def archiveDo(bot, position):
if debug:
send(bot, "Suggestion moved to the archive. (not really)")
return # todo move bot to a test sheet
wks = auth()
now = getTime()
archiveNames = list(filter(fNonEmpty, map(fValue, wks.range('G4:G1300'))))
suggestionNames = list(filter(fNonEmpty, map(fValue, wks.range('B4:B100'))))
lastSuggestion = len(suggestionNames) + 4
archiveLastPosition = len(archiveNames) + 4
rolledCells = wks.range('B'+str(position)+':E'+ str(position))
rolled = list(map(fValue, rolledCells))
# move archive cells down 1 row
archiveOldCells = wks.range('F4:L'+str(archiveLastPosition+1))
lenArchiveOld = len(archiveOldCells)
for i in reversed(range(len(archiveOldCells))):
if lenArchiveOld > i + 7:
archiveOldCells[i+7].value = archiveOldCells[i].value
wks.update_cells(archiveOldCells)
# move suggestion to F4
archiveCells = wks.range('F4:L4')
archiveCells[0].value = now.strftime("%d %b %y")
archiveCells[1].value = rolled[0]
archiveCells[2].value = rolled[1]
archiveCells[3].value = rolled[2]
archiveCells[4].value = rolled[3]
archiveCells[5].value = ""
archiveCells[6].value = ""
wks.update_cells(archiveCells)
# move suggestions up 1 row
suggestionCells = wks.range('B'+str(position)+':E'+str(lastSuggestion))
lenSuggestionCells = len(suggestionCells)
for i in range(len(suggestionCells)):
if lenSuggestionCells > i + 4:
suggestionCells[i].value = suggestionCells[i+4].value
wks.update_cells(suggestionCells)
send(bot, "Suggestion moved to the archive.")
############################################
#Main Block
############################################
infiles, outfilename = optParse(0)
#print infiles, outfilename;
print "# ======================================================================="
print "# Combining files:\t\t\t", infiles
print "# Writing output to:\t\t\t" + outfilename
print "# Writing only possible one-to-one orthologs to output file."
print "# -------------------------------------"
print "# " + core.getTime() + " Reading files..."
file_lines = {}
key_ids = {}
for each in infiles:
infile = open(each, "r")
inlines = infile.readlines()
infile.close()
file_lines[each] = []
key_ids[each] = []
i = 0
for line in inlines:
if i == 0:
if script_outdir_initial != None:
if not os.path.isdir(script_outdir_initial):
core.errorOut(8, "-z must be a valid directory")
optParse(1)
script_outdir = os.path.join(
script_outdir_initial,
os.path.basename(os.path.normpath(script_outdir)))
if outdir_suffix != None:
if script_outdir[-1] == "/":
script_outdir = script_outdir[:len(script_outdir) -
1] + "-" + outdir_suffix + "/"
else:
script_outdir = script_outdir + "-" + outdir_suffix + "/"
print core.getTime() + " | Creating main output directory:\t" + script_outdir
os.system("mkdir '" + script_outdir + "'")
logfilename = script_outdir + "supertreemaker.log"
logfile = open(logfilename, "w")
logfile.write("")
logfile.close()
##Pre-run prep: creating log files and output directories, etc...
core.logCheck(
l, logfilename,
"=======================================================================")
core.logCheck(l, logfilename,
"\tSupertree making with SDM, R, newickutils, and r8s")
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime())
core.logCheck(l, logfilename,
infilename, seqdir, speclist, remstart, outdir = optParse(0)
print "# ======================================================================="
print "# \t\t\tRetrieving sequences in FASTA format"
print "# \t\t\t" + core.getDateTime()
print "# Retrieving ortholog sequences from:\t", infilename
print "# Sequence directory\t\t\t" + seqdir
print "# Writing combined sequence files to:\t", outdir
if remstart == 1:
print "# Removing start Methionines (-m 1)"
else:
print "# NOT removing start Methionines (-m 0)"
print "# Reminder: Please ensure your species dictionary was entered correctly."
print "# Note: The script will skip any lines that do not have all species."
print "# -------------------------------------"
print "# " + core.getTime() + " Preparing species dictionary..."
specdict = {}
for each in speclist:
current = each.split(":")
specdict[current[0]] = current[1]
#print specdict;
print "# -------------------------------------"
print "# " + core.getTime(
) + " Reading peptide source files and extracting protein IDs..."
tmp_seq_dict = {}
for spec in specdict:
tmp_seq_dict[spec] = core.fastaGetDict(os.path.join(
seqdir, specdict[spec]))
def convCheck(cur_c, c, ropt, targets, backgrounds, d, ins, outs):
# cur_c = 0;
init_c = cur_c + 1
while cur_c < c:
#if c > 1:
if ropt != 0:
outfilename = outs + "_" + str(cur_c + 1) + ".txt"
else:
outfilename = outs + ".txt"
if ropt != 0:
#backgrounds = ["hg19", "rheMac3", "calJac3", "mm10", "rn5", "vicPac2", "bosTau7", "canFam3", "loxAfr3", "papHam1", "monDom5"];
backgrounds = []
cur_r = len(backgrounds)
while cur_r < ropt:
chosenspec = random.choice(all_specs.values())
if chosenspec not in targets and chosenspec not in backgrounds:
backgrounds.append(chosenspec)
cur_r = cur_r + 1
outfile = open(outfilename, "w")
outfile.write(
"# ==============================================================================================\n"
)
outfile.write("# \t\t\tConvergence testing\n")
outfile.write("# \t\t\t" + core.getDateTime() + "\n")
outfile.write("# Using alignments in:\t\t" + indir + "\n")
outfile.write("# Target species:\t\t\t" + ", ".join(targets) + "\n")
if ropt != 0:
outfile.write("# Randomly choosing " + str(r) +
" background species and performing " + str(c) +
" replicate tests for convergence.\n")
outfile.write("# This is replicate number " + str(cur_c + 1) +
"\n")
outfile.write("# Background species:\t\t" + ", ".join(backgrounds) +
"\n")
outfile.write("# Writing output to:\t\t\t" + outfilename + "\n")
if d == 0:
outfile.write("# Checking for convergent sites.\n")
elif d == 1:
outfile.write("# Checking for divergent sites.\n")
outfile.write("# ---------------------------------------------\n")
#sys.exit();
#cur_c = cur_c + 1;
#continue;
aligns = os.listdir(ins)
numbars = 0
donepercent = []
count = len(aligns)
i = 0
numsites = 0
totgenes = 0
outfile.write("# " + core.getTime() + " Starting Scan...\n")
outfile.write(
"# Site#\tChromosome\tGeneID\tAlignLen\tPosition\tTargetAlleles\tBackgroundAlleles\n"
)
for align in aligns:
#numbars, donepercent = core.loadingBar(i, count, donepercent, numbars);
i = i + 1
if align.find(".fa") == -1:
continue
#if i > 25:
# break;
infilename = ins + align
#print align;
gid = "_".join(align.split("_")[:2])
chrome = align[align.find("chr"):align.find("chr") + 4]
inseqs = core.fastaGetDict(infilename)
num_targets_present = 0
num_bg_present = 0
for title in inseqs:
if any(t in title for t in targets):
num_targets_present = num_targets_present + 1
if any(b in title for b in backgrounds):
num_bg_present = num_bg_present + 1
if num_targets_present == len(targets) and num_bg_present == len(
backgrounds):
#print "The following gene has all target and background species and will be checked:\t\t" + gid;
totgenes = totgenes + 1
seqlen = len(inseqs[inseqs.keys()[0]])
#print "Alignment length\t\t", seqlen;
t_alleles = {}
b_alleles = {}
for x in xrange(len(inseqs[inseqs.keys()[0]])):
for title in inseqs:
for t in targets:
if t in title:
t_alleles[t] = inseqs[title][x]
for b in backgrounds:
if b in title:
b_alleles[b] = inseqs[title][x]
t_states = t_alleles.values()
t_gap = t_states.count("-")
t_missing = t_states.count("X")
t_stop = t_states.count("*")
b_states = b_alleles.values()
b_gap = b_states.count("-")
b_missing = b_states.count("X")
b_stop = b_states.count("*")
t_final = remGapMiss(t_states)
b_final = remGapMiss(b_states)
#print t_alleles;
#print t_states;
#print t_gap;
#print t_missing;
#print t_stop;
#print t_final;
#print b_alleles;
#print b_states;
#print b_gap;
#print b_missing;
#print b_stop;
#print b_final;
if t_final == [] or b_final == []:
continue
if d == 0:
if len(t_final) == len(targets) and len(
b_final) == len(backgrounds) and t_final.count(
t_final[0]) == len(
t_final) and t_final[0] not in b_final:
numsites = numsites + 1
#print core.getTime() + " Convergent site found!";
#print "Filename:\t\t" + align;
#print "Chromosome:\t\t" + chrome;
#print "Gene ID:\t\t" + gid;
#print "Alignment length\t", seqlen;
#print "Target alleles:\t\t" + "".join(t_final);
#print "Background alleles:\t" + "".join(b_final);
#print "---------------";
outline = str(
numsites
) + "\t" + chrome + "\t" + gid + "\t" + str(
seqlen) + "\t" + str(x + 1) + "\t" + "".join(
t_final) + "\t" + "".join(b_final) + "\n"
outfile.write(outline)
#sys.exit();
elif d == 1:
if len(t_final) == len(targets) and len(
b_final
) == len(backgrounds) and t_final.count(
t_final[0]) != len(t_final) and b_final.count(
b_final[0]) == len(b_final):
if not any(t in b_final for t in t_final):
numsites = numsites + 1
#print "\nDivergent site found!";
#print "Filename:\t\t" + align;
#print "Chromosome:\t\t" + chrome;
#print "Gene ID:\t\t" + gid;
#print "Alignment length\t", seqlen;
#print t_final;
#print b_final;
outline = str(
numsites
) + "\t" + chrome + "\t" + gid + "\t" + str(
seqlen
) + "\t" + str(x + 1) + "\t" + "".join(
t_final) + "\t" + "".join(b_final) + "\n"
outfile.write(outline)
#pstring = "100.0% complete.";
#sys.stderr.write('\b' * len(pstring) + pstring);
outfile.write("\n# " + core.getTime() + " Done!\n")
outfile.write("# Total sites found: " + str(numsites) + "\n")
outfile.write("# Total genes checked: " + str(totgenes) + "\n")
outfile.write(
"# =============================================================================================="
)
cur_c = cur_c + 1
if ropt != 0:
print core.getTime() + " Replicates", init_c, "to", c, "complete."
i = i + 1;
if each.find(".fa") == -1:
continue;
specpos = 0;
infilename = ins + each;
inseqs = core.fastaGetDict(infilename);
for seq in inseqs:
tot_pos = tot_pos + len(inseqs[seq]);
if disp_file == 1:
specpos = specpos + len(inseqs[seq]);
print seq + "\t" + str(len(inseqs[seq]));
if disp_file == 1:
print "Total\t" + str(specpos);
if disp_file == 0:
pstring = "100.0% complete.";
sys.stderr.write('\b' * len(pstring) + pstring);
elif disp_file == 1:
print "----------";
print "\n" + core.getTime() + " Done!";
print "-----";
print "Total residues:\t", tot_pos;
print "=======================================================================";
ins, gb_path, seqtype, m, v, l = optParse(0)
starttime = core.getLogTime()
if os.path.isfile(ins):
fileflag = 1
indir = os.path.dirname(os.path.realpath(ins)) + "/"
indir, outdir = core.getOutdir(indir, "run_gblocks", starttime)
filelist = [ins]
else:
fileflag = 0
indir, outdir = core.getOutdir(ins, "run_gblocks", starttime)
filelist = os.listdir(indir)
print core.getTime() + " | Creating main output directory..."
os.system("mkdir " + outdir)
logfilename = outdir + "run_gblocks.log"
logfile = open(logfilename, "w")
logfile.write("")
logfile.close()
core.logCheck(
l, logfilename,
"=======================================================================")
core.logCheck(l, logfilename, "\t\t\tMasking alignments with GBlocks")
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime())
if fileflag == 1:
core.logCheck(l, logfilename,
"INPUT | Masking alignment from file: " + ins)
elif rep != "" and rep[1] == ":":
print "INFO | Replacing all " + rep[0] + " symbols in input sequences with a random AA symbol not present in that column.";
suffix = suffix + ".r";
if os.path.isfile(ins):
print "OUTPUT | Writing output to the following file:\t\t" + outs;
else:
if outs[len(outs)-1] != "/":
outs = outs + "/";
print "OUTPUT | Writing output to the following directory:\t\t" + outs;
if not os.path.exists(outs):
print "+Creating output directory.";
os.system("mkdir " + outs);
print "---------------------------------------------";
#sys.exit();
print core.getTime() + " Starting...";
numfiles = len(filelist);
numbars = 0;
donepercent = [];
i = 0;
for each in filelist:
if each.find(".fa") == -1:
continue;
if os.path.isfile(ins):
print ins;
infilename = ins;
outfilename = outs;
indir, script_outdir = core.getOutdir(indir, "supertreemaker", starttime);
print script_outdir;
print os.path.basename(os.path.normpath(script_outdir));
if script_outdir_initial != None:
if not os.path.isdir(script_outdir_initial):
core.errorOut(8, "-z must be a valid directory");
optParse(1);
script_outdir = os.path.join(script_outdir_initial, os.path.basename(os.path.normpath(script_outdir)));
if outdir_suffix != None:
if script_outdir[-1] == "/":
script_outdir = script_outdir[:len(script_outdir)-1] + "-" + outdir_suffix + "/";
else:
script_outdir = script_outdir + "-" + outdir_suffix + "/";
print core.getTime() + " | Creating main output directory:\t" + script_outdir;
os.system("mkdir '" + script_outdir + "'");
logfilename = script_outdir + "supertreemaker.log";
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
##Pre-run prep: creating log files and output directories, etc...
core.logCheck(l, logfilename, "=======================================================================");
core.logCheck(l, logfilename, "\tSupertree making with SDM, R, newickutils, and r8s");
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime());
core.logCheck(l, logfilename, "INPUT | Making tree from file:\t\t\t" + infilename);
core.logCheck(l, logfilename, "INPUT | Input file located in:\t\t\t" + indir);
if njopt == 1:
core.logCheck(l, logfilename, "INFO | Using Average Consensus method in SDM to build distance matrix.");
def convCheck(cur_c, c, ropt, targets, backgrounds, d, ins, outs):
# cur_c = 0;
init_c = cur_c+1;
while cur_c < c:
#if c > 1:
if ropt != 0:
outfilename = outs + "_" + str(cur_c+1) + ".txt";
else:
outfilename = outs + ".txt";
if ropt != 0:
#backgrounds = ["hg19", "rheMac3", "calJac3", "mm10", "rn5", "vicPac2", "bosTau7", "canFam3", "loxAfr3", "papHam1", "monDom5"];
backgrounds = [];
cur_r = len(backgrounds);
while cur_r < ropt:
chosenspec = random.choice(all_specs.values());
if chosenspec not in targets and chosenspec not in backgrounds:
backgrounds.append(chosenspec);
cur_r = cur_r + 1;
outfile = open(outfilename, "w");
outfile.write("# ==============================================================================================\n");
outfile.write("# \t\t\tConvergence testing\n");
outfile.write("# \t\t\t" + core.getDateTime() + "\n");
outfile.write("# Using alignments in:\t\t" + indir + "\n");
outfile.write("# Target species:\t\t\t" + ", ".join(targets) + "\n");
if ropt != 0:
outfile.write("# Randomly choosing " + str(r) + " background species and performing " + str(c) + " replicate tests for convergence.\n");
outfile.write("# This is replicate number " + str(cur_c+1) + "\n");
outfile.write("# Background species:\t\t" + ", ".join(backgrounds) + "\n");
outfile.write("# Writing output to:\t\t\t" + outfilename + "\n");
if d == 0:
outfile.write("# Checking for convergent sites.\n");
elif d == 1:
outfile.write("# Checking for divergent sites.\n");
outfile.write("# ---------------------------------------------\n");
#sys.exit();
#cur_c = cur_c + 1;
#continue;
aligns = os.listdir(ins);
numbars = 0;
donepercent = [];
count = len(aligns);
i = 0;
numsites = 0;
totgenes = 0;
outfile.write("# " + core.getTime() + " Starting Scan...\n");
outfile.write("# Site#\tChromosome\tGeneID\tAlignLen\tPosition\tTargetAlleles\tBackgroundAlleles\n");
for align in aligns:
#numbars, donepercent = core.loadingBar(i, count, donepercent, numbars);
i = i + 1;
if align.find(".fa") == -1:
continue;
#if i > 25:
# break;
infilename = ins + align;
#print align;
gid = "_".join(align.split("_")[:2]);
chrome = align[align.find("chr"):align.find("chr")+4]
inseqs = core.fastaGetDict(infilename);
num_targets_present = 0;
num_bg_present = 0;
for title in inseqs:
if any(t in title for t in targets):
num_targets_present = num_targets_present + 1;
if any(b in title for b in backgrounds):
num_bg_present = num_bg_present + 1;
if num_targets_present == len(targets) and num_bg_present == len(backgrounds):
#print "The following gene has all target and background species and will be checked:\t\t" + gid;
totgenes = totgenes + 1;
seqlen = len(inseqs[inseqs.keys()[0]]);
#print "Alignment length\t\t", seqlen;
t_alleles = {};
b_alleles = {};
for x in xrange(len(inseqs[inseqs.keys()[0]])):
for title in inseqs:
for t in targets:
if t in title:
t_alleles[t] = inseqs[title][x];
for b in backgrounds:
if b in title:
b_alleles[b] = inseqs[title][x];
t_states = t_alleles.values();
t_gap = t_states.count("-");
t_missing = t_states.count("X");
t_stop = t_states.count("*");
b_states = b_alleles.values();
b_gap = b_states.count("-");
b_missing = b_states.count("X");
b_stop = b_states.count("*");
t_final = remGapMiss(t_states);
b_final = remGapMiss(b_states);
#print t_alleles;
#print t_states;
#print t_gap;
#print t_missing;
#print t_stop;
#print t_final;
#print b_alleles;
#print b_states;
#print b_gap;
#print b_missing;
#print b_stop;
#print b_final;
if t_final == [] or b_final == []:
continue;
if d == 0:
if len(t_final) == len(targets) and len(b_final) == len(backgrounds) and t_final.count(t_final[0]) == len(t_final) and t_final[0] not in b_final:
numsites = numsites + 1;
#print core.getTime() + " Convergent site found!";
#print "Filename:\t\t" + align;
#print "Chromosome:\t\t" + chrome;
#print "Gene ID:\t\t" + gid;
#print "Alignment length\t", seqlen;
#print "Target alleles:\t\t" + "".join(t_final);
#print "Background alleles:\t" + "".join(b_final);
#print "---------------";
outline = str(numsites) + "\t" + chrome + "\t" + gid + "\t" + str(seqlen) + "\t" + str(x+1) + "\t" + "".join(t_final) + "\t" + "".join(b_final) + "\n";
outfile.write(outline);
#sys.exit();
elif d == 1:
if len(t_final) == len(targets) and len(b_final) == len(backgrounds) and t_final.count(t_final[0]) != len(t_final) and b_final.count(b_final[0]) == len(b_final):
if not any(t in b_final for t in t_final):
numsites = numsites + 1;
#print "\nDivergent site found!";
#print "Filename:\t\t" + align;
#print "Chromosome:\t\t" + chrome;
#print "Gene ID:\t\t" + gid;
#print "Alignment length\t", seqlen;
#print t_final;
#print b_final;
outline = str(numsites) + "\t" + chrome + "\t" + gid + "\t" + str(seqlen) + "\t" + str(x+1) + "\t" + "".join(t_final) + "\t" + "".join(b_final) + "\n";
outfile.write(outline);
#pstring = "100.0% complete.";
#sys.stderr.write('\b' * len(pstring) + pstring);
outfile.write("\n# " + core.getTime() + " Done!\n");
outfile.write("# Total sites found: " + str(numsites) + "\n");
outfile.write("# Total genes checked: " + str(totgenes) + "\n");
outfile.write("# ==============================================================================================");
cur_c = cur_c + 1;
if ropt != 0:
print core.getTime() + " Replicates", init_c, "to", c, "complete.";
print "INFO | Replacing all " + rep[
0] + " symbols in input sequences with a random AA symbol not present in that column."
suffix = suffix + ".r"
if os.path.isfile(ins):
print "OUTPUT | Writing output to the following file:\t\t" + outs
else:
if outs[len(outs) - 1] != "/":
outs = outs + "/"
print "OUTPUT | Writing output to the following directory:\t\t" + outs
if not os.path.exists(outs):
print "+Creating output directory."
os.system("mkdir " + outs)
print "---------------------------------------------"
#sys.exit();
print core.getTime() + " Starting..."
numfiles = len(filelist)
numbars = 0
donepercent = []
i = 0
for each in filelist:
if each.find(".fa") == -1:
continue
if os.path.isfile(ins):
print ins
infilename = ins
outfilename = outs
script_outdir = script_outdir[:script_outdir.index("-") +
1] + str(counter)
counter += 1
if os.path.isfile(ins):
fileflag = 1
filelist = [os.path.abspath(ins)]
else:
fileflag = 0
filelist = os.listdir(ins)
ins = os.path.abspath(ins)
script_outdir = os.path.abspath(script_outdir)
bestdir = os.path.join(script_outdir, "raxml-best")
outdir = os.path.join(script_outdir, "raxml-out")
print core.getTime() + " | Creating main output directory:\t" + script_outdir
os.system("mkdir '" + script_outdir + "'")
logfilename = os.path.join(script_outdir, "run_raxml.log")
core.filePrep(logfilename)
core.logCheck(
l, logfilename,
"=======================================================================")
core.logCheck(l, logfilename, "\t\t\tBuilding trees with RAxML")
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime())
if fileflag == 1:
core.logCheck(l, logfilename,
"INPUT | Making tree from file:\t\t" + ins)
else:
core.logCheck(l, logfilename,
def convCheck(cur_c, c, number_specs, d, ins, outs):
# cur_c = 0;
init_c = cur_c + 1
while cur_c < c:
#if c > 1:
spec_list = all_specs.values()
rep_specs = []
while len(rep_specs) < number_specs:
r = random.choice(spec_list)
rep_specs.append(r)
spec_list.remove(r)
outfilename = outs + "_" + str(cur_c + 1) + ".txt"
outfile = open(outfilename, "w")
outfile.write(
"# ==============================================================================================\n"
)
outfile.write("# \t\t\tConvergence testing\n")
outfile.write("# \t\t\t" + core.getDateTime() + "\n")
outfile.write("# Using alignments in:\t\t" + indir + "\n")
outfile.write("# Randomly choosing " + str(number_specs) +
" species and performing " + str(c) +
" replicate tests for convergence.\n")
outfile.write("# This is replicate number " + str(cur_c + 1) + "\n")
outfile.write("# Writing output to:\t\t\t" + outfilename + "\n")
if d == 0:
outfile.write("# Checking for convergent sites.\n")
elif d == 1:
outfile.write("# Checking for divergent sites.\n")
outfile.write("# Using species:\t" + ",".join(rep_specs))
outfile.write("# ---------------------------------------------\n")
#sys.exit();
#cur_c = cur_c + 1;
#continue;
aligns = os.listdir(ins)
numbars = 0
donepercent = []
count = len(aligns)
i = 0
numsites = 0
totgenes = 0
outfile.write("# " + core.getTime() + " Starting Scan...\n")
outfile.write(
"# Site#\tTargetSpecs\tChromosome\tGeneID\tAlignLen\tPosition\tTargetAlleles\tBackgroundAlleles\n"
)
for align in aligns:
#numbars, donepercent = core.loadingBar(i, count, donepercent, numbars);
i = i + 1
if align.find(".fa") == -1:
continue
infilename = os.path.join(ins, align)
gid = "_".join(align.split("_")[:2])
chrome = align[align.find("chr"):align.find("chr") + 4]
inseqs = core.fastaGetDict(infilename)
for t1 in rep_specs:
for t2 in rep_specs:
if t1 == t2:
continue
targets = [t1, t2]
backgrounds = [
spec for spec in rep_specs if spec not in targets
]
num_targets_present = 0
num_bg_present = 0
for title in inseqs:
if any(t in title for t in targets):
num_targets_present = num_targets_present + 1
if any(b in title for b in backgrounds):
num_bg_present = num_bg_present + 1
if num_targets_present == len(
targets) and num_bg_present == len(backgrounds):
# print "The following gene has all target and background species and will be checked:\t\t" + gid;
totgenes = totgenes + 1
seqlen = len(inseqs[inseqs.keys()[0]])
# print "Alignment length\t\t", seqlen;
t_alleles = {}
b_alleles = {}
for x in xrange(len(inseqs[inseqs.keys()[0]])):
for title in inseqs:
cur_spec = title[1:].replace("\n", "")
if cur_spec in targets:
t_alleles[cur_spec] = inseqs[title][x]
if cur_spec in backgrounds:
b_alleles[cur_spec] = inseqs[title][x]
t_states = t_alleles.values()
#t_gap = t_states.count("-");
#t_missing = t_states.count("X");
#t_stop = t_states.count("*");
b_states = b_alleles.values()
#b_gap = b_states.count("-");
#b_missing = b_states.count("X");
#b_stop = b_states.count("*");
t_final = remGapMiss(t_states)
b_final = remGapMiss(b_states)
if t_final == [] or b_final == []:
continue
if d == 0:
if len(t_final) == len(targets) and len(
b_final
) == len(backgrounds) and t_final.count(
t_final[0]) == len(
t_final
) and t_final[0] not in b_final:
numsites = numsites + 1
print core.getTime(
) + " Convergent site found!"
print "Filename:\t\t" + align
print "Chromosome:\t\t" + chrome
print "Gene ID:\t\t" + gid
print "Alignment length\t", seqlen
print "Target alleles:\t\t" + "".join(
t_final)
print "Background alleles:\t" + "".join(
b_final)
print "---------------"
outline = str(numsites) + "\t" + ",".join(
targets
) + "\t" + chrome + "\t" + gid + "\t" + str(
seqlen) + "\t" + str(
x + 1) + "\t" + "".join(
t_final) + "\t" + "".join(
b_final) + "\n"
outfile.write(outline)
elif d == 1:
if len(t_final) == len(targets) and len(
b_final
) == len(backgrounds) and t_final.count(
t_final[0]) != len(
t_final) and b_final.count(
b_final[0]) == len(b_final):
if not any(t in b_final for t in t_final):
numsites = numsites + 1
# print "\nDivergent site found!";
# print "Filename:\t\t" + align;
# print "Chromosome:\t\t" + chrome;
# print "Gene ID:\t\t" + gid;
# print "Alignment length\t", seqlen;
# print t_final;
# print b_final;
outline = str(
numsites
) + "\t" + ",".join(
targets
) + "\t" + chrome + "\t" + gid + "\t" + str(
seqlen) + "\t" + str(
x + 1) + "\t" + "".join(
t_final) + "\t" + "".join(
b_final) + "\n"
outfile.write(outline)
#pstring = "100.0% complete.";
#sys.stderr.write('\b' * len(pstring) + pstring);
outfile.write("\n# " + core.getTime() + " Done!\n")
outfile.write("# Total sites found: " + str(numsites) + "\n")
outfile.write("# Total genes checked: " + str(totgenes) + "\n")
outfile.write(
"# =============================================================================================="
)
cur_c = cur_c + 1
if ropt != 0:
print core.getTime() + " Replicates", init_c, "to", c, "complete."
reps) + " replicate tests."
print "The task will be split into " + str(
num_t
) + " processes and species will be chosen as the processes are split."
if cd == 0:
print "Checking for convergent sites."
elif cd == 1:
print "Checking for divergent sites."
print "---------------------------------------------"
if num_t > 1:
bgs = []
processes = []
output = mp.Queue()
reps_per_t = reps / num_t
print core.getTime() + " Generating function calls..."
print "Function calls and arguments are as follows:"
print "convCheck([start replicate], [stop replicate], [# random species], [target species], [background species], [convergence/divergence option], [input directory], [output prefix])"
print "----------"
x = 0
while x < num_t:
start_rep = reps_per_t * x
stop_rep = reps_per_t * (x + 1)
print core.getTime() + " Call " + str(x + 1) + ": convCheck(" + str(
start_rep) + " , " + str(stop_rep) + " , " + str(
specs) + " , " + str(cd) + ", " + indir + " , " + outfix + ")"
processes.append(
mp.Process(target=convCheck,
args=(start_rep, stop_rep, specs, cd, indir, outfix)))
x = x + 1
print "----------"
filelist = [ins];
else:
fileflag = 0;
indir, script_outdir = core.getOutdir(ins, "run_codeml", starttime);
if outdir_suffix != None:
if script_outdir[-1] == "/":
script_outdir = script_outdir[:len(script_outdir)-1] + "-" + outdir_suffix + "/";
else:
script_outdir = script_outdir + "-" + outdir_suffix + "/";
outdir = script_outdir + "codeml_out/";
filelist = os.listdir(indir);
if aopt == 1:
ancdir = script_outdir + "anc_seqs_fa/";
print core.getTime() + " | Creating main output directory:\t" + script_outdir;
os.system("mkdir " + script_outdir);
logfilename = script_outdir + "run_codeml.log";
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
core.logCheck(l, logfilename, "=======================================================================");
core.logCheck(l, logfilename, "\t\t\tRunning codeml");
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime());
if fileflag == 1:
core.logCheck(l, logfilename, "INPUT | Making tree from file:\t\t" + ins);
else:
core.logCheck(l, logfilename, "INPUT | Running codeml on all files in:\t" + indir);
core.logCheck(l, logfilename, "INFO | PAML path set to:\t\t\t" + ppath);
indir, script_outdir = core.getOutdir(indir, "run_codeml", starttime)
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 = core.getOutdir(ins, "run_codeml", outdir_suffix,
starttime)
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 core.getTime() + " | Creating main output directory:\t" + script_outdir
mk_cmd = "mkdir " + script_outdir
os.system(mk_cmd)
logfilename = os.path.join(script_outdir, "run_codeml.log")
# logfile = open(logfilename, "w");
# logfile.write("");
# logfile.close();
core.logCheck(
l, logfilename,
"=======================================================================")
core.logCheck(l, logfilename, "\t\t\tRunning codeml")
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime())
if fileflag == 1:
core.logCheck(l, logfilename,
print "\t\t\tSequence format conversion";
print "\t\t\t" + core.getDateTime();
if fileflag == 1:
print "INPUT | Converting file: " + ins;
else:
print "INPUT | Converting all files from directory: " + ins;
print "INFO | Input format: " + fr;
print "INFO | Output format: " + to;
if fileflag == 1:
print "OUTPUT | Writing output to file: " + outs;
else:
print "OUTPUT | Writing output files to directory: " + outs;
print "-------------------------------------";
if fileflag == 0:
print core.getTime() + " | Creating output directory...";
if not os.path.exists(outs):
os.system("mkdir " + outs);
numfiles = len(filelist);
numbars = 0;
donepercent = [];
i = 0;
if fr == "f":
init = ".fa";
elif fr == "p":
init = ".ph";
elif fr == "n":
init = ".nex";
print "\t\t\t" + core.getDateTime();
print "Using alignments in:\t\t" + indir
print "Choosing " + str(specs) + " species randomly and performing " + str(reps) + " replicate tests.";
print "The task will be split into " + str(num_t) + " processes and species will be chosen as the processes are split.";
if cd == 0:
print "Checking for convergent sites.";
elif cd == 1:
print "Checking for divergent sites.";
print "---------------------------------------------";
if num_t > 1:
bgs = [];
processes = []
output = mp.Queue()
reps_per_t = reps / num_t;
print core.getTime() + " Generating function calls...";
print "Function calls and arguments are as follows:";
print "convCheck([start replicate], [stop replicate], [# random species], [target species], [background species], [convergence/divergence option], [input directory], [output prefix])";
print "----------";
x = 0;
while x < num_t:
start_rep = reps_per_t * x;
stop_rep = reps_per_t * (x+1);
print core.getTime() + " Call " + str(x+1) + ": convCheck(" + str(start_rep) + " , " + str(stop_rep) + " , " + str(specs) + " , " + str(cd) + ", " + indir + " , " + outfix + ")";
processes.append(mp.Process(target=convCheck,args=(start_rep,stop_rep,specs,cd,indir,outfix)));
x = x + 1;
print "----------";
##print processes;
##convCheck(
for p in processes:
print core.getTime() + " start", p;
ins, gb_path, seqtype, m, v, l = optParse(0);
starttime = core.getLogTime();
if os.path.isfile(ins):
fileflag = 1;
indir = os.path.dirname(os.path.realpath(ins)) + "/";
indir, outdir = core.getOutdir(indir, "run_gblocks", starttime);
filelist = [ins];
else:
fileflag = 0;
indir, outdir = core.getOutdir(ins, "run_gblocks", starttime);
filelist = os.listdir(indir);
print core.getTime() + " | Creating main output directory...";
os.system("mkdir " + outdir);
logfilename = outdir + "run_gblocks.log";
logfile = open(logfilename, "w");
logfile.write("");
logfile.close();
core.logCheck(l, logfilename, "=======================================================================");
core.logCheck(l, logfilename, "\t\t\tMasking alignments with GBlocks");
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime());
if fileflag == 1:
core.logCheck(l, logfilename, "INPUT | Masking alignment from file: " + ins);
else:
core.logCheck(l, logfilename, "INPUT | Masking alignments from all files in: " + indir);
core.logCheck(l, logfilename, "INFO | GBlocks path set to: " + gb_path);
def convCheck(cur_c, c, number_specs, d, ins, outs):
# cur_c = 0;
init_c = cur_c+1;
while cur_c < c:
#if c > 1:
spec_list = all_specs.values();
rep_specs = [];
while len(rep_specs) < number_specs:
r = random.choice(spec_list);
rep_specs.append(r);
spec_list.remove(r);
outfilename = outs + "_" + str(cur_c+1) + ".txt";
outfile = open(outfilename, "w");
outfile.write("# ==============================================================================================\n");
outfile.write("# \t\t\tConvergence testing\n");
outfile.write("# \t\t\t" + core.getDateTime() + "\n");
outfile.write("# Using alignments in:\t\t" + indir + "\n");
outfile.write("# Randomly choosing " + str(number_specs) + " species and performing " + str(c) + " replicate tests for convergence.\n");
outfile.write("# This is replicate number " + str(cur_c+1) + "\n");
outfile.write("# Writing output to:\t\t\t" + outfilename + "\n");
if d == 0:
outfile.write("# Checking for convergent sites.\n");
elif d == 1:
outfile.write("# Checking for divergent sites.\n");
outfile.write("# Using species:\t" + ",".join(rep_specs));
outfile.write("# ---------------------------------------------\n");
#sys.exit();
#cur_c = cur_c + 1;
#continue;
aligns = os.listdir(ins);
numbars = 0;
donepercent = [];
count = len(aligns);
i = 0;
numsites = 0;
totgenes = 0;
outfile.write("# " + core.getTime() + " Starting Scan...\n");
outfile.write("# Site#\tTargetSpecs\tChromosome\tGeneID\tAlignLen\tPosition\tTargetAlleles\tBackgroundAlleles\n");
for align in aligns:
#numbars, donepercent = core.loadingBar(i, count, donepercent, numbars);
i = i + 1;
if align.find(".fa") == -1:
continue;
infilename = os.path.join(ins, align);
gid = "_".join(align.split("_")[:2]);
chrome = align[align.find("chr"):align.find("chr")+4]
inseqs = core.fastaGetDict(infilename);
for t1 in rep_specs:
for t2 in rep_specs:
if t1 == t2:
continue;
targets = [t1, t2];
backgrounds = [spec for spec in rep_specs if spec not in targets];
num_targets_present = 0;
num_bg_present = 0;
for title in inseqs:
if any(t in title for t in targets):
num_targets_present = num_targets_present + 1;
if any(b in title for b in backgrounds):
num_bg_present = num_bg_present + 1;
if num_targets_present == len(targets) and num_bg_present == len(backgrounds):
# print "The following gene has all target and background species and will be checked:\t\t" + gid;
totgenes = totgenes + 1;
seqlen = len(inseqs[inseqs.keys()[0]]);
# print "Alignment length\t\t", seqlen;
t_alleles = {};
b_alleles = {};
for x in xrange(len(inseqs[inseqs.keys()[0]])):
for title in inseqs:
cur_spec = title[1:].replace("\n","");
if cur_spec in targets:
t_alleles[cur_spec] = inseqs[title][x];
if cur_spec in backgrounds:
b_alleles[cur_spec] = inseqs[title][x];
t_states = t_alleles.values();
#t_gap = t_states.count("-");
#t_missing = t_states.count("X");
#t_stop = t_states.count("*");
b_states = b_alleles.values();
#b_gap = b_states.count("-");
#b_missing = b_states.count("X");
#b_stop = b_states.count("*");
t_final = remGapMiss(t_states);
b_final = remGapMiss(b_states);
if t_final == [] or b_final == []:
continue;
if d == 0:
if len(t_final) == len(targets) and len(b_final) == len(backgrounds) and t_final.count(t_final[0]) == len(t_final) and t_final[0] not in b_final:
numsites = numsites + 1;
print core.getTime() + " Convergent site found!";
print "Filename:\t\t" + align;
print "Chromosome:\t\t" + chrome;
print "Gene ID:\t\t" + gid;
print "Alignment length\t", seqlen;
print "Target alleles:\t\t" + "".join(t_final);
print "Background alleles:\t" + "".join(b_final);
print "---------------";
outline = str(numsites) + "\t" + ",".join(targets) + "\t" + chrome + "\t" + gid + "\t" + str(seqlen) + "\t" + str(x+1) + "\t" + "".join(t_final) + "\t" + "".join(b_final) + "\n";
outfile.write(outline);
elif d == 1:
if len(t_final) == len(targets) and len(b_final) == len(backgrounds) and t_final.count(t_final[0]) != len(t_final) and b_final.count(b_final[0]) == len(b_final):
if not any(t in b_final for t in t_final):
numsites = numsites + 1;
# print "\nDivergent site found!";
# print "Filename:\t\t" + align;
# print "Chromosome:\t\t" + chrome;
# print "Gene ID:\t\t" + gid;
# print "Alignment length\t", seqlen;
# print t_final;
# print b_final;
outline = str(numsites) + "\t" + ",".join(targets) + "\t" + chrome + "\t" + gid + "\t" + str(seqlen) + "\t" + str(x+1) + "\t" + "".join(t_final) + "\t" + "".join(b_final) + "\n";
outfile.write(outline);
#pstring = "100.0% complete.";
#sys.stderr.write('\b' * len(pstring) + pstring);
outfile.write("\n# " + core.getTime() + " Done!\n");
outfile.write("# Total sites found: " + str(numsites) + "\n");
outfile.write("# Total genes checked: " + str(totgenes) + "\n");
outfile.write("# ==============================================================================================");
cur_c = cur_c + 1;
if ropt != 0:
print core.getTime() + " Replicates", init_c, "to", c, "complete.";
print "Sequence\tLength"
i = i + 1
if each.find(".fa") == -1:
continue
specpos = 0
infilename = ins + each
inseqs = core.fastaGetDict(infilename)
for seq in inseqs:
tot_pos = tot_pos + len(inseqs[seq])
if disp_file == 1:
specpos = specpos + len(inseqs[seq])
print seq + "\t" + str(len(inseqs[seq]))
if disp_file == 1:
print "Total\t" + str(specpos)
if disp_file == 0:
pstring = "100.0% complete."
sys.stderr.write('\b' * len(pstring) + pstring)
elif disp_file == 1:
print "----------"
print "\n" + core.getTime() + " Done!"
print "-----"
print "Total residues:\t", tot_pos
print "======================================================================="
if os.path.isfile(ins):
fileflag = 1
indir = os.path.dirname(os.path.realpath(ins)) + "/"
indir, script_outdir = core.getOutdir(indir, "run_raxml", starttime)
bestdir = script_outdir + "raxml_best/"
outdir = script_outdir + "raxml_out/"
filelist = [ins]
else:
fileflag = 0
indir, script_outdir = core.getOutdir(ins, "run_raxml", starttime)
bestdir = script_outdir + "raxml_best/"
outdir = script_outdir + "raxml_out/"
filelist = os.listdir(indir)
print core.getTime() + " | Creating main output directory:\t" + script_outdir
os.system("mkdir '" + script_outdir + "'")
logfilename = script_outdir + "run_raxml.log"
logfile = open(logfilename, "w")
logfile.write("")
logfile.close()
core.logCheck(l, logfilename, "=======================================================================")
core.logCheck(l, logfilename, "\t\t\tBuilding trees with RAxML")
core.logCheck(l, logfilename, "\t\t\t" + core.getDateTime())
if fileflag == 1:
core.logCheck(l, logfilename, "INPUT | Making tree from file:\t\t" + indir)
else:
core.logCheck(l, logfilename, "INPUT | Making trees from all files in:\t" + indir)
core.logCheck(l, logfilename, "INPUT | RAxML path set to:\t\t\t" + rax_path)
