return results_dict
############################################
#Main Block
############################################
starttime = gc.getLogTime()
indir, orig_targets, pairwise, prob_thresh, num_threads, output = optParse()
if platform.system() == "Windows" and num_threads != 1:
print "\n** Warning! Multi-processing not currently supported on Windows. Switching to serial version (1 process).\n"
num_threads = 1
outdir = gc.defaultOut(output, indir, "-gwct")
print gc.getTime() + " | + Creating main output directory:\t" + outdir
os.system("mkdir " + outdir)
ancdir = os.path.join(indir, "anc-seqs-fa")
if not os.path.isdir(ancdir):
ancdir = os.path.join(indir, "anc_seqs_fa")
if not os.path.isdir(ancdir):
sys.exit(
gc.errorOut(
9, "Cannot find anc-seqs-fa directory within input directory."))
filelist = os.listdir(ancdir)
filelist = [f for f in filelist if "ancprobs" in f]
num_files = len(filelist)
if prob_thresh == 0:
convfilename = os.path.join(outdir, "conv-sites.txt")
divfilename = os.path.join(outdir, "div-sites.txt")
indir = os.path.dirname(os.path.realpath(ins));
indir, script_outdir = gwctcore.getOutdir(indir, "run_codeml", starttime, outdir_suffix);
outdir = os.path.join(script_outdir, "codeml_out");
if aopt == 1:
ancdir = os.path.join(script_outdir, "anc_seqs_fa");
filelist = [ins];
else:
fileflag = 0;
indir, script_outdir = gwctcore.getOutdir(ins, "run_codeml", starttime, outdir_suffix);
outdir = os.path.join(script_outdir, "codeml_out");
filelist = os.listdir(indir);
if aopt == 1:
ancdir = os.path.join(script_outdir, "anc_seqs_fa");
print gwctcore.getTime() + " | Creating main output directory:\t" + script_outdir;
os.system("mkdir " + script_outdir);
logfilename = os.path.join(script_outdir, "run_codeml.log");
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
gwctcore.logCheck(l, logfilename, "=======================================================================");
gwctcore.logCheck(l, logfilename, "\t\t\tRunning codeml");
gwctcore.logCheck(l, logfilename, "\t\t\t" + gwctcore.getDateTime());
if fileflag == 1:
gwctcore.logCheck(l, logfilename, "INPUT | Making tree from file:\t\t" + ins);
else:
gwctcore.logCheck(l, logfilename, "INPUT | Running codeml on all files in:\t" + indir);
gwctcore.logCheck(l, logfilename, "INFO | PAML path set to:\t\t\t" + ppath);
elif errorflag == 1:
parser.print_help();
sys.exit();
############################################
#Main Block
############################################
starttime = gwctcore.getLogTime();
indir, targets, suffix = optParse(0);
targets = targets.split(",");
indir, script_outdir = gwctcore.getOutdir(indir, "gwct", starttime, suffix);
print "# " + gwctcore.getTime() + " | Creating main output directory:\t" + script_outdir;
os.system("mkdir " + script_outdir);
logfilename = os.path.join(script_outdir, "gwct.log");
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
uniq_header = "#\tChromosome\tGeneID\tAlignLen\tPosition\tBackgroundAlleles\tTargetAlleles\n";
l = 1;
sp = 65;
gwctcore.logCheck(l, logfilename, "# =======================================================================");
gwctcore.logCheck(l, logfilename, "#\tGWCT: Genome-Wide Convergence Tester -- Unique substitutions");
gwctcore.logCheck(l, logfilename, "#\t\t\t" + gwctcore.getDateTime());
gwctcore.logCheck(l, logfilename, gwctcore.spacedOut("# INPUT | Using sequences in:", sp) + indir);
gwctcore.logCheck(l, logfilename, gwctcore.spacedOut("# INPUT | Target species:", sp) + ",".join(targets));
print indir;
inslist = os.listdir(indir);
if unique != 1:
for each in inslist:
if each.find("run_codeml") != -1 or each.find("codeml_combined") != -1:
#indir = indir + each + "/anc_seqs_fa/";
indir = os.path.join(indir, each, "anc_seqs_fa");
orig_filelist = os.listdir(indir);
filelist = [f for f in orig_filelist if f.find("ancprobs") != -1];
num_files = len(filelist);
break;
elif unique == 1:
filelist = os.listdir(indir);
num_files = len(filelist);
print gwctcore.getTime() + " | Creating main output directory:\t" + script_outdir;
os.system("mkdir " + script_outdir);
logfilename = os.path.join(script_outdir, "gwct.log");
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
main_header = "# Chromosome\tGeneID\tAlignLen\tPosition\tAncAlleles\tTargetAlleles\n";
uniq_header = "# Chromosome\tGeneID\tAlignLen\tPosition\tBackgroundAlleles\tTargetAlleles\n";
l = 1;
sp = 65;
gwctcore.logCheck(l, logfilename, "# =======================================================================");
gwctcore.logCheck(l, logfilename, "#\t\tGWCT: Genome-Wide Convergence Tester");
gwctcore.logCheck(l, logfilename, "#\t\t\t" + gwctcore.getDateTime());
gwctcore.logCheck(l, logfilename, gwctcore.spacedOut("# INPUT | Using ancestral reconstructions in:", sp) + indir);
indir, path, treefile, prune, v, output = optParse();
# Get input options.
file_flag = 0;
outdir = gc.defaultOut(output, indir, "-gwct-codeml");
print "+ Creating main output directory:\t" + outdir;
os.system("mkdir " + outdir);
codemldir = os.path.join(outdir, "codeml-out");
ancdir = os.path.join(outdir, "anc-seqs-fa");
logfilename = os.path.join(outdir, "gwct-codeml.log");
# Set output file and directory info.
gc.printWrite(logfilename, "Program call: " + " ".join(sys.argv));
pad = 50;
print gc.spacedOut(gc.getTime() + " | Creating main output directory:", pad) + outdir;
os.system("mkdir " + outdir);
gc.printWrite(logfilename, "=======================================================================");
gc.printWrite(logfilename, "\tRunning codeml to reconstruct ancestral sequences");
gc.printWrite(logfilename, "\t\t\t" + gc.getDateTime());
gc.printWrite(logfilename, gc.spacedOut("Input directory (-i):", pad) + indir);
gc.printWrite(logfilename, gc.spacedOut("PAML path (-p):", pad) + path);
if treefile != "":
gc.printWrite(logfilename, gc.spacedOut("Tree file (-t):", pad) + treefile);
else:
gc.printWrite(logfilename, gc.spacedOut("No tree file specified (-t):", pad) + "codeml will infer a tree for each gene.");
if prune:
gc.printWrite(logfilename, gc.spacedOut("--prune set", pad) + "Pruning the tree for each gene.");
# if seqtype == 'codon':
# gc.printWrite(logfilename, gc.spacedOut("INFO | Seqtype set to:", pad) + "codons");
# if seqtype == 'aa':
elif errorflag == 1:
parser.print_help()
sys.exit()
############################################
#Main Block
############################################
starttime = gwctcore.getLogTime()
indir, targets, suffix = optParse(0)
targets = targets.split(",")
indir, script_outdir = gwctcore.getOutdir(indir, "gwct", starttime, suffix)
print "# " + gwctcore.getTime(
) + " | Creating main output directory:\t" + script_outdir
os.system("mkdir " + script_outdir)
logfilename = os.path.join(script_outdir, "gwct.log")
logfile = open(logfilename, "w")
logfile.write("")
logfile.close()
uniq_header = "#\tChromosome\tGeneID\tAlignLen\tPosition\tBackgroundAlleles\tTargetAlleles\n"
l = 1
sp = 65
gwctcore.logCheck(
l, logfilename,
"# ======================================================================="
)
gwctcore.logCheck(
print indir
inslist = os.listdir(indir)
if unique != 1:
for each in inslist:
if each.find("run_codeml") != -1 or each.find("codeml_combined") != -1:
#indir = indir + each + "/anc_seqs_fa/";
indir = os.path.join(indir, each, "anc_seqs_fa")
orig_filelist = os.listdir(indir)
filelist = [f for f in orig_filelist if f.find("ancprobs") != -1]
num_files = len(filelist)
break
elif unique == 1:
filelist = os.listdir(indir)
num_files = len(filelist)
print gwctcore.getTime(
) + " | Creating main output directory:\t" + script_outdir
os.system("mkdir " + script_outdir)
logfilename = os.path.join(script_outdir, "gwct.log")
logfile = open(logfilename, "w")
logfile.write("")
logfile.close()
main_header = "# Chromosome\tGeneID\tAlignLen\tPosition\tAncAlleles\tTargetAlleles\n"
uniq_header = "# Chromosome\tGeneID\tAlignLen\tPosition\tBackgroundAlleles\tTargetAlleles\n"
l = 1
sp = 65
gwctcore.logCheck(
l, logfilename,
"# ======================================================================="
)