def convert(self):
remove = []
if (self.ind < 1.0 and self.ind > 0.0):
remove = self.get_ind_coverage()
#print(remove)
vcf_command = "vcftools --vcf " + self.vcf_file + " --plink --out " + self.prefix
if (self.thin > 0):
vcf_command = vcf_command + " --thin " + str(self.thin)
if (self.snp < 1.0 and self.snp > 0.0):
vcf_command = vcf_command + " --max-missing " + str(self.snp)
if (len(remove) > 0):
vcf_command = vcf_command + remove
if (self.maf > 0.0 and self.maf < 1.0):
vcf_command = vcf_command + " --maf " + str(self.maf)
if (self.mac > 0):
vcf_command = vcf_command + " --mac " + str(self.mac)
if (self.bi == True):
vcf_command = vcf_command + " --min-alleles 2 --max-alleles 2"
if (self.removeInds == True):
vcf_command = vcf_command + " --remove " + str(self.removeFile)
if (len(self.discard) > 0):
for ind in self.discard:
vcf_command = vcf_command + " --remove-indv " + str(ind)
call = SysCall(vcf_command)
call.run_program()
self.fix_map()
def loglik(self):
fh = open("loglik.txt", 'wb')
for fn in os.listdir("."):
if fn.endswith("stdout"):
temp = open(fn, 'r')
fnlist = fn.split("_")
fnlist2 = fnlist[-2].split(".")
kval = fnlist2[-1]
print(fnlist2)
for line in temp.readlines():
if line.startswith("Loglikelihood:"):
mylist = line.split()
#print(mylist)
fh.write(kval.encode())
fh.write("\t".encode())
fh.write(mylist[-1].encode())
fh.write("\n".encode())
temp.close()
fh.close()
print("Sorting log(likelihood) values...")
command = "sort -n -k1 -o loglik.txt loglik.txt"
sortCall = SysCall(command)
sortCall.run_program()
def admix(self):
ks = range(self.minK, self.maxK + 1)
#print(ks)
#for each k value
for i in ks:
for j in range(self.rep):
command_string = "admixture -j" + str(self.NP) + " -s " + str(
np.random.randint(1000000)) + " --cv=" + str(
self.cv) + " " + self.prefix + ".ped " + str(i)
#call Admixture
admixtureCall = SysCall(command_string)
admixtureCall.run_admixture(self.prefix, i, j)
#Manually re-name output files to include _j rep number
for filename in os.listdir("."):
fn = self.prefix + "." + str(i) + "."
if fn in filename:
oldname, extension = os.path.splitext(filename)
newname = oldname + "_" + str(j) + extension
if (extension.endswith("Q")):
self.qfiles[str(i)].append(newname)
os.rename(filename, newname)
# write dict of .Q files
jsonFile = self.prefix + ".qfiles.json"
with open(jsonFile, 'w') as json_file:
json.dump(self.qfiles, json_file)
def get_indlist(self):
string_vtools = "vcf-query -l " + self.vcf_file + " > vcf_indlist.txt"
try:
call = SysCall(string_vtools)
call.run_program()
except:
print(
"vcf-query failed to capture list of individuals from VCF file."
)
print("Check that vcf-query is installed on your system.")
raise SystemExit
def runDistruct(self):
print("Now running distruct for all drawparams files...")
contents = os.listdir(self.nd)
os.chdir(self.nd)
for f in contents:
if f.startswith("drawparams"):
distructCommand = "distruct -d " + str(f) + "; echo"
call = SysCall(distructCommand)
call.run_program()
print("WARNING: Check that distruct ran properly.")
print(
"This program does not check the exit status of DISTRUCT because its exit status always equals 1."
)
print("")
def evalAdmix(self, minK, maxK, np):
ks = range(int(minK), int(maxK)+1)
for k in ks:
for qf in self.qfiles[str(k)]:
print(qf)
temp = qf.split(".")
#make .P file name
temp[-1] = "P"
pf = ".".join(temp)
#make output .corres file name
temp[-1] = "corres"
eAf = ".".join(temp)
#build command for evalAdmix
evalAdmix_str_com = "evalAdmix -plink " + self.prefix + " -fname " + pf + " -qname " + qf + " -o " + eAf + " -P " + str(np)
call = SysCall(evalAdmix_str_com)
call.run_program()
def get_ind_coverage(self):
vcf_command = "vcftools --vcf " + self.vcf_file + " --missing-indv --out " + self.prefix
if (self.removeInds == True):
vcf_command = vcf_command + " --remove " + str(self.removeFile)
call = SysCall(vcf_command)
call.run_program()
fname = self.prefix + ".imiss"
ret = ""
with open(fname, 'r') as fh:
try:
lnum = 0
for line in fh:
line = line.strip()
if not line:
continue
lnum += 1
if lnum < 2: #skip header line
continue
else:
stuff = line.split()
#print(stuff)
if float(stuff[4]) > self.ind:
print("Removing individual %s: %s missing data" %
(stuff[0], stuff[4]))
self.blacklist[stuff[0]] = 1
ret = ret + " --remove-indv " + str(stuff[0])
return (ret)
except IOError as e:
print("Could not read file %s: %s" % (fname, e))
sys.exit(1)
except Exception as e:
print("Unexpected error reading file %s: %s" % (fname, e))
sys.exit(1)
finally:
fh.close()
def print_cv(self):
print("Printing CV values...")
command = "grep -h CV " + self.prefix + "*.stdout > " + self.prefix + "_cv_summary.txt"
grepCall = SysCall(command)
grepCall.run_program()
def makeBED(self): plink_command = "plink --file " + self.prefix + " --make-bed --out " + self.prefix call = SysCall(plink_command) call.run_program()
def recodePlink(self): plink_command = "plink --file " + self.prefix + " --noweb --allow-extra-chr 0 --recode12 --out " + self.prefix call = SysCall(plink_command) call.run_program()
def recodeStructure(self): plink_str_com = "plink --file " + self.prefix + " --allow-extra-chr 0 --recode structure --out " + self.prefix call = SysCall(plink_str_com) call.run_program()