1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286
|
#!/usr/bin/python
# See the LICENSE file included with this software for license information.
import os, sys, string, getopt, random,subprocess, time, glob,operator, math, datetime,numpy #pysam
import signal
import inspect
from multiprocessing import *
reroot_tree = True #use --midpoint-reroot
try:
import dendropy
except ImportError:
reroot_tree = False
#check for sane file names
special_chars = [",","[","]","{","}","(",")","!","\'","\"","*","\%","\<" ,"\>", "|", " ", "`"]
CSI=""#"\x1B["
reset=""#CSI+"m"
BOLDME = ""#CSI+'\033[1m'
STATUS_BLUE = ""#CSI+'\033[94m'
OK_GREEN = ""#CSI+'\033[92m'#'32m'
SKIP_GRAY = ""#CSI+'\033[37m'
WARNING_YELLOW = ""#CSI+'\033[93m'
ERROR_RED = ""#CSI+'\033[91m'
ENDC = ""#CSI+'0m'
VERSION="v1.2"
PARSNP_DIR = sys.path[0]
try:
os.environ["PARSNPDIR"]
PARSNP_DIR = os.environ["PARSNPDIR"]
except KeyError:
PARSNP_DIR = sys.path[0]
SIGINT = False
try:
os.environ["PYTHONPATH"] = PARSNP_DIR+os.pathsep+os.environ["PYTHONPATH"]
except KeyError:
os.environ["PYTHONPATH"] = PARSNP_DIR+os.pathsep
frozenbinary = True
application_path = ""
if getattr(sys, 'frozen', False):
application_path = os.path.dirname(sys.executable)
elif __file__:
application_path = os.path.dirname(__file__)
frozenbinary = False
if frozenbinary:
utilPath = PARSNP_DIR
libPath = os.path.abspath(utilPath + os.sep + ".." + os.sep + "lib")
if os.path.exists(libPath):
oldLDPath = ""
needToAdd = True
if "LD_LIBRARY_PATH" in os.environ:
oldLDPath = os.environ["LD_LIBRARY_PATH"]
if libPath in oldLDPath:
needToAdd = False
elif "DYLD_FALLBACK_LIBRARY_PATH" in os.environ:
oldLDPath = os.environ["DYLD_FALLBACK_LIBRARY_PATH"]
if libPath in oldLDPath:
needToAdd = False
if needToAdd:
os.environ["DYLD_FALLBACK_LIBRARY_PATH"] = libPath + os.pathsep + oldLDPath
os.environ["LD_LIBRARY_PATH"] = libPath + os.pathsep + oldLDPath
VERBOSE = 0
VERSION = "v1.2"
PHI_WINDOWSIZE = 1000
TOTSEQS=0
#template
#read input
#0) init
## Get start time
t1 = time.time()
OSTYPE="linux"
p = subprocess.Popen("echo `uname`", shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
(checkStdout, checkStderr) = p.communicate()
if checkStderr != "":
sys.stderr.write(WARNING_YELLOW+"Warning: Cannot determine OS, defaulting to %s\n"%(OSTYPE)+ENDC)
else:
OSTYPE = checkStdout.strip()
binary_type = "linux"
if OSTYPE == "Darwin":
binary_type = "osx"
else:
binary_type = "linux"
def handler(signum, frame):
global SIGINT
SIGINT = True
print 'Caught request to terminate by user (CTRL+C), exiting now, bye'
sys.exit(128)
signal.signal(signal.SIGINT, handler)
def run_phipack(query,seqlen,workingdir):
currdir = os.getcwd()
os.chdir(workingdir)
command = "/usr/bin/phipack-profile -o -v -n %d -w 100 -m 100 -f %s > %s.out"%(seqlen,query,query)
run_command(command,1)
os.chdir(currdir)
def run_fasttree(query,workingdir,recombination_sites):
currdir = os.getcwd()
os.chdir(workingdir)
command = "fasttree -nt -quote -gamma -slow -boot 100 seq.fna > out.tree"
run_command(command,1)
os.chdir(currdir)
def run_bng(query,workingdir):
currdir = os.getcwd()
os.chdir(workingdir)
command = "%s/run_fasta"%()
run_command(command,1)
command = "%s/run_fasta"%()
run_command(command,1)
command = "%s/run_fasta"%()
run_command(command,1)
os.chdir(currdir)
def parallelWrapper(params):
try:
jobID = params["jobID"]
result = {}
result["jobID"] = jobID
result["status"] = 0
run_mummer(params["ref"], params["query"], params["prefix"])
result["status"] = 1
return result
except KeyboardInterrupt:
result["status"] = 0
sys.stderr.write("Keyboard error in thread %d, quitting\n"%(jobID))
return result
except Exception:
result["status"] = 0
sys.stderr.write( "Other error in thread %d, quitting\n"%(jobID))
return result
def parallelFtWrapper(params):
try:
jobID = params["jobID"]
result = {}
result["jobID"] = jobID
result["status"] = 0
run_fasttree(params["query"], params["dir"], params["recombination"])
result["status"] = 1
return result
except KeyboardInterrupt:
result["status"] = 0
sys.stderr.write( "Keyboard error in thread %d, quitting\n"%(jobID))
return result
except Exception:
result["status"] = 0
sys.stderr.write( "Other error in thread %d, quitting\n"%(jobID))
return result
def parallelPhiWrapper(params):
try:
jobID = params["jobID"]
result = {}
result["jobID"] = jobID
result["status"] = 0
if params["seqlen"] >= 1000:
run_phipack(params["query"],params["seqlen"],params["dir"])
result["status"] = 1
else:
result["status"] = 2
return result
except KeyboardInterrupt:
result["status"] = 0
sys.stderr.write( "Keyboard error in thread %d, quitting\n"%(jobID))
return result
except Exception:
result["status"] = 0
sys.stderr.write( "Other error in thread %d, quitting\n"%(jobID))
return result
def run_command(command,ignorerc=0):
global SIGINT
p = subprocess.Popen(command, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE,close_fds=True,executable="/bin/bash")
fstdout,fstderr = p.communicate()
rc = p.returncode
if VERBOSE:
sys.stderr.write( fstderr)
if rc != 0 and not SIGINT and not ignorerc and "rm " not in command and "ls " not in command and "unlink " not in command and "ln " not in command and "mkdir " not in command and "mv " not in command:
sys.stderr.write(ERROR_RED+"**ERROR**"+ENDC+"\n")
sys.stderr.write( "The following command failed:\n")
sys.stderr.write( ">>%s\n"%(command))
sys.stderr.write( "Please veryify input data and restart Parsnp. If the problem persists please contact the Parsnp development team.\n")
sys.stderr.write(ERROR_RED+"**ERROR**"+ENDC+"\n")
sys.stderr.write( "\n")
sys.stderr.write( "\n")
sys.exit(rc)
sys.stderr.write( BOLDME+"|--Parsnp %s--|\n"%(VERSION)+ENDC)
sys.stderr.write( BOLDME+"For detailed documentation please see --> http://harvest.readthedocs.org/en/latest\n"+ENDC)
#set MUMmer paths
if os.path.exists("%s/MUMmer/nucmer_run"%(PARSNP_DIR)):
ff = open("%s/MUMmer/nucmer_run"%(PARSNP_DIR))
ffd = ff.read()
ff.close()
ffd = ffd.replace("$MUMMERPATH1",PARSNP_DIR)
ff = open("%s/MUMmer/nucmer"%(PARSNP_DIR),'w')
ff.write(ffd)
ff.close()
def version():
print VERSION
def usage():
print "usage: parsnp [options] [-g|-r|-q](see below) -d <genome_dir> -p <threads>"
print ""
print "Parsnp quick start for three example scenarios: "
print "1) With reference & genbank file: "
print " >parsnp -g <reference_genbank_file1,reference_genbank_file2,..> -d <genome_dir> -p <threads> "
print ""
print "2) With reference but without genbank file:"
print " >parsnp -r <reference_genome> -d <genome_dir> -p <threads> "
print ""
print "3) Autorecruit reference to a draft assembly:"
print " >parsnp -q <draft_assembly> -d <genome_db> -p <threads> "
print ""
print "[Input parameters]"
print "<<input/output>>"
print " -c = <flag>: (c)urated genome directory, use all genomes in dir and ignore MUMi? (default = NO)"
print " -d = <path>: (d)irectory containing genomes/contigs/scaffolds"
print " -r = <path>: (r)eference genome (set to ! to pick random one from genome dir)"
print " -g = <string>: Gen(b)ank file(s) (gbk), comma separated list (default = None)"
print " -o = <string>: output directory? default [./P_CURRDATE_CURRTIME]"
print " -q = <path>: (optional) specify (assembled) query genome to use, in addition to genomes found in genome dir (default = NONE)"
print ""
print "<<MUMi>>"
print " -U = <float>: max MUMi distance value for MUMi distribution "
print " -M = <flag>: calculate MUMi and exit? overrides all other choices! (default: NO)"
#new, mutually exclusive
print " -i = <float>: max MUM(i) distance (default: autocutoff based on distribution of MUMi values)"
print ""
print "<<MUM search>>"
#new, default to lower, 12-17
print " -a = <int>: min (a)NCHOR length (default = 1.1*Log(S))"
print " -C = <int>: maximal cluster D value? (default=100)"
print " -z = <path>: min LCB si(z)e? (default = 25)"
print ""
print "<<LCB alignment>>"
print " -D = <float>: maximal diagonal difference? Either percentage (e.g. 0.2) or bp (e.g. 100bp) (default = 0.12)"
print " -e = <flag> greedily extend LCBs? experimental! (default = NO)"
print " -n = <string>: alignment program (default: libMUSCLE)"
print " -u = <flag>: output unaligned regions? .unaligned (default: NO)"
print ""
print "<<Recombination filtration>>"
#new, default is OFF
print " -x = <flag>: enable filtering of SNPs located in PhiPack identified regions of recombination? (default: NO)"
print ""
print "<<Misc>>"
print " -h = <flag>: (h)elp: print this message and exit"
print " -p = <int>: number of threads to use? (default= 1)"
print " -P = <int>: max partition size? limits memory usage (default= 15000000)"
print " -v = <flag>: (v)erbose output? (default = NO)"
print " -V = <flag>: output (V)ersion and exit"
print ""
#hidden, not yet supported options
#print "-q = <path>: (optional) specify (assembled) query genome to use, in addition to genomes found in genome dir (default = NONE)"
#print "-s = <flag>: (s)plit genomes by n's (default = NO)"
#print "-z = <path>: min cluster si(z)e? (default = 10)"
#print "-F = <flag>: fast MUMi calc? (default=NO)"
#print "-g = <bool>: auto-launch (g)ingr? (default = NO)"
if __name__ == "__main__":
parsnp_dir= sys.path[0]
#print parsnp_dir
#PARSNP_DIR = parsnp_dir
opts = []
args = []
try:
opts, args = getopt.getopt(sys.argv[1:], "hxved:C:F:D:i:g:m:MU:o:a:cln:p:P:q:r:Rsz:uV", ["help","xtrafast","verbose","extend","sequencedir","clusterD","DiagonalDiff","iniFile","genbank","mumlength","onlymumi","MUMi","outputDir","anchorlength","curated","layout","aligNmentprog","threads","max-partition-size","query","reference","nofiltreps","split","minclustersiZe","unaligned","version"])
except getopt.GetoptError, err:
# print help information and exit:
print str(err)
usage()
sys.exit(2)
ref = ""
currdir = os.getcwd()
seqdir = "./genomes"
anchor = "1.0*(Log(S))"
mum = "1.1*(Log(S))"
maxpartition = 15000000
fastmum = True
cluster = "300"
curated = False
aligner = "2"
threads = "32"
unaligned = "0"
mincluster = "21"
diagdiff = "0.12"
splitseq = False
extend = False
layout = False
xtrafast = False
inifile=""
mumi_only = False
mumidistance = 0.5
genbank_file = ""
genbank_files = []
genbank_files_str = ""
genbank_files_cat = ""
genbank_ref = ""
outputDir = ""
query = ""
reflen = 0
use_gingr = ""
inifile_exists = False
req_params = {}
req_params["genbank"] = 0
req_params["refgenome"] = 0
req_params["genomedir"] = 0
filtreps = False
repfile = ""
multifasta = False
ref_seqs = {}
for o, a in opts:
if o in ("-v","--verbose"):
VERBOSE = True
if o in ("-V","--version"):
version()
sys.exit(0)
elif o in ("-h", "--help"):
usage()
sys.exit(0)
elif o in ("-R","--filtreps"):
print "WARNING: -R option is no longer supported, ignoring. Please see harvest.readthedocs.org for bed filtering w/ harvesttools"
filtreps = False
elif o in ("-r","--reference"):
ref = a
if a != "!":
try:
rf = open(ref,'r')
rfd = rf.read()
refseqs = rfd.split(">")[1:]
currpos = 0
seqnum = 1
if len(refseqs) > 1:
multifasta = True
for seq in refseqs:
fastalen = len(seq.split("\n",1)[-1].replace("\n",""))
ref_seqs[currpos+fastalen] = seqnum
currpos = currpos+fastalen
seqnum+=1
rf.close()
except IOError:
sys.stderr.write( "ERROR: Reference genome file %s not found\n"%(ref))
sys.exit(1)
req_params["refgenome"] = 1
elif o in ("-d","--sequenceDir"):
seqdir = a
if not os.path.exists(seqdir):
sys.stderr.write( "ERROR: genome dir %s does not exist\n"%(seqdir))
sys.exit(1)
if len(glob.glob("%s/*"%(seqdir))) == 0:
sys.stderr.write( "ERROR: genome dir %s is empty\n"%(seqdir))
sys.exit(1)
req_params["genomedir"] = 1
elif o in ("-q","--query"):
query= a
try:
rf = open(query,'r')
rf.close()
except IOError:
sys.stderr.write( "ERROR: optional Query file %s provided but not found\n"%(query))
sys.exit(1)
elif o in ("-g","--genbank"):
genbank_files_str = a
genbank_files = genbank_files_str.split(",")
ctcmd = "cat "
first = True
#genbank_ref = ""
for genbank_file in genbank_files_str.split(","):
if len(genbank_file) <= 1:
continue
ctcmd += genbank_file + " "
try:
#parse out reference, starts at ORIGIN ends at //, remove numbers,
rf = open(genbank_file,'r')
if first:
genbank_ref = genbank_file+".fna"
genbank_ref1 = open(genbank_ref,'w')
giline = ""
while 1:
giline = rf.readline()
if "VERSION" and "GI" in giline:
break
elif giline == None or giline == "":
sys.stderr.write( "ERROR: Genbank file %s malformatted \n"%(genbank_file))
sys.exit(1)
if len(giline) <= 2:
sys.stderr.write( "ERROR: Genbank file %s malformatted \n"%(genbank_file))
sys.exit(1)
genbank_ref1.write(">gi|"+giline.split("GI:")[-1])
first = False
else:
genbank_ref1 = open(genbank_ref,'a')
giline = ""
while 1:
giline = rf.readline()
if "VERSION" and "GI" in giline:
break
elif giline == None or giline == "":
sys.stderr.write( "ERROR: Genbank file %s malformatted \n"%(genbank_file))
sys.exit(1)
if len(giline) <= 2:
sys.stderr.write( "ERROR: Genbank file %s malformatted \n"%(genbank_file))
sys.exit(1)
genbank_ref1.write(">gi|"+giline.split("GI:")[-1])
ntdata = False
data = ""
for line in rf.xreadlines():
if ntdata:
if "//" in line:
ntdata = False
break
data += line[9:].replace(" ","")
if "ORIGIN" in line:
ntdata = True
rf.close()
if len(data) < 10:
sys.stderr.write( "ERROR: Genbank file %s contains no sequence data\n"%(genbank_file))
sys.exit(1)
genbank_ref1.write(data.upper())
genbank_ref1.close()
except IOError:
sys.stderr.write( "ERROR: Genbank file %s not found\n"%(genbank_file))
sys.exit(1)
genbank_files_cat = "%s.cat"%(genbank_files[0])
os.system(ctcmd+"> "+genbank_files_cat)
req_params["genbank"] = 1
elif o in ("-a","--anchorlength"):
anchor = a
elif o in ("-m","--mumlength"):
mum = a
elif o in ("-D","--DiagonalDiff"):
diagdiff = a
elif o in ("-o","--outputDir"):
outputDir = a
elif o in ("-e","--extend"):
extend = True
elif o in ("-M","--onlymumi"):
mumi_only = True
elif o in ("-U","--MUMi"):
mumidistance = a
elif o in ("-x","--xtrafast"):
xtrafast = True
elif o in ("-i","--iniFile"):
inifile = a
inifile_exists = True
elif o in ("-c","--curated"):
curated = True
elif o in ("-n","--alignmentprog"):
aligner = a
if aligner == "muscle":
aligner = "2"
elif aligner == "mafft":
aligner = "1"
elif aligner == "fsa":
aligner = "3"
elif aligner == "prank":
aligner = "4"
else:
aligner = "2"
elif o in ("-p","--threads"):
threads = a
elif o in ("-P","--max-partition-size"):
maxpartition = a
elif o in ("-F","--fastmum"):
fastmum = True
elif o in ("-C","--clusterD"):
cluster = a
elif o in ("-u","--unaligned"):
unaligned = "1"
elif o in ("-s","--split"):
splitseq = True
elif o in ("-l","--layout"):
layout = True
elif o in ("-z","--minclustersize"):
mincluster = a
if outputDir != "":
today = datetime.datetime.now()
timestamp = "P_"+today.isoformat().replace("-","_").replace(".","").replace(":","").replace("T","_")
outputDir2 = timestamp#outputDir+os.sep+timestamp
if outputDir == "." or outputDir == "./" or outputDir == "/":
sys.stderr.write( WARNING_YELLOW+"Warning: specified output dir is current working dir! will clobber any parsnp.* results"+ENDC)
outputDir = ""
elif os.path.exists("%s"%(outputDir)):
pass
else:
os.mkdir("%s"%(outputDir))
else:
today = datetime.datetime.now()
timestamp = "P_"+today.isoformat().replace("-","_").replace(".","").replace(":","").replace("T","_")
outputDir = os.getcwd()+os.sep+timestamp
os.mkdir("%s"%(outputDir))
if len(opts) < 2:
usage()
sys.exit(2)
sortem = True
if len(ref) == 0 and len(genbank_ref) != 0:
#we are parsing from genbank, set ref to genbank_ref && turn off sorting
ref = genbank_ref
sortem = False
autopick_ref = False
if (len(ref) == 0 and len(query) == 0) or len(seqdir) == "":
sys.stderr.write( ERROR_RED+"ERROR: no seqs provided, yet required. exit!\n"+ENDC)
sys.exit(0)
elif len(ref) == 0 and len(query) != 0:
sys.stderr.write( WARNING_YELLOW+"WARNING: no reference genome specified, going to autopick from %s as closest to %s\n"%(seqdir, query)+ENDC)
autopick_ref = True
ref = query
if 1:
print (len(outputDir)+17)*"*"
print BOLDME+"SETTINGS:"+ENDC
if ref != "!":
print "|-"+BOLDME+"refgenome:\t%s"%(ref)+ENDC
else:
print "|-"+BOLDME+"refgenome:\t%s"%("autopick")+ENDC
print "|-"+BOLDME+"aligner:\tlibMUSCLE"+ENDC
print "|-"+BOLDME+"seqdir:\t%s"%(seqdir)+ENDC
print "|-"+BOLDME+"outdir:\t%s"%(outputDir)+ENDC
print "|-"+BOLDME+"OS:\t\t%s"%(OSTYPE)+ENDC
print "|-"+BOLDME+"threads:\t%s"%(threads)+ENDC
print (len(outputDir)+17)*"*"
print "\n<<Parsnp started>>\n"
#1)read fasta files (contigs/scaffolds/finished/DBs/dirs)
sys.stderr.write( "-->Reading Genome (asm, fasta) files from %s..\n"%(seqdir))
files = []
try:
files1 = os.listdir(seqdir)
files = []
for f1 in files1:
if not os.path.isdir(seqdir+os.sep+f1):
files.append(f1)
sys.stderr.write( " |->["+OK_GREEN+"OK"+ENDC+"]\n")
except IOError:
sys.stderr.write( ERROR_RED+"ERROR: problem reading files from %s\n"%(seqdir)+ENDC)
sys.exit(1)
sys.stderr.write( "-->Reading Genbank file(s) for reference (.gbk) %s..\n"%(genbank_files_str))
if len(genbank_file) == 0:
sys.stderr.write( " |->["+WARNING_YELLOW+"WARNING"+ENDC+"]"+": no genbank file provided for reference annotations, skipping..\n"+ENDC)
elif not os.path.exists(genbank_file):
sys.stderr.write( " |->["+ERROR_RED+"ERROR"+ENDC+"]"+": provided genbank file does not exist, skipping..\n"+ENDC)
else:
sys.stderr.write( " |->["+OK_GREEN+"OK"+ENDC+"]\n")
fnafiles = []
allfiles = []
fnaf_sizes = {}
allfile_dict = {}
reflen = 0
fnafiles1 = []
for file in files:
#any file in genome dir will be added..
if file[0] != "." and file[-1] != "~" and len(file) > 1 and not os.path.isdir(seqdir+os.sep+file):
ff = open(seqdir+os.sep+file,'r')
hdr = ff.readline()
seq = ff.readline()
if len(seq) > 1 and ("A" in seq.upper() or "G" in seq.upper() or "C" in seq.upper() or "T" in seq.upper() or "N" in seq.upper()) and hdr[0] == ">":
nameok = True
for char in special_chars:
if char in file:
print "WARNING: File %s contains a non-supported special character (\'%s\') in file name. Please remove if you'd like to include. For best practices see: http://support.apple.com/en-us/HT202808"%(file,char)
nameok = False
break
if nameok:
fnafiles1.append(file)
if ref == "!":
ref = random.choice(fnafiles1)
ref = seqdir+os.sep+ref
if 1:
ff = open(ref,'r')
hdr = ff.readline()
if hdr[0] == ">":
data = ff.read()
data = data.replace("\n","")
if "-" in data:
sys.stderr.write( "ERROR: ref genome sequence %s seems to aligned! remove and restart \n"%(ref))
sys.exit(1)
reflen = len(data)
ff.close()
for file in files:
nameok = True
for char in special_chars:
if char in file:
#print "WARNING: File %s contains a non-supported special character (%s) in file name. Please remove if you'd like to include. For best practices see: http://support.apple.com/en-us/HT202808"%(file,char)
nameok = False
break
if not nameok:
continue
if file[0] != "." and file[-1] != "~":
ff = open(seqdir+os.sep+file,'r')
hdr = ff.readline()
if hdr[0] == ">":
data = []
totlen = 0
for line in ff.xreadlines():
if line[0] != ">":
data.append(line.replace("\n",""))
if "-" in line:
sys.stderr.write( "ERROR: genome sequence %s seems to aligned! remove and restart \n"%(file))
sys.exit(1)
totlen += len(line.replace("\n",""))
if ref in file or file in ref:
reflen = totlen#len(data)
continue
#sorry too small
if totlen <= 20:
continue
sizediff = float(reflen)/float(totlen)
if sizediff <= 0.6 or sizediff >= 1.4:
continue
fnafiles.append(file)
fnaf_sizes[file] = totlen#len(data)
ff.close()
if ref in fnafiles:
sys.stderr.write( "ERROR: reference genome %s also in genome directory, restart and select different reference genome\n"%(ref))
sys.exit(1)
if ref == "!":
fnafiles.remove(ref)
#sort reference by largest replicon to smallest
if sortem and os.path.exists(ref) and not autopick_ref:
ff = open(ref,'r')
seqs = ff.read().split(">")[1:]
seq_dict = {}
seq_len = {}
for seq in seqs:
hdr = ""
nt = ""
try:
hdr,nt = seq.split("\n",1)
except ValueError:
continue
seq_dict[hdr] = nt
seq_len[hdr] = len(nt.replace("\n",""))
seq_len_sort = sorted(seq_len.iteritems(), key=operator.itemgetter(1))
seq_len_sort.reverse()
ffo = open("%s"%(outputDir+os.sep+ref.split(os.sep)[-1]+".ref"),'w')
for item in seq_len_sort:
ffo.write(">%s\n"%(item[0]))
ffo.write("%s"%(seq_dict[item[0]]))
ff.close()
ffo.close()
ref = outputDir+os.sep+ref.split(os.sep)[-1]+".ref"
else:
ref = genbank_ref
#remove any query sequences 30% diff in length
allfiles = [ref.rsplit(os.sep,1)[-1]]
#write INI file
if xtrafast or 1:
extend = False
inifile1 = open("%s/template.ini"%(PARSNP_DIR),'r')
inifiled = inifile1.read()
inifiled = inifiled.replace("$REF",ref)
inifiled = inifiled.replace("$EXTEND","%d"%(extend))
inifiled = inifiled.replace("$ANCHORS",anchor)
inifiled = inifiled.replace("$MUMS",mum)
inifiled = inifiled.replace("$MINCLUSTER",mincluster)
inifiled = inifiled.replace("$CLUSTERD",cluster)
inifiled = inifiled.replace("$THREADS",threads)
inifiled = inifiled.replace("$ALIGNER",aligner)
inifiled = inifiled.replace("$DIAGDIFF",diagdiff)
inifiled = inifiled.replace("$RECOMBFILT","%d"%(xtrafast))
inifiled = inifiled.replace("$OUTDIR",outputDir)
if fastmum:
inifiled = inifiled.replace("$PARTPOS","%d"%(0.2*reflen))
else:
inifiled = inifiled.replace("$PARTPOS","%s"%(maxpartition))
finalfiles = []
#2)get near neighbors (mumi distance)
if os.path.exists(outputDir+os.sep+"alltogether.fasta"):
os.system("rm " + outputDir+os.sep+"alltogether.fasta")
if os.path.exists(outputDir+os.sep+"blocks/b1"):
ftrm = glob.glob(outputDir+os.sep+"blocks/b*")
for file in ftrm:
os.system("rm -rf "+file)
#processed = []
#fnafiles = processed
fileidx = -1
hit_dict = {}
qry_hit_dict = {}
hdr_dict = {}
length_dict = {}
TOTSEQS=len(fnafiles)+1
seqids_list = []
use_mummer_mumi = False
use_parsnp_mumi = True
if not inifile_exists:
if len(fnafiles) < 1 or ref == "":
sys.stderr.write( "Parsnp requires 2 or more genomes to run, exiting\n")
print fnafiles, ref
sys.exit(0)
file_string = ""
cnt = 1
for file in fnafiles:
file_string+="file%d=%s\n"%(cnt,seqdir+os.sep+file)
file_string+="reverse%d=0\n"%(cnt)
cnt +=1
inifiled2 = inifiled.replace("$FILES\n",file_string)
inifiled_mumi = inifiled2
inifiled_mumi = inifiled_mumi.replace("calcmumi=0","calcmumi=1")
inifile_mumi = open(outputDir+os.sep+"all_mumi.ini",'w')
inifile_mumi.write(inifiled_mumi)
inifile_mumi.close()
mumi_dict = {}
if use_parsnp_mumi and not curated:
sys.stderr.write( "-->Calculating MUMi..\n")
if not inifile_exists:
command = "/usr/lib/parsnp/parsnp %sall_mumi.ini"%(outputDir+os.sep)
else:
if not os.path.exists(inifile):
sys.stderr.write( "Error: ini file %s does not exist!\n"%(inifile))
sys.exit(1)
command = "/usr/lib/parsnp/parsnp %s"%(inifile.replace(".ini","_mumi.ini"))
run_command(command)
try:
mumif = open(outputDir+os.sep+"all.mumi",'r')
for line in mumif.xreadlines():
line = line.replace("\n","")
try:
idx,mi = line.split(":")
mumi_dict[int(idx)-1] = float(mi)
except ValueError:
pass
except IOError:
#mumi file generation failed, skip.. use all?
i = 0
for file in fnafiles:
mumi_dict[i] = 1
print " |->["+OK_GREEN+"OK"+ENDC+"]"
finalfiles = []
lowest_mumi = 100
auto_ref = ""
if autopick_ref:
for idx in mumi_dict.keys():
if mumi_dict[idx] < lowest_mumi:
auto_ref = seqdir+os.sep+fnafiles[idx]
ref = auto_ref
lowest_mumi = mumi_dict[idx]
mumi_f = ""
if mumi_only and not curated:
if not os.path.exists(outputDir):
sys.stderr.write("Output directory does not exist! writing to cwd\n")
outputDir = ""
mumi_f = open("recruited_genomes.lst",'w')
else:
mumi_f = open(outputDir+os.sep+"recruited_genomes.lst",'w')
if VERBOSE:
print "RECRUITED GENOMES:\n"
sorted_x = sorted(mumi_dict.iteritems(), key=operator.itemgetter(1))
scnt = 0
mumivals = []
for item in sorted_x:
if scnt > 100 or scnt >= len(sorted_x):
break
if float(item[1]) < float(mumidistance):
mumivals.append(float(item[1]))
scnt +=1
minv=1.0
if len(mumivals) > 0:
minv = numpy.percentile(mumivals,0)
dvals = mumivals
stdv = 0
hpv = 0
if len(dvals) > 0:
stdv = numpy.std(dvals)
hpv = minv+(3*stdv)
for idx in mumi_dict.keys():
if mumi_dict[idx] < (float(mumidistance)) or curated:
if fastmum and mumi_dict[idx] > hpv:
continue
if 1 or auto_ref != fnafiles[idx]:
if mumi_only:
mumi_f.write(os.path.abspath(seqdir+os.sep+fnafiles[idx])+",%f"%(mumi_dict[idx])+"\n")
if VERBOSE:
print "\t"+fnafiles[idx]
finalfiles.append(fnafiles[idx])
allfiles.append(fnafiles[idx])
if VERBOSE:
print
if curated:
for file in fnafiles:
if file not in finalfiles:
finalfiles.append(file)
if file not in allfiles:
allfiles.append(file)
if mumi_only:
mumi_f.close()
sys.exit(1)
orig_auto_ref = auto_ref
if os.path.exists(auto_ref) and autopick_ref:
ff = open(auto_ref,'r')
seqs = ff.read().split(">")[1:]
seq_dict = {}
seq_len = {}
for seq in seqs:
hdr = ""
nt = ""
try:
hdr,nt = seq.split("\n",1)
except ValueError:
continue
seq_dict[hdr] = nt
seq_len[hdr] = len(nt.replace("\n",""))
seq_len_sort = sorted(seq_len.iteritems(), key=operator.itemgetter(1))
seq_len_sort.reverse()
ffo = open("%s"%(outputDir+os.sep+auto_ref.split(os.sep)[-1]+".ref"),'w')
for item in seq_len_sort:
ffo.write(">%s\n"%(item[0]))
ffo.write("%s"%(seq_dict[item[0]]))
ff.close()
ffo.close()
auto_ref = outputDir+os.sep+auto_ref.split(os.sep)[-1]+".ref"
ref = auto_ref
#print ref
#print ref
inifiled_closest = inifiled
if not inifile_exists:
if len(finalfiles) < 1 or ref == "":
sys.stderr.write( "ERROR: Parsnp requires 2 or more genomes to run, exiting\n")
sys.exit(0)
file_string = ""
cnt = 1
file_string_closest = ""
for file in finalfiles[0:1]:
file_string_closest+="file%d=%s\n"%(cnt,seqdir+os.sep+file)
file_string_closest+="reverse%d=0\n"%(cnt)
cnt +=1
cnt = 1
for file in finalfiles:
file_string+="file%d=%s\n"%(cnt,seqdir+os.sep+file)
file_string+="reverse%d=0\n"%(cnt)
cnt +=1
inifiled = inifiled.replace("$FILES\n",file_string)
#new, output unaligned regions
inifiled = inifiled.replace("$UNALIGNED",unaligned)
inifiled_closest = inifiled.replace("$FILES\n",file_string_closest)
if fastmum:
inifiled = inifiled.replace("p=%d"%(0.2*reflen),"p=%s"%(maxpartition))
inifiled_closest = inifiled.replace("p=%d"%(0.2*reflen),"p=%s"%(maxpartition))
if autopick_ref:
inifiled = inifiled.replace(orig_auto_ref,auto_ref)
inifiled = inifiled.replace(auto_ref,"tmp_"+auto_ref)
inifiled = inifiled.replace(query,auto_ref)
inifiled = inifiled.replace("tmp_"+auto_ref,query)
inifiled_closest = inifiled_closest.replace(auto_ref,"tmp_"+auto_ref)
inifiled_closest = inifiled_closest.replace(query,auto_ref)
inifiled_closest = inifiled_closest.replace("tmp_"+auto_ref,query)
inifile = open(outputDir+os.sep+"parsnpAligner.ini",'w')
inifile.write(inifiled)
inifile.close()
inifile_closest = open(outputDir+os.sep+"psnn.ini",'w')
inifile_closest.write(inifiled_closest)
inifile_closest.close()
#3)run parsnp (cores, grid?)
print "-->Running Parsnp multi-MUM search and libMUSCLE aligner.."
if not os.path.exists(outputDir+os.sep+"blocks"):
os.mkdir(outputDir+os.sep+"blocks")
command = ""
run_parsnp = 1
if run_parsnp:
successful_run = False
maxruns = 2
runcnt = 0
while not successful_run:
if not inifile_exists:
if command == "" and xtrafast and 0:
command = "%s/parsnpA_fast %sparsnpAligner.ini"%(PARSNP_DIR,outputDir+os.sep)
elif command == "":
command = "/usr/lib/parsnp/parsnp %sparsnpAligner.ini"%(outputDir+os.sep)
else:
command = "/usr/lib/parsnp/parsnp %spsnn.ini"%(outputDir+os.sep)
else:
if not os.path.exists(inifile):
sys.stderr.write("Error: ini file %s does not exist!\n"%(inifile))
sys.exit(1)
command = "/usr/lib/parsnp/parsnp %s"%(inifile)
run_command(command)
if not os.path.exists(outputDir+os.sep+"parsnpAligner.xmfa"):
successful_run = False
runcnt +=1
if runcnt >= 2:
sys.stderr.write("Error: set of recruited genomes are too divergent for parsnp, please reduce MUMi (%f) and relaunch\n"%(float(mumidistance)))
sys.exit(1)
else:
successful_run = True
runcnt +=1
break
os.system("mv "+outputDir+os.sep+"parsnpAligner.xmfa "+outputDir+os.sep+"parsnp.xmfa")
xmfafile = open(outputDir+os.sep+"parsnp.xmfa",'r')
file2hdr_dict = {}
fileid = ""
blockfiles = []
#get coverage
coverage = 0
totlength = 0
totseqs = 0
try:
cf = open("%sparsnpAligner.log"%(outputDir+os.sep))
for line in cf.xreadlines():
if "Total coverage among all sequences:" in line:
coverage = line.split(":",1)[-1].replace("\n","")
coverage = float(coverage.replace("%",""))/100.0
elif "Length:" in line:
totlength += int(line.split(":",1)[-1].replace("\n","").split("bps")[0])
totseqs +=1
except IOError:
print ERROR_RED+"parsnpAligner.log missing, parsnpAligner failed, exiting.."+ENDC
sys.exit(1)
#update thresholds
if coverage <= 0.01:
sys.stderr.write( " |->["+ERROR_RED+"ERROR"+ENDC+"]"+": aligned regions cover less than 1% of reference genome, something is not right.. please adjust params and rerun. If problem persists please contact developers (treangen@gmail.com)"+ENDC)
sys.exit(1)
elif coverage < 0.1:
sys.stderr.write( " |->["+WARNING_YELLOW+"WARNING"+ENDC+"]"+": aligned regions cover less than 10% of reference genome! please verify recruited genomes are all strain of interest"+ENDC)
else:
pass
print " |->["+OK_GREEN+"OK"+ENDC+"]"
t2 = time.time()
elapsed = float(t2)-float(t1)
#print "-->Getting list of LCBs.."
allbfiles = glob.glob(outputDir+os.sep+"blocks/b*/*")
blockfiles = []
icnt = 0
block_startpos = []
block_dict = {}
for file in allbfiles:
if os.path.isfile(file):
if "seq.fna" in file:
blockfiles.append(file)
lf = open(file,'r')
header = lf.readline()
if header[0] != ">":
sys.stderr.write( "Error with LCB: %s\n"%(file))
continue
inf = header.split("+",1)[0]
rseq = ""
while 1:
lff = lf.readline()
if lff[0] == ">":
break
rseq += lff.replace("\n","")
spos,epos = inf.split(":",1)[-1].split("-",1)
block_startpos.append(int(spos))
block_dict[file] = [int(spos),int(epos), rseq]
lf.close()
run_repeat_filter = filtreps
#initiate parallelPhiPack tasks
run_recomb_filter = 0
if xtrafast:
run_recomb_filter = 1
else:
run_recomb_filter = 0
recombination_sites = {}
bedfile = ""
bedfile_dict = {}
print "-->Running PhiPack on LCBs to detect recombination.."
if run_recomb_filter and len(blockfiles) > 0:
bedfile = open("%s/parsnp.rec"%(outputDir),'w')
tasks = []
processed = []
icnt = 0
for file in blockfiles:
seq1 = ""
try:
bf = open(file,'r')
seq1 = bf.read().split(">")[1].split("\n",1)[-1]
seq1 = seq1.replace("\n","")
bf.close()
except IOError:
pass
processed.append(file)
params = {}
path,file = file.rsplit(os.sep,1)
params["jobID"] = len(tasks)
params["query"] = "%s"%(file)
params["seqlen"] = len(seq1)
params["spos"] = block_startpos[icnt]
params["dir"] = "%s"%(path)
params["output"] = "%sProfile.csv"%(path+os.sep)#(path+os.sep+file+".out")
tasks.append(params)
icnt +=1
#run parallelPhiPack
pool = Pool(processes=int(threads))
result = pool.map_async(parallelPhiWrapper,tasks).get(sys.maxint)
for i in result:
if (i["status"] == 1):
#process output
recregions = ""
block_spos = tasks[i["jobID"]]["spos"]
try:
recregions = open(tasks[i["jobID"]]["output"],'r').read()
except IOError:
if VERBOSE:
sys.stderr.write( "File %s doesn't exist, no rec regions or error in PhiPack\n"%(tasks[i["jobID"]]["output"]))
continue
reclines = recregions.split("\n")
prevpos = 0
for line in reclines:
try:
pos,eval = line.split(",")
except ValueError:
continue
pos = int(pos)
eval = float("%.5f"%(float(eval)))
if eval < 0.01 and eval >= 0:
idx = 0
srpos = 0
if pos-50 > 0:
srpos = (pos-50)+block_spos
else:
srpos = block_spos
eval = abs(eval)
if not multifasta:
bedfile_dict[srpos] = "1\t%s\t%s\tREC\t%.3f\t+\n"%(srpos,pos+50+block_spos,eval)
else:
chrnum = 1
chr_spos = ref_seqs.keys()
for cs in chr_spos:
if block_spos < chr_spos:
chrnum = ref_seqs[cs]
bedfile_dict[srpos] = "%d\t%s\t%s\tREC\t%.3f\t+\n"%(chrnum,srpos,pos+50+block_spos,eval)
qfile = tasks[i["jobID"]]["query"]
elif i["status"] != 2:
sys.stderr.write( "Error: parallel phipack job %d failed\n"%(i["jobID"]))
raise IOError
pool.close()
pool.join()
brkeys = bedfile_dict.keys()
brkeys.sort()
for key in brkeys:
bedfile.write(bedfile_dict[key])
bedfile.close()
if run_recomb_filter:
sys.stderr.write(" |->["+OK_GREEN+"OK"+ENDC+"]\n")
else:
sys.stderr.write(" |->["+SKIP_GRAY+"SKIP"+ENDC+"]\n")
run_lcb_trees = 0
annotation_dict = {}
if xtrafast or 1:
#add genbank here, if present
if len(genbank_ref) != 0:
rnc = "harvesttools -q -o %s/parsnp.ggr -x "%(outputDir)+outputDir+os.sep+"parsnp.xmfa"
for file in genbank_files:
rnc += " -g %s " %(file)
run_command(rnc)
else:
run_command("harvesttools -q -o %s/parsnp.ggr -f %s -x "%(outputDir,ref)+outputDir+os.sep+"parsnp.xmfa")
if run_recomb_filter:
run_command("harvesttools -q -b %s/parsnp.rec,REC,\"PhiPack\" -o %s/parsnp.ggr -i %s/parsnp.ggr"%(outputDir,outputDir,outputDir))
if run_repeat_filter:
run_command("harvesttools -q -b %s,REP,\"Intragenomic repeats > 100bp\" -o %s/parsnp.ggr -i %s/parsnp.ggr"%(repfile,outputDir,outputDir))
run_command("harvesttools -q -i %s/parsnp.ggr -S "%(outputDir)+outputDir+os.sep+"parsnp.snps.mblocks")
command = "fasttree -nt -quote -gamma -slow -boot 100 "+outputDir+os.sep+"parsnp.snps.mblocks > "+outputDir+os.sep+"parsnp.tree"
print "-->Reconstructing core genome phylogeny.."
run_command(command)
#7)reroot to midpoint
if os.path.exists("outtree"):
os.system("rm outtree")
if reroot_tree and len(finalfiles) > 1:
#print "-->Midpoint reroot.."
try:
mtree = open("%sparsnp.tree"%(outputDir+os.sep), 'r')
mtreedata = mtree.read()
mtreedata.replace("\n","")
tree = dendropy.Tree.get_from_string(mtreedata,"newick")
tree.reroot_at_midpoint(update_splits=False)
mftreef = tree.as_string('newick').split(" ",1)[1]
#print mftreef
mtreef = open(outputDir+os.sep+"parsnp.final.tree",'w')
mtreef.write(mftreef)
mtreef.close()
os.system("mv %s %s"%(outputDir+os.sep+"parsnp.final.tree",outputDir+os.sep+"parsnp.tree"))
except IOError:
sys.stderr.write( "ERROR: cannot process fasttree output, skipping midpoint reroot..\n")
print " |->["+OK_GREEN+"OK"+ENDC+"]"
if 1 or len(use_gingr) > 0:
print "-->Creating Gingr input file.."
if xtrafast or 1:
#if newick available, add
#new flag to update branch lengths
run_command("harvesttools --midpoint-reroot -u -q -i "+outputDir+os.sep+"parsnp.ggr -o "+outputDir+os.sep+"parsnp.ggr -n %s"%(outputDir+os.sep+"parsnp.tree "))
print " |->["+OK_GREEN+"OK"+ENDC+"]"
print "-->Calculating wall clock time.. "
if float(elapsed)/float(60.0) > 60:
print " |->"+BOLDME+"Aligned %d genomes in %.2f hours"%(totseqs,float(elapsed)/float(3600.0))+ENDC
elif float(elapsed) > 60:
print " |->"+BOLDME+"Aligned %d genomes in %.2f minutes"%(totseqs,float(elapsed)/float(60.0))+ENDC
else:
print " |->"+BOLDME+"Aligned %d genomes in %.2f seconds"%(totseqs,float(elapsed))+ENDC
#cleanup
rmfiles = glob.glob(outputDir+os.sep+"*.aln")
#rmfiles2 = glob.glob(outputDir+os.sep+"blocks/b*/*")
rmfiles3 = glob.glob(outputDir+os.sep+"blocks/b*")
for file in rmfiles:
os.system("rm %s"%(file))
for file in rmfiles3:
os.system("rm -rf %s"%(file))
filepres = 0
print BOLDME+"\n<<Parsnp finished! All output available in %s>>"%(outputDir)+ENDC
print
print BOLDME+"Validating output directory contents..."+ENDC
print BOLDME+"\t1)parsnp.tree:\t\tnewick format tree"+ENDC,
if os.path.exists("%sparsnp.tree"%(outputDir+os.sep)) and os.path.getsize("%sparsnp.tree"%(outputDir+os.sep)) > 0:
print "\t\t\t["+OK_GREEN+"OK"+ENDC+"]"
filepres+=1
else:
print "\t|->"+ERROR_RED+"MISSING"+ENDC
print BOLDME+"\t2)parsnp.ggr:\t\tharvest input file for gingr (GUI)"+ENDC,
if os.path.exists("%sparsnp.ggr"%(outputDir+os.sep)) and os.path.getsize("%sparsnp.ggr"%(outputDir+os.sep)) > 0:
print "\t["+OK_GREEN+"OK"+ENDC+"]"
filepres+=1
else:
print "\t|->"+ERROR_RED+"MISSING"+ENDC
print BOLDME+"\t3)parsnp.xmfa:\t\tXMFA formatted multi-alignment"+ENDC,
if os.path.exists("%sparsnp.xmfa"%(outputDir+os.sep)) and os.path.getsize("%sparsnp.xmfa"%(outputDir+os.sep)) > 0:
print "\t\t["+OK_GREEN+"OK"+ENDC+"]"
filepres+=1
else:
print "\t|->"+ERROR_RED+"MISSING"+ENDC
if filepres == 3:
pass
else:
print "\t\t["+ERROR_RED+"Output files missing, something went wrong. Check logs and relaunch or contact developers for assistance"+ENDC+"]"
print
if os.path.exists("%sblocks"%(outputDir+os.sep)):
os.rmdir("%sblocks"%(outputDir+os.sep))
if os.path.exists("allmums.out"):
os.remove("allmums.out")
if not VERBOSE and os.path.exists("parsnpAligner.ini"):
os.remove("parsnpAligner.ini")
prefix = outputDir+os.sep+ref.rsplit(".",1)[0].rsplit(os.sep)[-1]
if not VERBOSE and os.path.exists("%s.coords"%(prefix)):
os.remove("%s.coords"%(prefix))
if not VERBOSE and os.path.exists("%s.delta"%(prefix)):
os.remove("%s.delta"%(prefix))
files = glob.glob("%s/*.reps"%(outputDir))
for file in files:
if not VERBOSE and os.path.exists(file):
os.remove(file)
files = glob.glob("%s/*.ref"%(outputDir))
for file in files:
if not VERBOSE and os.path.exists(file):
os.remove(file)
if not VERBOSE and os.path.exists("%s/psnn.ini"%(outputDir)):
os.remove("%s/psnn.ini"%(outputDir))
if not VERBOSE and os.path.exists("%s/all_mumi.ini"%(outputDir)):
os.remove("%s/all_mumi.ini"%(outputDir))
if os.path.exists("%s/parsnp.snps.mblocks"%(outputDir)):
os.remove("%s/parsnp.snps.mblocks"%(outputDir))
if not VERBOSE and os.path.exists("%s/all.mumi"%(outputDir)):
os.remove("%s/all.mumi"%(outputDir))
if os.path.exists(use_gingr):
#check if available first
rc = 0
if binary_type == "osx":
print ">>Launching gingr.."
os.system("open -n %s --args %s/parsnp.ggr"%(use_gingr,outputDir))
|