cdscns_string = ""
outcns = open(options.outfileprename + "_cns.fa", 'w')
outaa = open(options.outfileprename + "_aa.fa", 'w')
outcdscns = open(options.outfileprename + "_cdscns.fa", 'w')
cdsmap = {}
if __name__ == '__main__':
if options.genomedepth != None:
depthfile = Util.GATK_depthfile(options.genomedepth,
options.genomedepth + ".index")
species_idx = depthfile.title.index("Depth_for_" + options.species)
Considerdepth = True
else:
Considerdepth = False
depthfile = None
species_idx = -1
vcfpop = VCFutil.VCF_Data(options.variants) # new a class
RefSeqMap, currentChromNO, nextChromNO = Util.getRefSeqMap(
refFastafilehander=reffa)
print(currentChromNO, nextChromNO)
cns_string += currentChromNO + "\n"
gtfMap = Util.getGtfMap(options.gtffile)
lastposofdepthfp = 0 #because this time RefSeqMap[0] is 0
vcfchrom = "begin"
while currentChromNO != "end of the reffile":
print("\t\twhile loop:", currentChromNO)
currentBaselocinGenome = RefSeqMap[currentChromNO][0] + 1
# statue = depthfile.set_depthfilefp(currentChromNO, currentBaselocinGenome, lastposofdepthfp)
# depth_chrom, depth_pos, depth_linelist,lastposofdepthfp = depthfile.getnextposline()
if currentChromNO in gtfMap:
gtfListOfCurrentChrom = gtfMap[currentChromNO]
def make_freq_xaxisKEY_yaxisseqVALUERelation(a):
chromlistfilename = a[0]
topleveltablename = a[1]
targetpopvcffile_withdepthconfig = a[2]
refpopvcffile_withdepthconfig = a[3]
numberofindvdoftargetpop_todividintobin = int(a[4])
mindepthtojudefixed = 20
d_increase = fractions.Fraction(
1, (2 * int(numberofindvdoftargetpop_todividintobin)))
d_increase = round(d_increase, 11)
minvalue = 0.000000000000
freq_xaxisKEY_yaxisVALUE_seq_list = {}
for i in range(numberofindvdoftargetpop_todividintobin * 2 - 1):
freq_xaxisKEY_yaxisVALUE_seq_list[(minvalue, minvalue + d_increase +
0.00000000004)] = []
minvalue += d_increase
else:
freq_xaxisKEY_yaxisVALUE_seq_list[(minvalue, 1)] = []
for a, b in sorted(freq_xaxisKEY_yaxisVALUE_seq_list.keys()):
print(str(a), str(b))
# while minvalue+d_increase<=1:
# freq_xaxisKEY_yaxisVALUE_seq_list[(minvalue,minvalue+d_increase+0.00000000004)]=[]
# print('%.12f'%minvalue,'%.12f'%(minvalue+d_increase+0.00000000004))
# minvalue+=d_increase
# else:
# freq_xaxisKEY_yaxisVALUE_seq_list[]
print("process ID:", os.getpid(), "start", chromlistfilename)
dbvariantstools = dbm.DBTools(Util.ip, Util.username, Util.password,
Util.vcfdbname)
chromlistfile = open(chromlistfilename, "r")
chromlistfilelines = chromlistfile.readlines()
chromlistfile.close()
chromlist = []
for chrrow in chromlistfilelines:
chrrowlist = re.split(r'\s+', chrrow.strip())
chromlist.append((chrrowlist[0].strip(), int(chrrowlist[1].strip())))
vcfnamelist = []
listofpopvcfmapOfAChr = []
methodlist = []
vcfnameKEY_vcfobj_pyBAMfilesVALUE = {}
N_of_targetpop = len(targetpopvcffile_withdepthconfig)
N_of_refpop = len(refpopvcffile_withdepthconfig)
#{ vcftablename1:[depthfilename1,name1,name2] , vcftablename2:[depthfilename2,name1,name2] } or {vcftablename1:None, vcftablename2:None}
for vcfconfigfilename in targetpopvcffile_withdepthconfig[:] + refpopvcffile_withdepthconfig[:]:
listofpopvcfmapOfAChr.append({})
vcfconfig = open(vcfconfigfilename, "r")
for line in vcfconfig:
vcffilename_obj = re.search(r"vcffilename=(.*)", line.strip())
if vcffilename_obj != None:
vcfname = vcffilename_obj.group(1).strip()
vcfnamelist.append(vcfname)
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname] = []
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname].append(
VCFutil.VCF_Data(vcfname))
elif line.split():
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname].append(
pysam.Samfile(line.strip(), 'rb'))
vcfconfig.close()
if re.search(r"indvd[^/]+", vcfname) != None:
methodlist.append("indvd")
elif re.search(r"pool[^/]+", vcfname) != None:
methodlist.append("pool")
else:
print("vcfname must with 'pool' or 'indvd'")
exit(-1)
for currentchrID, currentchrLen in chromlist:
for vcfname in vcfnamelist:
if currentchrID in vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname][
0].VcfIndexMap:
break
else:
print("this chr doesn't exist in anypop")
continue
for vcfobj_idx in range(len(vcfnamelist)):
listofpopvcfmapOfAChr[vcfobj_idx] = {}
listofpopvcfmapOfAChr[vcfobj_idx][
currentchrID] = vcfnameKEY_vcfobj_pyBAMfilesVALUE[
vcfnamelist[vcfobj_idx]][0].getVcfListByChrom(currentchrID)
target_ref_SNPs = Util.alinmultPopSnpPos(listofpopvcfmapOfAChr, "o")
for snp_aligned in target_ref_SNPs[currentchrID]:
if len(snp_aligned[1]) != 1 or len(snp_aligned[2]) != 1:
print("multple allele", snp_aligned)
continue
curpos = int(snp_aligned[0])
snp = dbvariantstools.operateDB(
"select",
"select * from " + topleveltablename + " where chrID='" +
currentchrID + "' and snp_pos=" + str(curpos) + "")
if not snp or snp == 0:
print(currentchrID, curpos, "snp not find in db,skip")
continue
else: #judge the ancenstrall allele
fanyadepthlist = re.split(r",", snp[0][9])
if len(fanyadepthlist) == 2 and int(
fanyadepthlist[1]
) >= mindepthtojudefixed and fanyadepthlist[0].strip() == "0":
A_base_idx = 1
elif len(fanyadepthlist) == 2 and int(
fanyadepthlist[0]
) >= mindepthtojudefixed and fanyadepthlist[1].strip() == "0":
A_base_idx = 0
else:
print("skip snp", snp[0][1], snp[0][7:])
continue
ancestrallcontext = snp[0][5].strip()[0].upper() + snp[0][
3 + A_base_idx].strip().upper() + snp[0][5].strip()[2].upper()
if "CG" in ancestrallcontext or "GC" in ancestrallcontext:
print("skip CG site", ancestrallcontext)
continue
##########x-axis
countedAF = 0
target_DAF_sum = 0 #;noofnocoveredsample=0
for i in range(3, N_of_targetpop + 3):
if snp_aligned[i] == None:
if len(vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfnamelist[
i - 3]]) == 1:
print("no depth file")
continue
else:
sum_depth = 0
for samfile in vcfnameKEY_vcfobj_pyBAMfilesVALUE[
vcfnamelist[i - 3]][1:]:
ACGTdep = samfile.count_coverage(
currentchrID, curpos - 1, curpos)
for dep in ACGTdep:
sum_depth += dep[0]
if sum_depth >= mindepthtojudefixed:
AF = 0
else:
continue
else:
if methodlist[i - 3] == "indvd":
AF = float(
re.search(r"AF=([\d\.]+);",
snp_aligned[i][0]).group(1))
elif methodlist[i - 3] == "pool":
refdep = 0
altalleledep = 0
AD_idx = (re.split(":", snp_aligned[i][1])).index(
"AD") # gatk GT:AD:DP:GQ:PL
for sample in snp_aligned[i][2]:
if len(re.split(":", sample)) == 1: # ./.
continue
AD_depth = re.split(",",
re.split(":", sample)[AD_idx])
try:
refdep += int(AD_depth[0])
altalleledep += int(AD_depth[1])
except ValueError:
print(sample, end="|")
if refdep == altalleledep and altalleledep == 0:
print("no sample available in this pop")
# noofnocoveredsample+=1
continue
AF = altalleledep / (altalleledep + refdep)
if A_base_idx == 0:
DAF = 1 - AF
elif A_base_idx == 1:
DAF = AF
target_DAF_sum += DAF
countedAF += 1
if countedAF == 0: #or target_DAF_sum==0:
print(
"skip this snp,because it fiexd as ancestral or no covered in this pos in target pops",
snp_aligned, snp)
continue
target_DAF = target_DAF_sum / countedAF
###############y-axis
countedAF = 0
rer_DAF_sum = 0
for i in range(3 + N_of_targetpop,
N_of_refpop + N_of_targetpop + 3):
if snp_aligned[i] == None:
if len(vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfnamelist[
i - 3]]) == 1:
continue
else:
# depth_linelist=vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfnamelist[i-3-N_of_targetpop]].getdepthByPos_optimized(currentchrID,curpos)
sum_depth = 0
for samfile in vcfnameKEY_vcfobj_pyBAMfilesVALUE[
vcfnamelist[i - 3]][1:]:
ACGTdep = samfile.count_coverage(
currentchrID, curpos - 1, curpos)
for dep in ACGTdep:
sum_depth += dep[0]
if sum_depth >= mindepthtojudefixed:
AF = 0
else:
continue
else:
if methodlist[i - 3] == "indvd":
AF = float(
re.search(r"AF=([\d\.]+);",
snp_aligned[i][0]).group(1))
AN = float(
re.search(r"AN=([\d\.]+);",
snp_aligned[i][0]).group(1))
if AN < 5:
continue
elif methodlist[i - 3] == "pool":
refdep = 0
altalleledep = 0
AD_idx = (re.split(":", snp_aligned[i][1])).index(
"AD") # gatk GT:AD:DP:GQ:PL
for sample in snp_aligned[i][2]:
if len(re.split(":", sample)) == 1: # ./.
continue
AD_depth = re.split(",",
re.split(":", sample)[AD_idx])
try:
refdep += int(AD_depth[0])
altalleledep += int(AD_depth[1])
except ValueError:
print(sample, end="|")
if (refdep == altalleledep and altalleledep
== 0) or altalleledep + refdep < 10:
continue
AF = altalleledep / (altalleledep + refdep)
if A_base_idx == 0:
DAF = 1 - AF
elif A_base_idx == 1:
DAF = AF
rer_DAF_sum += DAF
countedAF += 1
if countedAF == 0 or rer_DAF_sum == 0:
print(
"skip this snp,because it no covered in this pos in ref pops",
snp_aligned, snp)
continue
######collect according bins
for a, b in sorted(freq_xaxisKEY_yaxisVALUE_seq_list.keys()):
if target_DAF > a and target_DAF <= b:
freq_xaxisKEY_yaxisVALUE_seq_list[(a, b)].append(
rer_DAF_sum / countedAF)
break
# freq_xaxisKEY_yaxisVALUERelation={}
# for a,b in sorted(freq_xaxisKEY_yaxisVALUE_seq_list.keys()):
# freq_xaxisKEY_yaxisVALUERelation[(a,b)]=numpy.mean(freq_xaxisKEY_yaxisVALUE_seq_list[(a,b)])
# print('%.12f'%a,'%.12f'%(b),'%.12f'%(freq_xaxisKEY_yaxisVALUERelation[(a,b)]),"process ID:",os.getpid(),"done",sep="\t")
print("process ID:", os.getpid(), "done")
return copy.deepcopy(freq_xaxisKEY_yaxisVALUE_seq_list)
sitesingap = open(sys.argv[5], 'w')
if __name__ == '__main__':
win = Util.Window()
i = 0
interferf = open(sys.argv[5] + ".InterferingTEMP", 'w')
for gapregion in gapf:
i += 1
filledsites = []
gaplist = re.split(r"\s+", gapregion.strip())
if not os.path.exists(sys.argv[5] + "temp" + str(i) + ".recode.vcf"):
os.system(
vcftools + " --vcf " + sys.argv[2] +
" --recode --recode-INFO-all --remove-indv DSW33216 --chr " +
gaplist[0] + " --from-bp " + str(gaplist[1]) + " --to-bp " +
str(gaplist[2]) + " --out " + sys.argv[5] + "temp" + str(i))
vcfobj = VCFutil.VCF_Data(sys.argv[5] + "temp" + str(i) +
".recode.vcf")
vcflist = vcfobj.getVcfListByChrom(gaplist[0], MQfilter=0)
findtagcaculator = Caculators.CaculatorToFindTAGs(
mod="randomvcf", Interferingf=interferf)
findtagcaculator.curchrom = gaplist[0]
win.slidWindowOverlap(vcflist, int(gaplist[2]), winsize, winsize,
findtagcaculator, int(gaplist[1]))
filledsites = copy.deepcopy(win.winValueL)
for s, e, n, poss in filledsites:
if poss[0] != "NA":
RefSeqMap = Util.getRefSeqBypos_faster(reff, refidx,
gaplist[0],
poss[0][0] - 35,
poss[0][0] + 35,
chrlenm[gaplist[0]])
dilute = 1
else:
print("error")
exit(-1)
print(chromlisttosub)
software = options.software.upper().strip()
Morganperbp = float(options.Morganperbp)
chromlistfile = open(options.chromlistfilename, "r")
chromlist = []
for chrrow in chromlistfile:
chrrowlist = re.split(r'\s+', chrrow.strip())
chromlist.append(chrrowlist[0].strip())
tempvcffile = open(outputprefix + ".vcf", "w")
if __name__ == '__main__':
vcfdata = VCFutil.VCF_Data(options.vcffilename.strip())
i = 0
outputfilepart = 0
sumRecOfVCF = 0
if chromlisttosub == None:
lastpos = 0
for chrom in chromlist:
if chrom not in vcfdata.chromOrder:
continue
vcfRecOfAChrom = vcfdata.getVcfListByChrom(
chrom, dilute, dilutetodensity=dilutetodensity)
if len(vcfRecOfAChrom) < 30:
print("Call_geno_snp_ind_Style_software_cyclly",
"skip chrom with snps less than 100")
continue
else:
affectedlist = []
unaffectedlist = []
affectunaffectmark = {}
f = open(options.affectedlist, 'r')
for line in f:
affectedlist.append(line.strip())
affectunaffectmark[line.strip()] = "2"
f.close()
f = open(options.unaffectedlist, 'r')
for line in f:
affectunaffectmark[line.strip()] = "1"
f.close()
mapfile = open(options.output + ".map", "w")
pedfile = open(options.output + ".ped", "w")
vcfobj = VCFutil.VCF_Data(options.vcffile[0])
chromchangemap = {}
excludesitesMapBchr = {}
f = open(options.chrommap, 'r')
for line in f:
linelist = re.split(r'\s+', line.strip())
chromchangemap[linelist[0].strip()] = linelist[1].strip()
f.close()
f = open(options.excludesites, 'r')
for line in f:
linelist = re.split(r'\s+', line.strip())
if linelist[0] in excludesitesMapBchr:
excludesitesMapBchr[linelist[0]].append(int(linelist[1]))
else:
excludesitesMapBchr[linelist[0]] = [int(linelist[1])]
default=True,
help="don't print status messages to stdout")
(options, args) = parser.parse_args()
vcfnameKEY_vcfobj_pyBAMfilesVALUE = {}
if options.ancenstralref == None:
archicpopvcfbamconfig = options.vcfbamconfig.strip()
vcfconfig = open(archicpopvcfbamconfig, "r")
for line in vcfconfig:
vcffilename_obj = re.search(r"vcffilename=(.*)", line.strip())
if vcffilename_obj != None:
vcfname = vcffilename_obj.group(1).strip()
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname] = []
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname].append(
VCFutil.VCF_Data(vcfname))
elif line.split():
vcfnameKEY_vcfobj_pyBAMfilesVALUE[vcfname].append(
pysam.Samfile(line.strip(), 'rb'))
vcfconfig.close()
toplevelsnptablename = options.toplevelsnptable
flanklen = int(options.flanklen.strip())
if __name__ == '__main__':
ancestralalleletabletools = AncestralAlleletabletools(
database=Util.vcfdbname,
ip=Util.ip,
usrname=Util.username,
pw=Util.password,
dbgenome=Util.genomeinfodbname)
if options.mode.strip() == "1":
for k, v in MfileNameMap.items():
if k in VfileNameMap:
VtoMmap[VfileNameMap[k]] = v
print(VfileNameMap[k], v, sep="\t", file=mf)
mf.close()
myformatNamelist = []
f = open(options.myformatNamelistfile, "r")
for my_Sample_name in f:
myformatNamelist.append(my_Sample_name.strip())
f.close()
#find the same indvd END
refFastahandle1 = open(refFastaName1, 'r')
refFastahandle2 = open(refFastaName2, 'r')
vcfdataset = VCFutil.VCF_Data(options.vcffilename)
for k, v in VtoMmap.items():
commsample_idxlistinM.append(myformatNamelist.index(v))
commsample_idxlistinV.append(vcfdataset.VcfIndexMap["title"].index(k))
#
# bbb=Util.getRefSeqBypos_faster(refFastahandle, refidxByChr, "1", 1, 1)
# print(bbb)
# exit()
for chrom in vcfdataset.chromOrder:
vcfRecOfAChrom = vcfdataset.getVcfListByChrom(chrom, MQfilter=None)
MFfRecOfAChrom = []
#read -M file and change format
try:
curMyFormatfile = open(
'Chr0' + chrom + options.myformatfilesuffix.strip(), 'r')
def fillarchicpop(self,
archicpopVcfFile,
depthFile,
chromtable,
archicpopNameindepthFile,
tablename="derived_alle_ref",
archicpopfieldNameintable="archicpop"):
"""
abandon the snps which exist in archicpopVcfFile but absence in all others pop snp sets
"""
depthfile = Util.GATK_depthfile(depthFile, depthFile + ".index")
species_idx = depthfile.title.index("Depth_for_" +
archicpopNameindepthFile)
archicpop = VCFutil.VCF_Data(archicpopVcfFile)
totalChroms = self.dbtools.operateDB(
"select", "select count(*) from " + chromtable)[0][0]
for i in range(0, totalChroms, 20):
currentsql = "select * from " + chromtable + " order by chrlength desc limit " + str(
i) + ",20"
result = self.dbtools.operateDB("select", currentsql)
for row in result:
currentchrID = row[0]
print(currentchrID + ":", end="")
currentchrLen = int(row[2])
archicpopSeqOfAChr = {}
archicpopSeqOfAChr[currentchrID] = archicpop.getVcfListByChrom(
archicpopVcfFile, currentchrID)
allsnpsInAchr = self.dbtools.operateDB(
"select", "select snp_pos,alt_base from " + tablename +
" where chrID='" + currentchrID + "'")
for snp in allsnpsInAchr:
snp_pos = int(snp[0])
ALT = snp[1]
low = 0
high = len(archicpopSeqOfAChr[currentchrID]) - 1
while low <= high:
mid = (low + high) >> 1
if archicpopSeqOfAChr[currentchrID][mid][0] < snp_pos:
low = mid + 1
elif archicpopSeqOfAChr[currentchrID][mid][0] > snp_pos:
high = mid - 1
else: #find the pos
pos, REF, ALT, INFO, FORMAT, samples = archicpopSeqOfAChr[
currentchrID][mid]
dp4 = re.search(r"DP4=(\d*),(\d*),(\d*),(\d*)",
INFO)
refdep = 0
altalleledep = 0
if dp4 != None: #vcf from samtools
refdep = int(dp4.group(1)) + int(dp4.group(2))
altalleledep = int(dp4.group(3)) + int(
dp4.group(4))
else:
AD_idx = (re.split(":", FORMAT)).index(
"AD") #gatk GT:AD:DP:GQ:PL
for sample in samples:
if len(re.split(":", sample)) == 1: # ./.
continue
AD_depth = re.split(
",",
re.split(":", sample)[AD_idx])
try:
refdep += int(AD_depth[0])
altalleledep += int(AD_depth[1])
except ValueError:
print(sample, end="")
popsdata = ALT + ":" + str(refdep) + "," + str(
altalleledep)
break
else:
depth_linelist = depthfile.getdepthByPos(
currentchrID, snp_pos)
if int(depth_linelist[species_idx]) <= 1:
popsdata = "no covered"
else:
popsdata = ALT + ":" + depth_linelist[
species_idx] + ",0"
# print(snp[0],end="\t")
self.dbtools.operateDB(
"update", "update " + tablename + " set " +
archicpopfieldNameintable + " = '" + popsdata +
"' where chrID=" + "'" + currentchrID +
"' and snp_pos=" + str(snp[0]))
def filldata(self,
vcfFileName,
depthfileName,
tablename="derived_alle_ref",
posUniq=True,
continuechrom=None,
continuepos=None):
depthfile = Util.GATK_depthfile(depthfileName,
depthfileName + ".index")
depth_linelist = None
vcffile = open(vcfFileName, 'r')
vcfline = vcffile.readline()
while re.search(r'^##', vcfline) != None:
vcfline = vcffile.readline()
if re.search(r'^#', vcfline) != None:
poptitlelist = re.split(r'\s+', vcfline.strip())[9:]
print(poptitlelist)
else:
print(
"need title'#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT'"
)
exit(-1)
for pop in poptitlelist:
self.dbtools.operateDB("callproc",
"mysql_sp_add_column",
data=("life_pilot", tablename, pop,
"varchar(128)", "default null"))
popsdata = [] #depth for ref or alt
if continuechrom != None and continuepos != None:
print("filldata", continuechrom, continuepos)
vcfpossearcher = VCFutil.VCF_Data(vcfFileName)
vcffile.seek(vcfpossearcher.VcfIndexMap[continuechrom])
vcfline = vcffile.readline()
while vcfline:
vcflist = re.split(r'\s+', vcfline.strip())
chrom = vcflist[0].strip()
pos = int(vcflist[1].strip())
print(chrom, pos)
if chrom == continuechrom and pos == continuepos:
break
vcfline = vcffile.readline()
else:
justiceGATKorSamtools = vcffile.readline()
vcflist = re.split(r'\s+', justiceGATKorSamtools.strip())
dp4 = re.search(r"DP4=(\d*),(\d*),(\d*),(\d*)", vcflist[7])
refdep = 0
altalleledep = 0
if dp4 != None: #vcf from samtools
print("function for samtools vcf is still need to be finish")
exit(-1)
else:
chrom = vcflist[0].strip()
pos = int(vcflist[1].strip())
snpID = vcflist[2].strip()
REF = vcflist[3].strip()
ALT = vcflist[4].strip()
AD_idx = (re.split(":", vcflist[8])).index(
"AD") #gatk GT:AD:DP:GQ:PL
sample_idx_in_vcf = 0
for sample in vcflist[9:]:
samplename = poptitlelist[sample_idx_in_vcf]
sample_idx_in_vcf += 1
species_idx = depthfile.title.index("Depth_for_" +
samplename)
if len(re.split(":", sample)) != len(
re.split(":", vcflist[8])
) and depth_linelist == None: # ./. when lack of variantion information,then consider the depthfile
depth_linelist = depthfile.getdepthByPos(chrom, pos)
if int(depth_linelist[species_idx]) <= 1:
popsdata.append('no covered')
else:
popsdata.append(depth_linelist[species_idx] + ",0")
continue
elif len(re.split(":", sample)) != len(
re.split(":",
vcflist[8])) and depth_linelist != None:
if int(depth_linelist[species_idx]) <= 1:
popsdata.append('no covered')
else:
popsdata.append(depth_linelist[species_idx] + ",0")
continue
popsdata.append(re.split(":", sample)[AD_idx])
depth_linelist = None
print(
"insert into " + tablename +
"(chrID,snp_pos,snpID,ref_base,alt_base," +
"".join([e + ","
for e in poptitlelist[:-1]] + poptitlelist[-1:]) +
") select %s,%s,%s,%s,%s," + "%s," *
(len(poptitlelist) - 1) +
"%s from dual where not exists( select * from " +
tablename + " where " + tablename + ".chrID='" + chrom +
"' and " + tablename + ".snp_pos=" + str(pos) + ")",
(chrom, pos, snpID, REF, ALT) + tuple(popsdata))
self.dbtools.operateDB(
"insert",
"insert into " + tablename +
"(chrID,snp_pos,snpID,ref_base,alt_base," +
"".join([e + ","
for e in poptitlelist[:-1]] + poptitlelist[-1:]) +
") select %s,%s,%s,%s,%s," + "%s," *
(len(poptitlelist) - 1) +
"%s from dual where not exists( select * from " +
tablename + " where " + tablename + ".chrID='" + chrom +
"' and " + tablename + ".snp_pos=" + str(pos) + ")",
data=(chrom, pos, snpID, REF, ALT) + tuple(popsdata))
for vcfline in vcffile:
vcflist = re.split(r'\s+', vcfline.strip())
print(vcfline)
if posUniq and pos == int(vcflist[1].strip()):
continue
chrom = vcflist[0].strip()
pos = int(vcflist[1].strip())
snpID = vcflist[2].strip()
REF = vcflist[3].strip()
ALT = vcflist[4].strip()
AD_idx = (re.split(":",
vcflist[8])).index("AD") #gatk GT:AD:DP:GQ:PL
sample_idx_in_vcf = 0
popsdata = []
for sample in vcflist[9:]:
samplename = poptitlelist[sample_idx_in_vcf]
sample_idx_in_vcf += 1
species_idx = depthfile.title.index("Depth_for_" + samplename)
if len(re.split(":", sample)) != len(re.split(
":", vcflist[8])) and depth_linelist == None: # ./.
depth_linelist = depthfile.getdepthByPos(chrom, pos)
if int(depth_linelist[species_idx]) <= 1:
popsdata.append('no covered')
else:
popsdata.append(depth_linelist[species_idx] + ",0")
continue
elif len(re.split(":", sample)) != len(
re.split(":", vcflist[8])) and depth_linelist != None:
if int(depth_linelist[species_idx]) <= 1:
popsdata.append('no covered')
else:
popsdata.append(depth_linelist[species_idx] + ",0")
continue
# AD_depth = re.split(",", re.split(":", sample)[AD_idx])
popsdata.append(re.split(":", sample)[AD_idx])
depth_linelist = None
print(
"insert into " + tablename +
"(chrID,snp_pos,snpID,ref_base,alt_base," +
"".join([e + ","
for e in poptitlelist[:-1]] + poptitlelist[-1:]) +
") select %s,%s,%s,%s,%s," + "%s," * (len(poptitlelist) - 1) +
"%s from dual where not exists( select * from " + tablename +
" where " + tablename + ".chrID='" + chrom + "' and " +
tablename + ".snp_pos=" + str(pos) + ")",
(chrom, pos, snpID, REF, ALT) + tuple(popsdata))
self.dbtools.operateDB(
"insert",
"insert into " + tablename +
"(chrID,snp_pos,snpID,ref_base,alt_base," +
"".join([e + ","
for e in poptitlelist[:-1]] + poptitlelist[-1:]) +
") select %s,%s,%s,%s,%s," + "%s," * (len(poptitlelist) - 1) +
"%s from dual where not exists( select * from " + tablename +
" where " + tablename + ".chrID='" + chrom + "' and " +
tablename + ".snp_pos=" + str(pos) + ")",
data=(chrom, pos, snpID, REF, ALT) + tuple(popsdata))
depthfile.closedepthfile()
vcffile.close()
"--outfileprename",
dest="outfileprename",
help="default infile1_infile2")
parser.add_option("-2",
"--ancenstral_or_derived",
dest="ancenstral_or_derived",
default="d",
help="ancenstral(a) or derived(d)")
(options, args) = parser.parse_args()
mindeptojudgefix = 15
#####################
VCFobj = {}
vcfnameKEY_depthfilename_titlenameVALUE_tojudgeancestrall = {}
vcfnameKEY_depthobjVALUE_tojudgeancestral = {}
VCFobj["wigeon"] = VCFutil.VCF_Data(
"/home/bioinfo/liurui/data/vcffiles/uniqmap/taihudomesticgoose/taihudomesticgoose.pool.withindel.vcf"
)
VCFobj["fanya"] = VCFutil.VCF_Data(
"/home/bioinfo/liurui/data/vcffiles/uniqmap/fanya/fanya._pool.withindel.vcf"
)
vcfnameKEY_depthfilename_titlenameVALUE_tojudgeancestrall[
"wigeon"] = Util.GATK_depthfile(
"/home/bioinfo/liurui/data/depth/g_j_sm_k_l_y_f_w_pool/gjsmklyfw_gatk.depth",
"/home/bioinfo/liurui/data/depth/g_j_sm_k_l_y_f_w_pool/gjsmklyfw_gatk.depth.index"
) #here is a temp trick not a error
vcfnameKEY_depthfilename_titlenameVALUE_tojudgeancestrall[
"fanya"] = Util.GATK_depthfile(
"/home/bioinfo/liurui/data/depth/g_j_sm_k_l_y_f_w_pool/gjsmklyfw_gatk.depth",
"/home/bioinfo/liurui/data/depth/g_j_sm_k_l_y_f_w_pool/gjsmklyfw_gatk.depth.index"
)
vcfnameKEY_depthobjVALUE_tojudgeancestral["wigeon"] = [