def txt_equals_csv(population, algo, reverse, count):
splitted = ""
for i in range(0, count):
splitted = splitted + "Splitted"
indir = qlibs.get_datadir() + population
sets = os.listdir(indir)
text = ""
for set in sets:
csvfiles = []
txtfiles = []
if os.path.isdir(indir + "/" + set):
for dir in os.listdir(indir + "/" + set):
if dir.find(algo + reverse + splitted) >= 0:
if os.path.isdir(indir + "/" + set + "/" + dir + "/"):
for file in os.listdir(indir + "/" + set + "/" + dir +
"/"):
if file.find(".csv") > 0: csvfiles.append(file)
if dir.find("Text" + reverse + algo + splitted) >= 0:
if os.path.isdir(indir + "/" + set + "/" + dir + "/"):
for file in os.listdir(indir + "/" + set + "/" + dir +
"/"):
if file.find(".txt") > 0: txtfiles.append(file)
for file in txtfiles:
if qlibs.find(file.replace(".txt", ".csv"), csvfiles) < 0:
text = text + qlibs.get_datadir(
) + population + "/" + set + "/Text" + reverse + algo + splitted + "/" + file + "\n"
if text == "": result = True
else:
outfile = get_filename(population, algo, count)
fout = open(outfile, "w")
fout.write(text)
fout.close()
result = False
return result
def dist(root, algodir, reverse, regiondir="any", setdir="any"):
data = pan.DataFrame()
dist = pan.DataFrame()
header = True
rootfile = ""
datadir = qlibs.get_datadir()
rootdir = datadir + root + "/"
popfirst = True
for set in os.listdir(rootdir):
if os.path.isdir(rootdir + set):
if set == setdir or setdir == "any":
outfile = rootdir + set + "/" + "dist_" + algodir + reverse + "_" + root + "_" + set + "_YYYYmmdd.csv"
newfile = rootdir + set + "/" + "dist_" + algodir + reverse + "_" + root + "_" + set + "_" + str(
datetime.date.today()).replace("-", "") + ".csv"
if setdir == "any":
rootfile = rootdir + "dist_" + algodir + reverse + "_" + root + "_YYYYmmdd.csv"
popfirst = dist_data(rootdir, set, algodir, reverse,
outfile, rootfile, regiondir,
popfirst)
else:
dist_data(rootdir, set, algodir, reverse, outfile,
regiondir)
if os.path.isfile(outfile):
if os.path.isfile(newfile): os.remove(newfile)
os.rename(outfile, newfile)
if rootfile != "":
newrootfile = rootdir + "dist_" + algodir + reverse + "_" + root + "_" + str(
datetime.date.today()).replace("-", "") + ".csv"
if os.path.isfile(rootfile):
if os.path.isfile(newrootfile): os.remove(newrootfile)
os.rename(rootfile, newrootfile)
pass
return
def callback(self, event):
try:
if event.widget.cget("text") == "Browse":
if self.opt == "get_seq": self.browse_get_seq()
if self.opt == "lost": self.browse_get_seq()
if self.opt == "errors": self.browse_errors()
if self.opt == "graph": self.browse_graphics()
if self.opt == "select": self.browse_select()
if event.widget.cget("text") == "Execute":
cfgn.save(self)
qlibs.create_path(qlibs.get_datadir() + self.pop.get() + "/")
if self.opt == "get_seq": self.get_seq()
if self.opt == "lost": self.lost()
if self.opt == "reverse": self.reverse()
if self.opt == "quad_search": self.quad_search()
if self.opt == "errors": self.errors()
if self.opt == "dist": self.dist()
if self.opt == "graph": self.graphics()
if self.opt == "select": self.select()
if self.opt == "intersect": self.intersections()
messagebox.showinfo("Quad", "END!")
if event.widget.cget("text") == "Confirm":
cfgn.save(self)
except:
pass
return
def get_seq(population, finput, search):
result = []
basedir = qlibs.get_datadir() + population + "/"
search = indata[1]
fin = open(finput, "r")
buf = fin.read()
fin.close()
rows = buf.split("\n")
i = 0
while i < len(rows):
cols = rows[i].split(";")
if len(cols) > 1:
code = cols[0]
gene = cols[1]
text = get_fasta(gene, code, search)
if text == "": qlibs.trace("lostfasta", gene + "\t" + code, population)
else:
fout = open(datadir + gene + "__" + code + ".fasta", "w")
fout.write (get_fasta(gene, code, search))
fout.close()
time.sleep(5)
i = i + 1
return result
def quad_search(self):
#
# Submit sequence to a prediction algorithm
#
population = self.pop.get()
set = self.set.get()
reverse = ""
if self.rev.get() == 1:
#
# Submit the reversed sequences
#
reverse = "ReverseComplement"
textdir = qlibs.get_datadir(
) + population + "/" + set + "/Text" + reverse + "/"
regions = ""
#
# The following enable to choose region type
#
if int(self.up.get()) == 1:
regions = regions + "Upstream" + self.upno.get() + ";"
if int(self.u5.get()) == 1: regions = regions + "UtrExon5" + ";"
if int(self.u3.get()) == 1: regions = regions + "UtrExon3" + ";"
if int(self.ce.get()) == 1: regions = regions + "CdsExon" + ";"
if int(self.it.get()) == 1: regions = regions + "Intron" + ";"
if int(self.dw.get()) == 1:
regions = regions + "Downstream" + self.dwno.get() + ";"
if regions != "": regions = regions[:len(regions) - 1]
algo = ""
if int(self.v.get()) == 1:
#
# Use qgrs-cpp (https://github.com/freezer333/qgrs-cpp) recompiled as library
#
algo = "Qgrs"
qgrs.save_csv(population, textdir, regions, algo, reverse)
if int(self.v.get()) == 2:
#
# Submit query to QGRS Mapper (http://bioinformatics.ramapo.edu/QGRS/analyze.php)
#
algo = "QgrsWeb"
qgrs.save_csv(population, textdir, regions, algo, reverse)
if int(self.v.get()) == 3:
#
# Use pqs function from R-library pqsfinder previously installed (http://www.bioconductor.org/packages/release/bioc/html/pqsfinder.html)
#
try:
algo = "Pqs"
script = qlibs.get_scriptsdir() + "pqs.r"
cmd = ["Rscript", script] + [
self.libpath.get(), population, textdir, regions, algo
]
result = subprocess.check_output(cmd, universal_newlines=True)
except Exception as e:
qlibs.trace("pqs", str(e), population)
print("qgrs.py " + population + " " + textdir + " " + regions + " " +
algo)
return
def open(self):
indir = qlibs.get_datadir()
types = (("csv files", "*.csv"), ("all files", "*.*"))
fname = filedialog.askopenfilename(parent=self.root,
initialdir=indir,
title='Please select a file',
filetypes=types)
if os.name == 'nt': os.system("start " + fname)
if os.name == 'posix': os.system("open " + shlex.quote(fname))
return
def browse_select(self):
indir = qlibs.get_datadir() + self.pop.get() + "/"
types = (("csv files", "*.csv"), ("all files", "*.*"))
fname = filedialog.askopenfilename(parent=self.root,
initialdir=indir,
title='Please select a file',
filetypes=types)
self.file.set(fname)
print("select")
return
def browse_graphics(self):
indir = qlibs.get_datadir() + self.pop.get() + "/"
types = (("csv files", "*.csv"), ("all files", "*.*"))
fname = filedialog.askopenfilename(parent=self.root,
initialdir=indir,
title='Please select a file',
filetypes=types)
self.file.set(fname)
buf = fname[:fname.rfind("/")]
buf = buf[buf.rfind("/") + 1:]
self.tit.set(buf)
return
def save_union(population, algo, reverse):
indir = qlibs.get_datadir() + population + "/"
sets = os.listdir(indir)
print(sets)
for set in sets:
if os.path.isdir(indir + set):
for dir in os.listdir(indir + set + "/"):
if dir.find(algo + reverse + "Splitted") >= 0:
if os.path.isdir(indir + set + "/" + dir + "/"):
for file in os.listdir(indir + set + "/" + dir + "/"):
if file.find(".csv") > 0:
union(indir, set, dir, file, population, algo,
reverse)
return
def getlost(infile, population, set):
datadir = qlibs.get_datadir()
outdir = datadir + "Lost/" + set + "/"
outfile = outdir + "/lost_" + set + ".csv"
qlibs.create_path(outdir)
rows = qlibs.get_rows(infile)
text = ""
for row in rows:
cols = row.split(";")
if len(cols) > 1:
code = cols[0]
gene = cols[1]
found = False
indir = qlibs.get_datadir() + population + "/" + set + "/Text/"
for region in os.listdir(indir):
if os.path.isdir(indir + region):
datadir = indir + region + "/" + gene + "__" + code
if os.path.isdir(datadir):
found = True
if found == False: text += code + ";" + gene + ";\n"
ft = open(outfile, "w")
ft.write(text)
ft.close()
return
def reverse_set(population, set):
datadir = qlibs.get_datadir()
indir = datadir + population + "/" + set + "/Text/"
outdir = indir.replace("/Text/", "/TextReverseComplement/")
regions = []
for r, d, f in os.walk(indir):
for rname in d:
regions.append(rname)
for region in regions:
for r, d, f in os.walk(indir + region):
for gene_code in d:
for r, d, f in os.walk(indir + region + "/" + gene_code + "/"):
for fname in f:
infile = indir + region + "/" + gene_code + "/" + fname
outfile = outdir + region + "/" + gene_code + "/" + fname
qlibs.create_path(outdir + region + "/" + gene_code + "/")
qlibs.trace("reverse", infile, population)
reverse_file(infile, outfile)
return
def getlost_fromerrors(infile, population, set):
datadir = qlibs.get_datadir()
outdir = datadir + "Lost/" + set + "/"
outfile = outdir + "/declost_" + set + ".csv"
qlibs.create_path(outdir)
rows = qlibs.get_rows(infile)
text = ""
for row in rows:
cols = row.split("\t")
if len(cols) > 1:
codebuf = cols[1]
gene = cols[0]
buf = codebuf.split(".")
if int(buf[1]) > 1:
code = buf[0] + "." + str(int(buf[1]) - 1)
text += code + ";" + gene + ";\n"
ft = open(outfile, "a")
ft.write(text)
ft.close()
return
def get_seq(population, argv):
result = []
basedir = qlibs.get_datadir() + population + "/"
countfile = qlibs.get_datadir() + "Countfile.log"
indata = params(argv)
finput = indata[0]
search = indata[1]
col3rd = indata[3]
if col3rd == False:
basename = os.path.basename(indata[0])
result.append(basename[:len(basename) - 4])
datadir = basedir + basename[:len(basename) - 4]
datadir = create_dir(datadir, indata)
fin = open(finput, "r")
buf = fin.read()
fin.close()
rows = buf.split("\n")
try:
fc = open(countfile, "r")
buf = fc.read()
fc.close()
cols = buf.split("\t")
count = int(cols[0])
day = time.strptime(cols[3], "%Y-%m-%d")
today = time.strptime(str(datetime.date.today()), "%Y-%m-%d")
print(day, today)
if today > day:
count = 0
elif count >= 5000:
tk.messagebox.showinfo("Quad", "Daily hits limit reached!")
return result
if cols[2] == finput:
i = int(cols[1])
if i >= len(rows):
res = tk.messagebox.askyesno(
"Quad",
"WARNING:\n\n File already processed \n\n Do you want to force Execution?"
)
if res == True:
i = 0
else:
i = 0
except:
count = 0
i = 0
while i < len(rows):
cols = rows[i].split(";")
if len(cols) > 1:
code = cols[0]
gene = cols[1]
if col3rd == True:
if qlibs.find(cols[2], result) < 0: result.append(cols[2])
datadir = basedir + cols[2]
datadir = create_dir(datadir, indata)
count = count + 1
print(count, gene, code)
text = get_fasta(gene, code, search)
if text == "":
text = get_fasta_gene(gene, code, search)
if text == "":
get_fasta_alt(gene, code, search)
if text == "":
text = get_fasta_gene_alt(gene, code, search)
if text == "":
qlibs.trace("fasta", gene + "\t" + code,
population)
else:
fout = open(
datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta",
"w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
else:
fout = open(datadir + gene + "__" + code + ".fasta", "w")
fout.write(text)
fout.close()
if count % 5000 == 0:
tk.messagebox.showinfo("Quad", "Daily hits limit reached!")
break
time.sleep(5)
i = i + 1
fc = open(countfile, "w")
fc.write(
str(count) + "\t" + str(i) + "\t" + finput + "\t" +
str(datetime.date.today()))
fc.close()
return result
def intersect(population, algo):
lists = []
sets = []
dists = []
indir = qlibs.get_datadir() + population + "/"
outfile = indir + "intersect_genes_" + population + str(
datetime.date.today()).replace("-", "") + ".csv"
for set in os.listdir(indir):
if os.path.isdir(indir + set):
files = [
f for f in os.listdir(indir + set)
if os.path.isfile(indir + set + "/" + f)
]
lastfile = ""
for file in files:
try:
if file.index("dist_" + algo) == 0 and file.index(
".csv") == len(file) - 4:
if file > lastfile: lastfile = file
except:
pass
if lastfile == "": qlibs.trace("intersect", set, pop=population)
else:
lists.append(qlibs.get_uniques(indir + set + "/" + lastfile))
sets.append(set)
f = open(indir + set + "/" + lastfile, "r")
buf = f.read()
f.close()
dists.append(buf)
elems = []
setreps = []
setidxs = []
for i in range(len(sets) - 1):
j = i + 1
while j < len(lists):
for elem in lists[i]:
if qlibs.find(elem, lists[j]) >= 0:
k = qlibs.find(elem, elems)
if k >= 0:
if qlibs.find(sets[j], setreps[k]) < 0:
setreps[k].append(sets[j])
setidxs[k].append(j)
else:
elems.append(elem)
list = [sets[i], sets[j]]
setreps.append(list)
list = [i, j]
setidxs.append(list)
j = j + 1
text = ""
print(sets)
print(setreps)
print(setidxs)
for i in range(len(elems)):
text = text + elems[i] + ";"
for set in setreps[i]:
text = text + set + ";"
text = text + "\n"
if text == "": text = "No intersection found"
fout = open(outfile, "w")
fout.write(text)
fout.close()
text = ""
for i in range(len(elems)):
j = setidxs[i][0]
buf = dists[j]
print(j)
print(elems[i])
rows = buf.split("\n")
for row in rows:
if row.find(elems[i]) >= 0:
text = text + row
for set in setreps[i]:
text = text + set + ";"
text = text + "\n"
outfile = indir + "intersect_dists_" + algo + "_" + population + str(
datetime.date.today()).replace("-", "") + ".csv"
fout = open(outfile, "w")
fout.write(text)
fout.close()
return
def substr_not_founds(population,
algo,
overlap,
reverse,
nsplit=2,
libpath=""):
count = get_filecount(population, algo)
if count <= 0: start_file(population, algo)
else: count = count - 1
infile = get_filename(population, algo, count)
#logdir = qlibs.get_logdir() + population + "/"
fin = open(infile, "r")
buf = fin.read()
fin.close()
lines = buf.split("\n")
print(lines, reverse)
for line in lines:
if line.find("C:/") >= 0 or line.find("./") >= 0:
if line.find(".txt") >= 0:
infile = qlibs.get_datadir() + line[line.find(population):]
outfile = infile.replace("/Text",
"/" + algo).replace(".txt", ".csv")
buf = outfile[outfile.find(algo):]
length = buf.find("/") + 2
outdir = outfile[:outfile.find("/" + algo) + length]
print(population, line, infile, outfile, outdir, buf)
if not os.path.exists(outdir):
os.mkdir(outdir)
splittedoutfile = infile.replace(
"/Text" + reverse, "/Text" + reverse + algo + "Splitted")
buf = splittedoutfile[splittedoutfile.find("Text" + reverse +
algo + "Splitted"):]
length = buf.find("/") + 2
splittedoutdir = splittedoutfile[:splittedoutfile.
find("/Text" + reverse +
algo + "Splitted") +
length]
if not os.path.exists(splittedoutdir):
os.mkdir(splittedoutdir)
if not os.path.exists(outfile):
if algo == "QgrsWeb":
if qgrs.qgrs_web(population, infile, outfile) == False:
found = False
try:
split_file(population, algo, infile,
splittedoutdir, nsplit, overlap,
reverse)
except:
pass
if algo == "Qgrs":
if platform.system().find("Windows") >= 0:
libcpp = cdll.LoadLibrary("../lib/Qgrs.dll")
if platform.system().find("Linux") >= 0:
libcpp = cdll.LoadLibrary("../lib/qgrs-linux.a")
if platform.system().find("Darwin") >= 0:
libcpp = cdll.LoadLibrary("../lib/qgrs-mac.so")
if qgrs.qgrs_local(population, infile, outfile,
libcpp) == False:
found = False
try:
split_file(population, algo, infile,
splittedoutdir, nsplit, overlap,
reverse)
except:
pass
if algo == "Pqs":
if qgrs.pqs(libpath, population, infile,
outfile) == False:
found = False
try:
split_file(population, algo, infile,
splittedoutdir, nsplit, overlap,
reverse)
except:
pass
else:
print(outfile)
count = count + 1
result = txt_equals_csv(population, algo, reverse, count)
return result
def get_seq(self):
#
# Get transcript sequence from UCSC Genome Browser (https://genome.ucsc.edu/)
#
u = False
d = False
uddir = ""
udpar = ""
ftcidir = ""
ftcipar = ""
chr = ""
nregs = 0
regions = ""
opts = ""
argv = ["quad.exe"]
argv.append(self.file.get())
print("get")
print(self.t)
if int(self.up.get()) == 1:
argv.append("-u")
argv.append(self.upno.get())
u = True
if int(self.s.get()) == 1:
uddir = "Upstream" + str(self.upno.get()) + "OnePerRegion/"
regions = regions + "Upstream" + str(self.upno.get())
opts = opts + "u"
if int(self.s.get()) == 2:
uddir = "Upstream" + str(self.upno.get()) + "/"
regions = regions + "Upstream" + str(self.upno.get())
opts = opts + "u"
if udpar == "": udpar = "Upstream" + str(self.upno.get())
else: udpar = udpar + ";" + "Upstream" + str(self.upno.get())
if int(self.u5.get()) == 1:
argv.append("-f")
if int(self.s.get()) == 1:
ftcidir = "UtrExon5OnePerRegion/"
nregs = nregs + 1
regions = regions + "UtrExon5"
opts = opts + "f"
if int(self.s.get()) == 2:
ftcidir = "UtrExon5/"
nregs = nregs + 1
regions = regions + "UtrExon5"
opts = opts + "f"
if ftcipar == "": ftcipar = "UtrExon5;"
else: ftcipar = ftcipar + "UtrExon5;"
chr = "f"
if int(self.u3.get()) == 1:
argv.append("-t")
if int(self.s.get()) == 1:
ftcidir = "UtrExon3OnePerRegion/"
nregs = nregs + 1
regions = regions + "UtrExon3"
opts = opts + "t"
if int(self.s.get()) == 2:
ftcidir = "UtrExon3/"
nregs = nregs + 1
regions = regions + "UtrExon3"
opts = opts + "t"
if ftcipar == "": ftcipar = "UtrExon3;"
else: ftcipar = ftcipar + "UtrExon3;"
chr = "t"
if int(self.ce.get()) == 1:
argv.append("-c")
if int(self.s.get()) == 1:
ftcidir = "CdsExonOnePerRegion/"
nregs = nregs + 1
regions = regions + "CdsExon"
opts = opts + "c"
if int(self.s.get()) == 2:
ftcidir = "CdsExon/"
nregs = nregs + 1
regions = regions + "CdsExon"
opts = opts + "c"
if ftcipar == "": ftcipar = "CdsExon;"
else: ftcipar = ftcipar + "CdsExon;"
chr = "c"
if int(self.it.get()) == 1:
argv.append("-i")
if int(self.s.get()) == 1:
ftcidir = "IntronOnePerRegion/"
nregs = nregs + 1
regions = regions + "Intron"
opts = opts + "i"
if int(self.s.get()) == 2:
ftcidir = "Intron/"
nregs = nregs + 1
regions = regions + "Intron"
opts = opts + "i"
if ftcipar == "": ftcipar = "Intron;"
else: ftcipar = ftcipar + "Intron;"
chr = "i"
if int(self.dw.get()) == 1:
argv.append("-d")
argv.append(self.dwno.get())
d = True
if int(self.s.get()) == 1:
uddir = "Downstream" + self.dwno.get() + "OnePerRegion/"
regions = regions + "Downstream" + self.dwno.get()
opts = opts + "d"
if int(self.s.get()) == 2:
uddir = "Upstream" + str(self.upno.get()) + "/"
regions = regions + "Downstream" + self.dwno.get()
opts = opts + "d"
if udpar == "": udpar = "Downstream" + self.dwno.get()
else: udpar = udpar + ";" + "Downstream" + self.dwno.get()
argv.append("-g")
if int(self.s.get()) == 1: argv.append("feature")
if int(self.s.get()) == 2: argv.append("gene")
else: argv.append("feature")
if self.t.get() == 1:
argv.append("-n")
print(argv)
sets = gs.get_seq(self.pop.get(), argv)
regionsopr = regions
if nregs == 4 and u == True and d == True:
regions = "FullGeneSeq"
if int(self.s.get()) == 1: opts = "full"
if int(self.s.get()) == 2: opts = "full_gene"
if int(self.s.get()) == 1:
regionsopr = regions + "OnePerRegion"
if int(self.s.get()) == 2:
regionsopr = regions
print(str(int(self.s.get())))
print("sets", sets)
for set in sets:
print(regionsopr)
print("regionsopr")
f2t.set_text(
qlibs.get_datadir() + self.pop.get() + "/" + set + "/Fasta/" +
regionsopr + "/", regions, opts)
return