chaopower
/
pipeline
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

纯合调整为0.9

master
chaopower 2023-12-28 10:41:01 +08:00
parent 47cbe45d8b
commit 493a99cecd
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
codes/hereditary.py
View File

@ -45,7 +45,7 @@ class HereditaryRun:
row_df['inheritance'] = selected_rows['inheritance'] row_df['inheritance'] = selected_rows['inheritance']
row_df['Gene'] = gene row_df['Gene'] = gene
row_df['mutation'] = mutation row_df['mutation'] = mutation
row_df['genotype'] = '纯合' if rows['Freq'] > 0.8 else '杂合' row_df['genotype'] = '纯合' if rows['Freq'] > 0.9 else '杂合'
row_df['ClinicalSign'] = str(rows['ClinicalSign']) row_df['ClinicalSign'] = str(rows['ClinicalSign'])
result_df = pd.concat([result_df, row_df]) result_df = pd.concat([result_df, row_df])

14
wdl/call_mutation.wdl
View File

@ -27,7 +27,7 @@ task mutation_calling_umi {
-UN -Q 20 -m 3 -r 2 -th 10 -z 1 -c 1 -S 2 -E 3 -g 4 ${bed} \ -UN -Q 20 -m 3 -r 2 -th 10 -z 1 -c 1 -S 2 -E 3 -g 4 ${bed} \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ |/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
| /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl \ | /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl \
-N ${name} -E -f 0.0005 > ${output_dir}/mutation/${name}.1r.vcf -N ${name} -E -f 0.0005 -F 0.1 > ${output_dir}/mutation/${name}.1r.vcf
#提取>=2条矫正的序列 #提取>=2条矫正的序列
bam_fetch.py ${output_dir}/alignment/${name}.rmdup.bam ${output_dir}/alignment/${name}.2r.rmdup.bam bam_fetch.py ${output_dir}/alignment/${name}.rmdup.bam ${output_dir}/alignment/${name}.2r.rmdup.bam
@ -42,7 +42,7 @@ task mutation_calling_umi {
-b ${output_dir}/alignment/${name}.2r.rmdup.bam \ -b ${output_dir}/alignment/${name}.2r.rmdup.bam \
-UN -Q 20 -m 3 -r 1 -th 10 -z 1 -c 1 -S 2 -E 3 -g 4 ${bed} \ -UN -Q 20 -m 3 -r 1 -th 10 -z 1 -c 1 -S 2 -E 3 -g 4 ${bed} \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ |/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.0001 >${output_dir}/mutation/${name}.2r.vcf |/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.0001 -F 0.1 >${output_dir}/mutation/${name}.2r.vcf
# merge突变，以1条方式call的>0.01的突变+两条方式的对一条方式的低频区域（AF<0.01）进行矫正。 # merge突变，以1条方式call的>0.01的突变+两条方式的对一条方式的低频区域（AF<0.01）进行矫正。
correct_umi_1r_plus_2r.pl \ correct_umi_1r_plus_2r.pl \
@ -110,7 +110,7 @@ task mutation_calling_umi_control {
-r 3 \ -r 3 \
-th 10 \ -th 10 \
-c 1 -S 2 -E 3 -g 4 ${bed} |/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ -c 1 -S 2 -E 3 -g 4 ${bed} |/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.01 >${output_dir}/mutation/${name}.normal.vcf |/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.01 -F 0.1 >${output_dir}/mutation/${name}.normal.vcf
# 实验样本 # 实验样本
java -jar /dataseq/jmdna/software/VarDict-1.8.3/lib/VarDict-1.8.3.jar \ java -jar /dataseq/jmdna/software/VarDict-1.8.3/lib/VarDict-1.8.3.jar \
@ -121,7 +121,7 @@ task mutation_calling_umi_control {
-UN -Q 20 -m 3 -r 2 -th 10 -c 1 -S 2 -E 3 -g 4 ${bed} \ -UN -Q 20 -m 3 -r 2 -th 10 -c 1 -S 2 -E 3 -g 4 ${bed} \
| /dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ | /dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
| /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl \ | /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl \
-N ${name} -E -f 0.0005 > ${output_dir}/mutation/${name}.1r.vcf -N ${name} -E -f 0.0005 -F 0.1 > ${output_dir}/mutation/${name}.1r.vcf
#提取>=2条矫正的序列 #提取>=2条矫正的序列
bam_fetch.py ${output_dir}/alignment/${name}.rmdup.bam ${output_dir}/alignment/${name}.2r.rmdup.bam bam_fetch.py ${output_dir}/alignment/${name}.rmdup.bam ${output_dir}/alignment/${name}.2r.rmdup.bam
@ -132,7 +132,7 @@ task mutation_calling_umi_control {
java -jar /dataseq/jmdna/software/VarDict-1.8.3/lib/VarDict-1.8.3.jar -G ${ref} \ java -jar /dataseq/jmdna/software/VarDict-1.8.3/lib/VarDict-1.8.3.jar -G ${ref} \
-f 0.0001 -N ${name}_2r -b ${output_dir}/alignment/${name}.2r.rmdup.bam \ -f 0.0001 -N ${name}_2r -b ${output_dir}/alignment/${name}.2r.rmdup.bam \
-UN -Q 20 -m 3 -r 1 -th 10 -c 1 -S 2 -E 3 -g 4 ${bed} | /dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ -UN -Q 20 -m 3 -r 1 -th 10 -c 1 -S 2 -E 3 -g 4 ${bed} | /dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
| /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.0001 >${output_dir}/mutation/${name}.2r.vcf | /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.0001 -F 0.1 >${output_dir}/mutation/${name}.2r.vcf
# merge突变，以1条方式call的>0.01的突变+两条方式的对一条方式的低频区域（AF<0.01）进行矫正。 # merge突变，以1条方式call的>0.01的突变+两条方式的对一条方式的低频区域（AF<0.01）进行矫正。
correct_umi_1r_plus_2r.pl \ correct_umi_1r_plus_2r.pl \
@ -203,7 +203,7 @@ task mutation_calling_tissue {
-th 10 \ -th 10 \
-c 1 -S 2 -E 3 -g 4 ${bed} \ -c 1 -S 2 -E 3 -g 4 ${bed} \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \ |/dataseq/jmdna/software/VarDict-1.8.3/bin/teststrandbias.R \
|/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.005 \ |/dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_valid.pl -N ${name} -E -f 0.005 -F 0.1 \
>${output_dir}/mutation/${name}.raw.vcf >${output_dir}/mutation/${name}.raw.vcf
vcf_filter.py \ vcf_filter.py \
@ -255,7 +255,7 @@ task mutation_calling_tissue_control {
-r 2 \ -r 2 \
-th 20 \ -th 20 \
-z 1 -c 1 -S 2 -E 3 -g 4 ${bed} | /dataseq/jmdna/software/VarDict-1.8.3/bin/testsomatic.R \ -z 1 -c 1 -S 2 -E 3 -g 4 ${bed} | /dataseq/jmdna/software/VarDict-1.8.3/bin/testsomatic.R \
| /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_paired.pl -N ${name} -f 0.005 \ | /dataseq/jmdna/software/VarDict-1.8.3/bin/var2vcf_paired.pl -N ${name} -f 0.005 -F 0.1 \
>${output_dir}/mutation/${name}.raw.vcf >${output_dir}/mutation/${name}.raw.vcf
vcf_filter.py \ vcf_filter.py \