def varscan2(self):
reference = self.reference
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
bedFile = self.bed
threads = self.threads
MAF = self.MAF
DP = self.filtDP
minCov = str(int(int(DP) * float(MAF)))
tmpDir = resultsDir + "/tempFile/varscan2_" + sampleID
mkdir(tmpDir)
vs = "/home/bioinfo/ubuntu/software/VarScan.v2.3.9/VarScan.v2.3.9.jar"
if pairID == None:
print("varscan2仅适用于配对分析，请指定配对样本并重新运行")
exit()
cmd = """
samtools mpileup -B -f {reference} -q 15 -d 10000 \\
{resultsDir}/bam/{pairID}.bam {resultsDir}/bam/{sampleID}.bam \\
| java -jar {vs} somatic -mpileup {tmpDir}/{sampleID} \\
--min-coverage-normal {minCov} --min-coverage-tumor {minCov} \\
--min-var-freq {MAF} --strand-filter 1 --output-vcf
bcftools reheader -f {reference}.fai {tmpDir}/{sampleID}.indel.vcf -o {tmpDir}/{sampleID}.indel.fix.vcf
bcftools reheader -f {reference}.fai {tmpDir}/{sampleID}.snp.vcf -o {tmpDir}/{sampleID}.snp.fix.vcf
""".format(reference=reference, resultsDir=resultsDir, pairID=pairID, sampleID=sampleID, vs=vs, tmpDir=tmpDir, minCov=minCov, MAF=MAF)
print(cmd)
os.system(cmd)
def annovar(self):
humandb = self.runningInfo["setting"]["Annotation"]["humandb"]
buildver = self.runningInfo["setting"]["Annotation"]["buildver"]
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
threads = self.threads
tmpDir = resultsDir + "/tempFile/annovar_" + sampleID
mkdir(tmpDir)
self.snpeff()
cmd = """
convert2annovar.pl -format vcf4 \\
{resultsDir}/annotation/{sampleID}.snpeff.vcf \\
--includeinfo > {tmpDir}/{sampleID}.avinput
table_annovar.pl {tmpDir}/{sampleID}.avinput \\
{humandb} -buildver {buildver} \\
-out {tmpDir}/{sampleID} -remove \\
-protocol refGene,avsnp150,gnomad211_genome,clinvar_20210308,JaxCkb,Civic,OncoKB,dbnsfp41a,cosmic92_coding,intervar_20180118 \\
-operation g,f,f,f,f,f,f,f,f,f \\
-nastring - -thread {threads} -otherinfo
cp {tmpDir}/{sampleID}.{buildver}_multianno.txt {resultsDir}/annotation/
""".format(tmpDir=tmpDir,
resultsDir=resultsDir,
sampleID=sampleID,
humandb=humandb,
threads=threads,
buildver=buildver)
print(cmd)
os.system(cmd)
def msisensor_pro(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
msi_baseline = self.runningInfo["setting"]["Other"]["msisensorpro_baseline"]
msi_list = self.runningInfo["setting"]["Other"]["msi_list"]
tmpDir = resultsDir + "/tempFile/msisensorpro_" + sampleID
mkdir(tmpDir)
if pairID == None:
cmd = """
msisensor-pro pro -d {msi_list} \\
-t {resultsDir}/bam/{sampleID}.bam \\
-o {tmpDir}/{sampleID}
mv {tmpDir}/{sampleID} {tmpDir}/{sampleID}.txt
cp {tmpDir}/{sampleID}.txt {resultsDir}/msi/{sampleID}.MSIsensorp.txt
""".format(msi_list=msi_list, resultsDir=resultsDir, sampleID=sampleID, tmpDir=tmpDir)
else:
cmd = """
msisensor-pro msi -d {msi_list} \\
-n {resultsDir}/bam/{pairID}.bam \\
-t {resultsDir}/bam/{sampleID}.bam \\
-o {tmpDir}/{sampleID}
mv {tmpDir}/{sampleID} {tmpDir}/{sampleID}.txt
cp {tmpDir}/{sampleID}.txt {resultsDir}/msi/{sampleID}.MSIsensorp.txt
""".format(msi_list=msi_list, resultsDir=resultsDir, pairID=pairID, sampleID=sampleID, tmpDir=tmpDir)
print(cmd)
os.system(cmd)
def bcftools(self):
reference = self.reference
resultsDir = self.output
sampleID = self.sample
bedFile = self.bed
threads = self.threads
tmpDir = resultsDir + "/tempFile/bcftools_" + sampleID
mkdir(tmpDir)
if bedFile != None:
cmd = """
bcftools mpileup -f {reference} \\
{resultsDir}/bam/{sampleID}.bam \\
| bcftools call -mv -O v \\
-o {tmpDir}/{sampleID}.bcftools.vcf \\
-t {threads} -R {bedFile}
""".format(bedFile=bedFile, reference=reference, resultsDir=resultsDir, sampleID=sampleID, tmpDir=tmpDir)
else:
cmd = """
bcftools mpileup -f {reference} \\
{resultsDir}/bam/{sampleID}.bam \\
| bcftools call -mv -O v \\
-o {tmpDir}/{sampleID}.bcftools.vcf \\
-t {threads}
""".format(bedFile=bedFile, reference=reference, resultsDir=resultsDir, sampleID=sampleID, tmpDir=tmpDir)
print(cmd)
os.system(cmd)
def hlahd(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
buildver = self.buildver
threads = self.threads
# 以下数据库无需指定参考基因坐标，为通用数据库，因此不写入配置文件中
freq = "/home/bioinfo/ubuntu/software/hlahd.1.3.0/freq_data"
dictionary = "/home/bioinfo/ubuntu/software/hlahd.1.3.0/dictionary"
split_file = "/home/bioinfo/ubuntu/software/hlahd.1.3.0/HLA_gene.ABC.txt"
tmpDir = resultsDir + "/tempFile/hlahd_" + sampleID
self.tmpDir = tmpDir
mkdir(tmpDir)
self.extractHLA()
if pairID != None:
sampleID = pairID
cmd = """
hlahd.sh -t {threads} -m 100 -c 0.95 -f {freq} \\
{tmpDir}/{sampleID}.HLA.R1.fastq {tmpDir}/{sampleID}.HLA.R2.fastq \\
{split_file} {dictionary} {sampleID} {tmpDir}
cp {tmpDir}/{sampleID}/result/{sampleID}_final.result.txt {resultsDir}/HLA/{sampleID}.hlahd.txt
""".format(threads=threads,
freq=freq,
split_file=split_file,
dictionary=dictionary,
resultsDir=resultsDir,
sampleID=sampleID,
tmpDir=tmpDir)
print(cmd)
os.system(cmd)
def optitype(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
buildver = self.buildver
threads = self.threads
optipipe = "/home/bioinfo/ubuntu/software/OptiType-1.3.5/OptiTypePipeline.py"
tmpDir = resultsDir + "/tempFile/optitype_" + sampleID
self.tmpDir = tmpDir
mkdir(tmpDir)
self.extractHLA()
if pairID != None:
sampleID = pairID
cmd = """
python {optipipe} \\
-i {tmpDir}/{sampleID}.HLA.R1.fastq {tmpDir}/{sampleID}.HLA.R2.fastq \\
-d -o {tmpDir} -p {sampleID} -v
cp {tmpDir}/{sampleID}_result.tsv {resultsDir}/HLA/{sampleID}.optitype.txt
""".format(optipipe=optipipe,
tmpDir=tmpDir,
sampleID=sampleID,
resultsDir=resultsDir)
print(cmd)
os.system(cmd)
def seq2hla(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
buildver = self.buildver
threads = self.threads
tmpDir = resultsDir + "/tempFile/seq2hla_" + sampleID
self.tmpDir = tmpDir
mkdir(tmpDir)
self.extractHLA()
if pairID != None:
sampleID = pairID
s2h = "/home/bioinfo/ubuntu/software/seq2HLA/seq2HLA.py"
cmd = """
python {s2h} \\
-1 {tmpDir}/{sampleID}.HLA.R1.fastq \\
-2 {tmpDir}/{sampleID}.HLA.R2.fastq \\
-r {tmpDir}/{sampleID} -p {threads}
cp {tmpDir}/{sampleID}-ClassI-class.HLAgenotype4digits {resultsDir}/HLA/{sampleID}.seq2HLA.txt
""".format(s2h=s2h,
tmpDir=tmpDir,
sampleID=sampleID,
threads=threads,
resultsDir=resultsDir)
print(cmd)
os.system(cmd)
# end
def snpeff(self):
humandb = self.runningInfo["setting"]["Annotation"]["humandb"]
buildver = self.runningInfo["setting"]["Annotation"]["buildver"]
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
if pairID == None:
vcfFile = resultsDir + "/vcf/" + sampleID + ".vcf"
else:
vcfFile = resultsDir + "/vcf/" + sampleID + ".filter.vcf"
tmpDir = resultsDir + "/tempFile/snpeff_" + sampleID
mkdir(tmpDir)
cmd = """
java -jar /home/bioinfo/ubuntu/software/snpEff/snpEff.jar \\
-c /home/bioinfo/ubuntu/software/snpEff/snpEff.config \\
-s {tmpDir}/{sampleID}.summary.html \\
{buildver} {vcfFile} > {tmpDir}/{sampleID}.snpeff.vcf
cp {tmpDir}/{sampleID}.snpeff.vcf {resultsDir}/annotation/
""".format(buildver=buildver,
vcfFile=vcfFile,
tmpDir=tmpDir,
sampleID=sampleID,
resultsDir=resultsDir)
print(cmd)
os.system(cmd)
def neopredpipe(self):
sampleID = self.sample
pairID = self.pair
resultsDir = self.output
threads = self.threads
buildver = self.buildver
NeoPred = "/home/bioinfo/ubuntu/software/NeoPredPipe-1.1/NeoPredPipe.py"
tmpDir = resultsDir + "/tempFile/Neoantigen_" + sampleID
mkdir(tmpDir)
vcf = resultsDir + "/vcf/" + sampleID + ".filter.vcf"
vcfDir = tmpDir + "/vcf"
mkdir(vcfDir)
shutil.copy(vcf, vcfDir + "/" + sampleID + ".vcf")
self.extractHLAResults()
cmd = """
python {NeoPred} \\
-I {tmpDir}/vcf \\
-H {tmpDir}/{sampleID}.hlas \\
-o {tmpDir} \\
-n {sampleID} \\
-c 0
sed '1iSample\\tR\\tLine\\tchrom\\tallelepos\\tref\\talt\\tGeneName\\tpos\\thla\\tpeptide\\tcore\\tOf\\tGp\\tGl\\tIp\\tIl\\tIcore\\tIdentity\\tScore_EL\\t%Rank_EL\\tScore_BA\\t%Rank_BA\\tAff(nM)\\tCandidate\\tBindLevel\\tNovelty' \\
{tmpDir}/{sampleID}.neoantigens.txt > {tmpDir}/{sampleID}.neoantigens.tsv
cp {tmpDir}/{sampleID}.neoantigens.tsv {resultsDir}/Neoantigen/
""".format(NeoPred=NeoPred,
vcf=vcf,
tmpDir=tmpDir,
sampleID=sampleID,
resultsDir=resultsDir)
print(cmd)
os.system(cmd)
def pisces(self):
"""
需建立索引
dotnet CreateGenomeSizeFile.dll \
-g hg19/ \
-s "H**o sapiens (UCSC hg19)" \
-o hg19/
"""
database = self.databases
resultsDir = self.output
sampleID = self.sample
bedFile = self.bed
threads = self.threads
minDP = self.filtDP
minMAF = self.MAF
piscesBin = "/home/bioinfo/ubuntu/software/Pisces_5.2.10.49/Pisces.dll"
tmpDir = resultsDir + "/tempFile/pisces_" + sampleID
mkdir(tmpDir)
if bedFile != None:
cmd = """
dotnet {piscesBin} -b {resultsDir}/bam/{sampleID}.bam \\
-g {database} \\
-o {tmpDir} \\
-t {threads} \\
-i {bedFile} \\
--mindp {minDP} \\
--minvf {minMAF} \\
--minvq 0 --threadbychr true
""".format(bedFile=bedFile, minDP=minDP, minMAF=minMAF, piscesBin=piscesBin, resultsDir=resultsDir, sampleID=sampleID, database=database, tmpDir=tmpDir, threads=threads)
else:
cmd = """
dotnet {piscesBin} -b {resultsDir}/bam/{sampleID}.bam \\
-g {database} \\
-o {tmpDir} \\
-t {threads} \\
--mindp {minDP} \\
--minvf {minMAF} \\
--minvq 0 --threadbychr true
""".format(minDP=minDP, minMAF=minMAF, piscesBin=piscesBin, resultsDir=resultsDir, sampleID=sampleID, database=database, tmpDir=tmpDir, threads=threads)
print(cmd)
os.system(cmd)
filt = """
bcftools view \\
-e "GT='0/0' | GT='./.' | GT='0/.'" \\
{tmpDir}/{sampleID}.genome.vcf > {tmpDir}/{sampleID}.muts.vcf
bcftools view \\
-e "FILTER='LowDP'" \\
{tmpDir}/{sampleID}.muts.vcf > {tmpDir}/{sampleID}.pisces.vcf
cp {tmpDir}/{sampleID}.pisces.vcf {resultsDir}/vcf/{sampleID}.vcf
""".format(tmpDir=tmpDir, sampleID=sampleID, resultsDir=resultsDir)
print(filt)
os.system(filt)
def TempPurityPloidy(self):
sampleID = self.sample
pairID = self.pair
resultsDir = self.output
tmpDir = resultsDir + "/tempFile/LOH_" + sampleID
mkdir(tmpDir)
solution = open(tmpDir + "/" + sampleID + ".solutions.txt", "w")
solution.write("Ploidy\ttumorPurity\ttumorPloidy\n")
solution.write(sampleID + "\t2\t0.8\t2\n")
solution.close()
def manta(self):
manta = "/home/bioinfo/ubuntu/software/manta-1.6.0/bin/configManta.py"
reference = self.reference
tumorBam = self.bam
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
threads = self.threads
tmpDir = resultsDir + "/tempFile/manta_" + sampleID
mkdir(tmpDir)
if pairID == None:
cmd = """
rm -rf {tmpDir}/*
{manta} \\
--tumorBam {tumorBam} \\
--referenceFasta {reference} \\
--exome \\
--generateEvidenceBam \\
--runDir {tmpDir}
{tmpDir}/runWorkflow.py -j {threads}
zcat {tmpDir}/results/variants/tumorSV.vcf.gz > {tmpDir}/{sampleID}.manta.vcf
""".format(threads=threads,
sampleID=sampleID,
manta=manta,
tumorBam=tumorBam,
reference=reference,
tmpDir=tmpDir)
else:
normalBam = self.normal
cmd = """
rm -rf {tmpDir}/*
{manta} \\
--tumorBam {tumorBam} \\
--normalBam {normalBam} \\
--referenceFasta {reference} \\
--exome \\
--generateEvidenceBam \\
--runDir {tmpDir}
{tmpDir}/runWorkflow.py -j {threads}
zcat {tmpDir}/results/variants/somaticSV.vcf.gz > {tmpDir}/{sampleID}.manta.vcf
""".format(threads=threads,
sampleID=sampleID,
manta=manta,
normalBam=normalBam,
tumorBam=tumorBam,
reference=reference,
tmpDir=tmpDir)
print(cmd)
os.system(cmd)
def bwa_mem(self):
reference = self.reference
threads = self.threads
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
tmpDir = resultsDir + "/tempFile/bwa_" + sampleID
mkdir(tmpDir)
tmp = tmpDir + "/tmp"
mkdir(tmp)
cmd = """
bwa mem -t {threads} \\
-M \\
-R "@RG\\tID:{sampleID}\\tLB:{sampleID}\\tPL:illumina\\tPU:Hiseq\\tSM:{sampleID}" \\
{reference} \\
{resultsDir}/cleandata/{sampleID}.clean_R1.fastq.gz \\
{resultsDir}/cleandata/{sampleID}.clean_R2.fastq.gz \\
| sambamba view -f bam -t {threads} -S /dev/stdin > {tmpDir}/{sampleID}.bam
sambamba sort {tmpDir}/{sampleID}.bam -t {threads} -o {tmpDir}/{sampleID}.sort.bam --tmpdir {tmp} -p
rm {tmpDir}/{sampleID}.bam
cp {tmpDir}/{sampleID}.sort.bam {resultsDir}/bam/{sampleID}.bam
cp {tmpDir}/{sampleID}.sort.bam.bai {resultsDir}/bam/{sampleID}.bam.bai
rm -rf {tmp}
""".format(tmpDir=tmpDir,
threads=threads,
sampleID=sampleID,
reference=reference,
resultsDir=resultsDir,
tmp=tmp)
print(cmd)
os.system(cmd)
if pairID != None:
pairDir = resultsDir + "/tempFile/bwa_" + pairID
mkdir(pairDir)
tmp = pairDir + "/tmp"
mkdir(tmp)
p = """
bwa mem -t {threads} \\
-M \\
-R "@RG\\tID:{pairID}\\tLB:{pairID}\\tPL:illumina\\tPU:Hiseq\\tSM:{pairID}" \\
{reference} \\
{resultsDir}/cleandata/{pairID}.clean_R1.fastq.gz \\
{resultsDir}/cleandata/{pairID}.clean_R2.fastq.gz \\
| sambamba view -f bam -t {threads} -S /dev/stdin > {pairDir}/{pairID}.bam
sambamba sort {pairDir}/{pairID}.bam -t {threads} -o {pairDir}/{pairID}.sort.bam --tmpdir {tmp} -p
rm {pairDir}/{pairID}.bam
cp {pairDir}/{pairID}.sort.bam {resultsDir}/bam/{pairID}.bam
cp {pairDir}/{pairID}.sort.bam.bai {resultsDir}/bam/{pairID}.bam.bai
rm -rf {tmp}
""".format(pairDir=pairDir,
threads=threads,
pairID=pairID,
reference=reference,
resultsDir=resultsDir,
tmp=tmp)
print(p)
os.system(p)
def msisensor_ct(self):
resultsDir = self.output
sampleID = self.sample
threads = self.threads
msi_model = self.runningInfo["setting"]["Other"]["MSIsensor_ct"]
tmpDir = resultsDir + "/tempFile/msisensorct_" + sampleID
mkdir(tmpDir)
cmd = """
msisensor-ct msi -D -M {msi_model} -t {resultsDir}/bam/{sampleID}.bam \\
-o {tmpDir} -b {threads}
""".format(msi_model=msi_model, resultsDir=resultsDir, sampleID=sampleID, tmpDir=tmpDir, threads=threads)
print(cmd)
os.system(cmd)
def markDuplicates(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
threads = self.threads
if self.removeDups:
remove = "-r"
else:
remove = ""
tmpDir = resultsDir + "/tempFile/markDups_" + sampleID
mkdir(tmpDir)
tmp = tmpDir + "/tmp"
mkdir(tmp)
cmd = """
sambamba markdup \\
{resultsDir}/bam/{sampleID}.bam \\
{tmpDir}/{sampleID}.marked.bam \\
-p --overflow-list-size 600000 \\
--tmpdir {tmp} \\
-t {threads} {remove}
rm -rf {tmp}
cp {tmpDir}/{sampleID}.marked.bam {resultsDir}/bam/{sampleID}.bam
cp {tmpDir}/{sampleID}.marked.bam.bai {resultsDir}/bam/{sampleID}.bam.bai
""".format(threads=threads,
tmpDir=tmpDir,
resultsDir=resultsDir,
sampleID=sampleID,
remove=remove,
tmp=tmp)
print(cmd)
os.system(cmd)
if pairID != None:
pairDir = resultsDir + "/tempFile/markDups_" + pairID
mkdir(pairDir)
tmp = pairDir + "/tmp"
mkdir(tmp)
p = """
sambamba markdup \\
{resultsDir}/bam/{pairID}.bam \\
{pairDir}/{pairID}.marked.bam \\
-p --overflow-list-size 600000 \\
--tmpdir {tmp} \\
-t {threads} {remove}
rm -rf {tmp}
cp {pairDir}/{pairID}.marked.bam {resultsDir}/bam/{pairID}.bam
cp {pairDir}/{pairID}.marked.bam.bai {resultsDir}/bam/{pairID}.bam.bai
""".format(threads=threads,
pairDir=pairDir,
resultsDir=resultsDir,
pairID=pairID,
remove=remove,
tmp=tmp)
print(p)
os.system(p)
def varscan_filter(self):
reference = self.reference
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
filtDP = self.filtDP
MAF = self.filtQUAL
tmpDir = resultsDir + "/tempFile/varscan2_" + sampleID
outputFile = tmpDir + "/" + sampleID + ".merge.vcf"
output = open(outputFile, "w")
indel = open(tmpDir + "/" + sampleID + ".indel.fix.vcf", "r")
snp = open(tmpDir + "/" + sampleID + ".snp.fix.vcf", "r")
for i in indel:
if i.startswith("#"):
if "NORMAL\tTUMOR" in i:
i = i.replace("NORMAL\tTUMOR", sampleID + "\t" + pairID)
else:
ii = i.replace("\n", "").split("\t")
li = ii[0:9]
li.append(ii[10])
li.append(ii[9])
i = "\t".join(li) + "\n"
output.write(i)
indel.close()
for s in snp:
if not s.startswith("#"):
ss = s.replace("\n", "").split("\t")
si = ss[0:9]
si.append(ss[10])
si.append(ss[9])
s = "\t".join(si) + "\n"
output.write(s)
snp.close()
output.close()
tmp = tmpDir + "/tmp"
mkdir(tmp)
cmd = """
bcftools sort {outputFile} -O v -o {tmpDir}/{sampleID}.vcf -T {tmp}
cp {tmpDir}/{sampleID}.vcf {resultsDir}/vcf/{sampleID}_{pairID}.vcf
""".format(resultsDir=resultsDir, outputFile=outputFile, tmpDir=tmpDir, sampleID=sampleID, pairID=pairID, tmp=tmp)
print(cmd)
os.system(cmd)
def gemini(self):
gemini_multi = "/home/bioinfo/ubuntu/software/GeminiMulti_5.2.10.49/GeminiMulti.dll"
databases = self.databases
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
threads = self.threads
tmpDir = resultsDir + "/tempFile/gemini_" + sampleID
mkdir(tmpDir)
cmd = """
dotnet {gemini_multi} -bam {resultsDir}/bam/{sampleID}.bam \\
-genome {databases} \\
--outFolder {tmpDir} \\
--numprocesses {threads} \\
--samtools /home/bioinfo/ubuntu/software/samtools-1.11
""".format(gemini_multi=gemini_multi,
resultsDir=resultsDir,
sampleID=sampleID,
databases=databases,
tmpDir=tmpDir,
threads=threads)
print(cmd)
os.system(cmd)
if pairID != None:
pairDir = resultsDir + "/tempFile/gemini_" + pairID
mkdir(pairDir)
p = """
dotnet {gemini_multi} -bam {resultsDir}/bam/{pairID}.bam \\
-genome {databases} \\
--outFolder {pairDir} \\
--numprocesses {threads} \\
--samtools /home/bioinfo/ubuntu/software/samtools-1.11
""".format(gemini_multi=gemini_multi,
resultsDir=resultsDir,
pairID=pairID,
databases=databases,
pairDir=pairDir,
threads=threads)
print(p)
os.system(p)
def gatk_filter(self):
small_exac = self.databases + "/" + self.runningInfo["setting"]["Mutation"]["gatk_filter"]["small_exac"]
bedFile = self.bed
reference = self.reference
resultsDir = self.output
sampleID = self.sample
checkBQSR = sampleID + ".BQSR.bam"
if checkBQSR in os.listdir(resultsDir + "/bam"):
bamFile = checkBQSR
else:
bamFile = sampleID + ".bam"
tmpDir = resultsDir + "/tempFile/gatk_" + sampleID
mkdir(tmpDir)
cmd = """
gatk GetPileupSummaries \\
-I {resultsDir}/bam/{bamFile} \\
-O {tmpDir}/{sampleID}.pileups.table \\
-V {small_exac} \\
-L {bedFile} \\
-R {reference}
gatk CalculateContamination \\
-I {tmpDir}/{sampleID}.pileups.table \\
-O {tmpDir}/{sampleID}.contamination.table
gatk FilterMutectCalls \\
-R {reference} \\
-V {tmpDir}/{sampleID}.m2.vcf \\
-O {tmpDir}/{sampleID}.m2.contFiltered.vcf \\
--contamination-table {tmpDir}/{sampleID}.contamination.table
bcftools view \\
{tmpDir}/{sampleID}.m2.contFiltered.vcf \\
-f PASS,clustered_events,slippage \\
> {tmpDir}/{sampleID}.filter.vcf
cp {tmpDir}/{sampleID}.filter.vcf {resultsDir}/vcf/{sampleID}.vcf
""".format(tmpDir=tmpDir, bamFile=bamFile, resultsDir=resultsDir, sampleID=sampleID, small_exac=small_exac, bedFile=bedFile, reference=reference)
print(cmd)
os.system(cmd)
def hlascan(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
buildver = self.buildver
threads = self.threads
hla_scan = "/home/bioinfo/ubuntu/software/HLAscan/hla_scan_r_v2.1.4"
hla_db = "/home/bioinfo/ubuntu/software/HLAscan/HLA-ALL.IMGT"
tmpDir = resultsDir + "/tempFile/hlascan_" + sampleID
self.tmpDir = tmpDir
mkdir(tmpDir)
self.extractHLA()
if pairID != None:
sampleID = pairID
print("开始进行HLA分型")
cmd = """
{hla_scan} -l {tmpDir}/{sampleID}.HLA.R1.fastq \\
-r {tmpDir}/{sampleID}.HLA.R2.fastq \\
-t {threads} \\
-d {hla_db} -g HLA-A > {tmpDir}/{sampleID}.HLA-A.txt
{hla_scan} -l {tmpDir}/{sampleID}.HLA.R1.fastq \\
-r {tmpDir}/{sampleID}.HLA.R2.fastq \\
-t {threads} \\
-d {hla_db} -g HLA-B > {tmpDir}/{sampleID}.HLA-B.txt
{hla_scan} -l {tmpDir}/{sampleID}.HLA.R1.fastq \\
-r {tmpDir}/{sampleID}.HLA.R2.fastq \\
-t {threads} \\
-d {hla_db} -g HLA-C > {tmpDir}/{sampleID}.HLA-C.txt
cat {tmpDir}/{sampleID}.HLA-A.txt {tmpDir}/{sampleID}.HLA-B.txt {tmpDir}/{sampleID}.HLA-C.txt \\
> {tmpDir}/{sampleID}.hlascan.txt
cp {tmpDir}/{sampleID}.hlascan.txt {resultsDir}/HLA/
""".format(hla_scan=hla_scan,
hla_db=hla_db,
tmpDir=tmpDir,
sampleID=sampleID,
threads=threads,
resultsDir=resultsDir)
print(cmd)
os.system(cmd)
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.pair = runningInfo["pair"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.threads = str(runningInfo["process"]["threads"])
self.runApp = runningInfo["process"]["Mutation"]["SV"]
self.reference = runningInfo["setting"]["Mapping"]["reference"]
self.bed = runningInfo["setting"]["Mutation"]["Bed"]
if runningInfo["setting"]["QC"]["UMI_loc"] != None:
self.bam = self.output + "/tempFile/bwa_" + self.sample + "/" + self.sample + ".sort.bam"
if self.pair != None:
self.normal = self.output + "/tempFile/bwa_" + self.pair + "/" + self.sample + ".sort.bam"
if not os.path.exists(self.bam):
self.bam = self.output + "/bam/" + self.sample + ".bam"
if self.pair != None:
self.normal = self.output + "/bam/" + self.pair + ".bam"
else:
self.bam = self.output + "/bam/" + self.sample + ".bam"
if self.pair != None:
self.normal = self.output + "/bam/" + self.pair + ".bam"
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/Fusion")
def fastqc(self):
rawdataDir = self.rawdata
sampleID = self.sample
pairID = self.pair
resultsDir = self.output
threads = self.threads
tmpDir = resultsDir + "/tempFile/fastqc_" + sampleID
mkdir(tmpDir)
if pairID != None:
pairDir = resultsDir + "/tempFile/fastqc_" + pairID
mkdir(pairDir)
cmd = """
fastqc \\
{rawdataDir}/{sampleID}_R1.fastq.gz \\
{rawdataDir}/{sampleID}_R2.fastq.gz \\
-t {threads} -o {tmpDir}
""".format(rawdataDir=rawdataDir,
sampleID=sampleID,
threads=threads,
tmpDir=tmpDir)
print(cmd)
os.system(cmd)
if pairID != None:
p = """
fastqc \\
{rawdataDir}/{pairID}_R1.fastq.gz \\
{rawdataDir}/{pairID}_R2.fastq.gz \\
-t {threads} -o {pairDir}
""".format(rawdataDir=rawdataDir,
pairID=pairID,
threads=threads,
pairDir=pairDir)
print(p)
os.system(p)
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.pair = runningInfo["pair"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.threads = str(runningInfo["process"]["threads"])
self.buildver = runningInfo["setting"]["Annotation"]["buildver"]
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/HLA")
mkdir(self.output + "/LOH")
def factera(self):
factera = "/home/bioinfo/ubuntu/software/factera/factera.pl"
resultsDir = self.output
sampleID = self.sample
threads = self.threads
tmpDir = resultsDir + "/tempFile/factera_" + sampleID
mkdir(tmpDir)
cmd = """
{factera} -F -p {threads} \\
-o {tmpDir} \\
{resultsDir}/bam/{sampleID}.bam \\
{exonBed} \\
{referenceTwoBit}
""".format(factera=factera,
resultsDir=resultsDir,
sampleID=sampleID,
exonBed=exonBed,
referenceTwoBit=referenceTwoBit,
tmpDir=tmpDir,
threads=threads)
print(cmd)
os.system(cmd)
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.pair = runningInfo["pair"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.threads = str(runningInfo["process"]["threads"])
self.runApp = runningInfo["process"]["QC"]
self.UMI_loc = runningInfo["setting"]["QC"]["UMI_loc"]
self.UMI_len = runningInfo["setting"]["QC"]["UMI_len"]
mkdir(self.output)
mkdir(self.output + "/QC")
mkdir(self.output + "/cleandata")
mkdir(self.output + "/tempFile")
def gatk_haplotypecaller(self):
reference = self.reference
resultsDir = self.output
sampleID = self.sample
bedFile = self.bed
threads = self.threads
bedFile = self.bed
tmpDir = resultsDir + "/tempFile/HaplotypeCaller_" + sampleID
mkdir(tmpDir)
if bedFile == None:
bedFile = "null"
cmd = """
gatk HaplotypeCaller \\
-R {reference} \\
-I {resultsDir}/bam/{sampleID}.bam \\
-O {tmpDir}/{sampleID}.htc.vcf \\
-L {bedFile} \\
--native-pair-hmm-threads {threads}
cp {tmpDir}/{sampleID}.htc.vcf {resultsDir}/vcf/{sampleID}.vcf
""".format(reference=reference, resultsDir=resultsDir, tmpDir=tmpDir, sampleID=sampleID, bedFile=bedFile, threads=threads)
print(cmd)
os.system(cmd)
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.pair = runningInfo["pair"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.threads = str(runningInfo["process"]["threads"])
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/annotation")
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.runApp = runningInfo["process"]["Other"]["TMB"]
self.panelSize = runningInfo["setting"]["Other"]["PanelSize"]
self.buildver = runningInfo["setting"]["Annotation"]["buildver"]
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/TMB")
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.rawdata = runningInfo["rawdata"]
self.pair = runningInfo["pair"]
self.output = runningInfo["output"]
self.threads = str(runningInfo["process"]["threads"])
self.runApp = runningInfo["process"]["Other"]["MSI"]
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/msi")
def gencore(self):
resultsDir = self.output
sampleID = self.sample
pairID = self.pair
threads = self.threads
reference = self.reference
tmpDir = resultsDir + "/tempFile/gencore_" + sampleID
mkdir(tmpDir)
tmp = tmpDir + "/tmp"
mkdir(tmp)
cmd = """
gencore -i {resultsDir}/bam/{sampleID}.bam \\
-r {reference} \\
-o {tmpDir}/{sampleID}.umi.bam \\
-u UMI -s 2 -d 1 \\
-j {tmpDir}/{sampleID}.json -h {tmpDir}/{sampleID}.html
sambamba sort -t {threads} {tmpDir}/{sampleID}.umi.bam -o {tmpDir}/{sampleID}.umi.sort.bam --tmpdir {tmp} -p
cp {tmpDir}/{sampleID}.umi.sort.bam {resultsDir}/bam/{sampleID}.bam
cp {tmpDir}/{sampleID}.umi.sort.bam.bai {resultsDir}/bam/{sampleID}.bam.bai
rm -rf {tmp}
""".format(reference=reference,
resultsDir=resultsDir,
sampleID=sampleID,
tmpDir=tmpDir,
threads=threads,
tmp=tmp)
print(cmd)
os.system(cmd)
if pairID != None:
pairDir = resultsDir + "/tempFile/gencore_" + pairID
mkdir(pairDir)
p = """
gencore -i {resultsDir}/bam/{pairID}.bam \\
-r {reference} \\
-o {pairDir}/{pairID}.umi.bam \\
-u UMI -s 2 -d 1 \\
-j {pairDir}/{pairID}.json -h {pairDir}/{pairID}.html
sambamba sort -t {threads} {pairDir}/{pairID}.umi.bam -o {pairDir}/{pairID}.umi.sort.bam --tmpdir {tmp} -p
cp {pairDir}/{pairID}.umi.sort.bam {resultsDir}/bam/{pairID}.bam
cp {pairDir}/{pairID}.umi.sort.bam.bai {resultsDir}/bam/{pairID}.bam.bai
rm -rf {tmp}
""".format(reference=reference,
resultsDir=resultsDir,
pairID=pairID,
pairDir=pairDir,
threads=threads,
tmp=tmp)
print(p)
os.system(p)
def __init__(self, runningInfo):
self.runningInfo = runningInfo
self.sample = runningInfo["sample"]
self.pair = runningInfo["pair"]
self.rawdata = runningInfo["rawdata"]
self.output = runningInfo["output"]
self.reference = runningInfo["setting"]["Mapping"]["reference"]
self.threads = str(runningInfo["process"]["threads"])
self.runApp = runningInfo["process"]["Mutation"]["CNV"]
mkdir(self.output)
mkdir(self.output + "/tempFile")
mkdir(self.output + "/cnv")
