger.info("1-Chimera checking Failed")
runobj.chimera_status_file_h.write("1-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("1-CHIMERA ERROR: \n")
sys.exit("1-Chimera Failed")
else:
logger.info("2-Chimera checking Failed")
runobj.chimera_status_file_h.write("2-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("2-CHIMERA ERROR: \n")
sys.exit("2-Chimera checking Failed")
sleep(2)
if chimera_code == 'PASS' and chimera_cluster_code[0] == 'SUCCESS':
logger.info("Writing Chimeras to deleted files")
mychimera.write_chimeras_to_deleted_file()
# should also recreate fasta
# then read chimera files and place (or replace) any chimeric read_id
# into the deleted file.
mymblutils = MBLPipelineFastaUtils(idx_keys, runobj)
# write new cleaned files that remove chimera if apropriate
# these are in fasta_mbl_pipeline.py
# the cleaned file are renamed to the original name:
# lane_key.unique.fa
# lane_key.trimmed.fa
# lane_key.names --
# lane_key.abund.fa -- this file is for the uclust chimera script
# lane_key.deleted.txt -- no change in this file
# THE ORDER IS IMPORTANT HERE:
mymblutils.write_clean_fasta_file()
mymblutils.write_clean_names_file()
mymblutils.write_clean_uniques_file()
mymblutils.write_clean_abundance_file()
def illumina_chimera(runobj):
utils = PipelneUtils()
# start = time.time()
mychimera = Chimera(runobj)
# elapsed = (time.time() - start)
# logger.debug(elapsed)
logger.debug(
"Preparing input files (replacing \"frequency:\" with \";size=\" and capitalize reads)"
)
# start = time.time()
# mychimera.illumina_freq_to_size_in_chg()
# elapsed = (time.time() - start)
# logger.debug("1a) illumina_freq_to_size_in_chg time: %s" % elapsed)
start = time.time()
mychimera.call_illumina_sed("from_frequency_to_size")
elapsed = (time.time() - start)
logger.debug("call_illumina_sed from_frequency_to_size time: %s" % elapsed)
#
logger.debug("START chimera checking")
# c_den =
mychimera.chimera_checking()
# # logger.debug("c_den - check denovo res: %s" % c_den)
# logger.debug(c_den)
# c_den =
# mychimera.chimera_checking("ref")
# logger.debug(c_den)
# todo: use run_until_done_on_cluster from utils
"""run after cluster is done with it work:"""
start = time.time()
time_before = utils.get_time_now()
logger.debug("time_before = %s" % time_before)
logger.debug("Waiting for the cluster...")
while True:
if utils.is_local():
sleep(1)
break
else:
sleep(120)
cluster_done = mychimera.check_if_cluster_is_done(time_before)
logger.debug("cluster_done = %s" % cluster_done)
if cluster_done:
break
elapsed = (time.time() - start)
logger.debug("Cluster is done with both chimera checkings in: %s" %
elapsed)
mychimera.check_if_chimera_dir_empty()
mychimera.illumina_rm_size_files()
# start = time.time()
# mychimera.illumina_size_to_freq_in_chimer()
# elapsed = (time.time() - start)
# logger.debug("2a) illumina_size_to_freq_in_chimer time: %s" % elapsed)
start = time.time()
mychimera.call_illumina_sed("from_size_to_frequency")
elapsed = (time.time() - start)
logger.debug("call_illumina_sed from_size_to_frequency time: %s" % elapsed)
# start = time.time()
# logger.debug("Check chimeric statistics. If ref > 15% and ratio ref to de-novo > 2 use only de-novo")
# mychimera.check_chimeric_stats()
# elapsed = (time.time() - start)
# logger.debug("check_chimeric_stats time: %s" % elapsed)
start = time.time()
logger.debug("Creating nonchimeric files in %s" % mychimera.indir)
mychimera.move_out_chimeric()
elapsed = (time.time() - start)
logger.debug("move_out_chimeric time: %s" % elapsed)
def chimera(runobj):
chimera_cluster_ids = []
logger.debug("Starting Chimera Checker")
# lets read the trim status file out here and keep those details out of the Chimera code
idx_keys = get_keys(runobj)
# new_lane_keys = convert_unicode_dictionary_to_str(json.loads(open(runobj.trim_status_file_name,"r").read()))["new_lane_keys"]
# Open run STATUS File here.
# open in append mode because we may start the run in the middle
# say at the gast stage and don't want to over write.
# if we re-run trimming we'll get two trim status reports
runobj.run_status_file_h = open(runobj.run_status_file_name, "a")
mychimera = Chimera(runobj)
logger.debug("\nStarting DeNovo Chimera")
c_den = mychimera.chimera_denovo()
logger.debug("Ending DeNovo Chimera")
if c_den[0] == 'SUCCESS':
chimera_cluster_ids += c_den[2] # add a list to a list
logger.debug("chimera_cluster_ids: " + ' '.join(chimera_cluster_ids))
chimera_code = 'PASS'
elif c_den[0] == 'NOREGION':
chimera_code = 'NOREGION'
elif c_den[0] == 'FAIL':
chimera_code = 'FAIL'
else:
chimera_code = 'FAIL'
logger.debug("Chimera DeNovo Code: " + chimera_code)
logger.debug("\nStarting Reference Chimera")
c_ref = mychimera.chimera_reference()
if c_ref[0] == 'SUCCESS':
chimera_cluster_ids += c_ref[2]
chimera_code = 'PASS'
elif c_ref[0] == 'NOREGION':
chimera_code = 'NOREGION'
elif c_ref[0] == 'FAIL':
chimera_code = 'FAIL'
else:
chimera_code = 'FAIL'
# logger.debug(chimera_cluster_ids)
runobj.chimera_status_file_h = open(runobj.chimera_status_file_name, "w")
if chimera_code == 'PASS':
if runobj.use_cluster:
chimera_cluster_code = wait_for_cluster_to_finish(
chimera_cluster_ids)
if chimera_cluster_code[0] == 'SUCCESS':
logger.info("Chimera checking finished successfully")
runobj.chimera_status_file_h.write("CHIMERA SUCCESS\n")
runobj.run_status_file_h.write("CHIMERA SUCCESS\n")
else:
logger.info("3-Chimera checking Failed")
runobj.chimera_status_file_h.write(
"3-CHIMERA ERROR: " + str(chimera_cluster_code[1]) + " " +
str(chimera_cluster_code[2]) + "\n")
runobj.run_status_file_h.write("3-CHIMERA ERROR: " +
str(chimera_cluster_code[1]) +
" " +
str(chimera_cluster_code[2]) +
"\n")
sys.exit("3-Chimera checking Failed")
else:
chimera_cluster_code = ['SUCCESS', 'Not using cluster']
logger.info("Chimera checking finished without using cluster")
runobj.chimera_status_file_h.write("CHIMERA SUCCESS--no cluster\n")
runobj.run_status_file_h.write("CHIMERA SUCCESS--no cluster\n")
elif chimera_code == 'NOREGION':
logger.info("No regions found that need chimera checking")
runobj.chimera_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
runobj.run_status_file_h.write("CHIMERA CHECK NOT NEEDED\n")
elif chimera_code == 'FAIL':
logger.info("1-Chimera checking Failed")
runobj.chimera_status_file_h.write("1-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("1-CHIMERA ERROR: \n")
sys.exit("1-Chimera Failed")
else:
logger.info("2-Chimera checking Failed")
runobj.chimera_status_file_h.write("2-CHIMERA ERROR: \n")
runobj.run_status_file_h.write("2-CHIMERA ERROR: \n")
sys.exit("2-Chimera checking Failed")
sleep(2)
if chimera_code == 'PASS' and chimera_cluster_code[0] == 'SUCCESS':
logger.info("Writing Chimeras to deleted files")
mychimera.write_chimeras_to_deleted_file()
# should also recreate fasta
# then read chimera files and place (or replace) any chimeric read_id
# into the deleted file.
mymblutils = MBLPipelineFastaUtils(idx_keys, runobj)
# write new cleaned files that remove chimera if apropriate
# these are in fasta_mbl_pipeline.py
# the cleaned file are renamed to the original name:
# lane_key.unique.fa
# lane_key.trimmed.fa
# lane_key.names --
# lane_key.abund.fa -- this file is for the uclust chimera script
# lane_key.deleted.txt -- no change in this file
# THE ORDER IS IMPORTANT HERE:
mymblutils.write_clean_fasta_file()
mymblutils.write_clean_names_file()
mymblutils.write_clean_uniques_file()
mymblutils.write_clean_abundance_file()
