Ejemplo n.º 1
0
Archivo: gwct.py Proyecto: gwct/gwct
    gc.filePrep(divfilename, main_header)
    gc.filePrep(uniqfilename, uniq_header)

logfilename = os.path.join(outdir, "gwct.log")
gc.filePrep(logfilename, "")

sp = 65
gc.printWrite(
    logfilename,
    "# ======================================================================="
)
gc.printWrite(logfilename, "#\t\tGWCT: Genome-Wide Convergence Tester")
gc.printWrite(logfilename, "#\t\t\t" + gc.getDateTime())
gc.printWrite(
    logfilename,
    gc.spacedOut("# INPUT  | Using ancestral reconstructions in:", sp) + indir)
if orig_targets != "":
    orig_targets = [t.split(",") for t in orig_targets.split(" ")]
    gc.printWrite(
        logfilename,
        gc.spacedOut("# INFO   | Target species:", sp) + str(orig_targets))
elif pairwise == 1:
    pw_dir = outdir + "pairwise-tips/"
    pw_dir = os.path.join(outdir, "pairwise-tips")
    gc.printWrite(
        logfilename,
        "# INFO   | Performing pairwise comparisons of TIP branches")
elif pairwise == 2:
    pw_dir = os.path.join(outdir, "pairwise-all")
    gc.printWrite(
        logfilename,
Ejemplo n.º 2
0
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));
gwctcore.logCheck(l, logfilename, gwctcore.spacedOut("# OUTPUT | Output directory created within input directory:", sp) + script_outdir);
gwctcore.logCheck(l, logfilename, "# ---------------------------------------------");
gwctcore.logCheck(2, logfilename, uniq_header);
################################
print "# " + gwctcore.getTime() + " | Counting unique substitutions....";

filelist = os.listdir(indir);
numfiles = len(filelist);
numbars = 0;
donepercent = [];
i = 0;

numsubs = 0;
numgenes = 0;
Ejemplo n.º 3
0
Archivo: gwct.py Proyecto: gwct/gwct
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);
if orig_targets != "":
	orig_targets = orig_targets.split(" ");
	for t in xrange(len(orig_targets)):
		if orig_targets[t].find(",") != -1:
			orig_targets[t] = orig_targets[t].split(",");
	if prob_thresh == 0:
		convfilename = os.path.join(script_outdir, "conv_sites.txt");
		divfilename = os.path.join(script_outdir, "div_sites.txt");
	elif prob_thresh != 0:
		convfilename = os.path.join(script_outdir, "conv_sites_" + str(prob_thresh) + ".txt");
		divfilename = os.path.join(script_outdir, "div_sites_" + str(prob_thresh) + ".txt");
	gwctcore.filePrep(convfilename, main_header);
	gwctcore.filePrep(divfilename, main_header);
	gwctcore.logCheck(l, logfilename, gwctcore.spacedOut("# INFO   | Target species:", sp) + str(orig_targets));
	if unique == 1:
Ejemplo n.º 4
0
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':
Ejemplo n.º 5
0
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))
gwctcore.logCheck(
    l, logfilename,
    gwctcore.spacedOut(
        "# OUTPUT | Output directory created within input directory:", sp) +
    script_outdir)
gwctcore.logCheck(l, logfilename,
                  "# ---------------------------------------------")
gwctcore.logCheck(2, logfilename, uniq_header)
################################
print "# " + gwctcore.getTime() + " | Counting unique substitutions...."

filelist = os.listdir(indir)
Ejemplo n.º 6
0
Archivo: gwct.py Proyecto: gwct/gwct
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)
if orig_targets != "":
    orig_targets = orig_targets.split(" ")
    for t in xrange(len(orig_targets)):
        if orig_targets[t].find(",") != -1:
            orig_targets[t] = orig_targets[t].split(",")
    if prob_thresh == 0:
        convfilename = os.path.join(script_outdir, "conv_sites.txt")
        divfilename = os.path.join(script_outdir, "div_sites.txt")
    elif prob_thresh != 0:
        convfilename = os.path.join(script_outdir,
                                    "conv_sites_" + str(prob_thresh) + ".txt")
        divfilename = os.path.join(script_outdir,
                                   "div_sites_" + str(prob_thresh) + ".txt")
    gwctcore.filePrep(convfilename, main_header)