#
# print 'Dumping to files'
# dump_file = bz2.BZ2File(os.path.join(save_path, 'pentaplets_merged_across.p.bz2'), 'w')
# pickle.dump(pentaplets, dump_file)
# dump_file = bz2.BZ2File(os.path.join(save_path, 'quadruplets_merged_across.p.bz2'), 'w')
# pickle.dump(quadruplets, dump_file)
# dump_file = bz2.BZ2File(os.path.join(save_path, 'triplets_merged_across.p.bz2'), 'w')
# pickle.dump(triplets, dump_file)
# dump_file = bz2.BZ2File(os.path.join(save_path, 'duplets_merged_across.p.bz2'), 'w')
# pickle.dump(duplets, dump_file)
if __name__ == '__main__':
print 'Pre-Loading dictionaries'
target_profiles = t.bacteria_target_profiles()
profile2def = t.map_cdd_profile2def()
gid2arcog_cdd = t.map_gid2arcog_cdd()
neighborhood_files_path = neighborhoods_path()
profile_id2code = map_id2cdd()
# for limit_to, report_dir in zip([300, 500, 1000, 100000],['top_300', 'top_500', 'top_1000', 'top_100000']):
#
# print "Limit_to:", limit_to
# print
# generate_plots(limit_to, report_dir, target_profiles, profile2def, gid2arcog_cdd, neighborhood_files_path, profile_id2code)
# print 'Done'
# print "------------------------"
data_path = os.path.join(gv.project_data_path, 'Bacteria/pickle/')
for i, kplet_pool in zip([5, 4, 3, 2], [pentaplets, quadruplets, triplets, duplets]):
for j, kplet_sublist in enumerate(kplet_pool):
cur_reports_folder = os.path.join(report_files_dir, str(i))
if not os.path.exists(cur_reports_folder):
os.mkdir(cur_reports_folder)
xls_file_name = os.path.join(cur_reports_folder, "%d_%d.xls" % (j+1, i))
r.write_to_xls(xls_file_name,kplet_sublist,target_profiles,profile2def,gid2arcog_cdd,neighborhood_files_path,file2src_src2org_map)
if __name__ == '__main__':
import cPickle
import bz2
print 'Pre-Loading dictionaries'
target_profiles = t.bacteria_target_profiles()
profile2def = t.map_cdd_profile2def()
gid2arcog_cdd = t.map_gid2arcog_cdd()
neighborhood_files_path = neighborhoods_path()
# profile_id2code = map_id2cdd()
# pickle.dump(profile_id2code, open('profile_id2code.p','w'))
profile_id2code = cPickle.load(open('/Users/hudaiber/Projects/NewSystems/code/Bacteria/profile_id2code.p'))
fname = '/Users/hudaiber/Projects/NewSystems/data/Bacteria/pickle/100000/pentaplets_merged_across.p.bz2'
f = bz2.BZ2File(fname, 'rb')
buffer = ""
while 1:
data = f.read()
if data == "":
break
import lib.utils.search_in_genomes as sig
from lib.db import map_id2cdd_clusters
from lib.db.bacteria import pentaplets as p
if __name__=='__main__':
work_path = os.path.join(gv.project_data_path, 'Bacteria/cases')
pty_path = gv.pty_data_path
kplet_id = 306123
id2cdd = map_id2cdd_clusters()
kplet = p.get_report_kplet(kplet_id, id2cdd, load_locations=True)
target_profiles = set(t.bacteria_target_profiles())
dump_file = os.path.join(work_path, 'kplet.p.bz2')
t.dump_compressed_pickle(dump_file, kplet)
kplet = t.load_compressed_pickle(dump_file)
kplet_codes = kplet.codes.difference(target_profiles)
org2src, src2blocks = sig.search_kplet_in_genomes(kplet_codes, target_profiles, max_dist=4)
# dump_file = os.path.join(work_path, 'org2src_global.p.bz2')
# t.dump_compressed_pickle(dump_file, org2src)
# dump_file = os.path.join(work_path, 'src2blocks_global.p.bz2')
# t.dump_compressed_pickle(dump_file, src2blocks)
#
# dump_file = os.path.join(work_path, 'org2src_global.p.bz2')
# org2src = t.load_compressed_pickle(dump_file)
import lib.utils.reporting as r
import lib.utils.search_in_genomes as sig
from lib.db import map_id2cdd_clusters
from lib.db.bacteria import pentaplets as p
if __name__ == '__main__':
work_path = os.path.join(gv.project_data_path, 'Bacteria/cases')
pty_path = gv.pty_data_path
kplet_id = 306123
id2cdd = map_id2cdd_clusters()
kplet = p.get_report_kplet(kplet_id, id2cdd, load_locations=True)
target_profiles = set(t.bacteria_target_profiles())
dump_file = os.path.join(work_path, 'kplet.p.bz2')
t.dump_compressed_pickle(dump_file, kplet)
kplet = t.load_compressed_pickle(dump_file)
kplet_codes = kplet.codes.difference(target_profiles)
org2src, src2blocks = sig.search_kplet_in_genomes(kplet_codes,
target_profiles,
max_dist=4)
# dump_file = os.path.join(work_path, 'org2src_global.p.bz2')
# t.dump_compressed_pickle(dump_file, org2src)
# dump_file = os.path.join(work_path, 'src2blocks_global.p.bz2')
# t.dump_compressed_pickle(dump_file, src2blocks)
#