master
parent
b54741ee46
commit
47cbe45d8b
|
|
@ -13,6 +13,7 @@ java17 -Dconfig.file=/home/zhangchao/project/pipeline/wdl/cromwell.examples.conf
|
|||
## dot
|
||||
```bash
|
||||
womtool graph pipeline.wdl > other/pipeline.dot
|
||||
dot -Tpng .\pipeline.dot -o pipeline.png
|
||||
```
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ system {
|
|||
# If 'true', a SIGTERM or SIGINT will trigger Cromwell to attempt to gracefully shutdown in server mode,
|
||||
# in particular clearing up all queued database writes before letting the JVM shut down.
|
||||
# The shutdown is a multi-phase process, each phase having its own configurable timeout. See the Dev Wiki for more details.
|
||||
graceful-server-shutdown = false
|
||||
graceful-server-shutdown = true
|
||||
|
||||
# Cromwell will cap the number of running workflows at N
|
||||
max-concurrent-workflows = 10000
|
||||
|
|
@ -95,7 +95,7 @@ system {
|
|||
# These are the default values in Cromwell, in most circumstances there should not be a need to change them.
|
||||
|
||||
# How frequently Cromwell should scan for aborts.
|
||||
scan-frequency: 600 seconds
|
||||
scan-frequency: 30 seconds
|
||||
|
||||
# The cache of in-progress aborts. Cromwell will add entries to this cache once a WorkflowActor has been messaged to abort.
|
||||
# If on the next scan an 'Aborting' status is found for a workflow that has an entry in this cache, Cromwell will not ask
|
||||
|
|
@ -134,7 +134,7 @@ workflow-options {
|
|||
|
||||
default {
|
||||
# When a workflow type is not provided on workflow submission, this specifies the default type.
|
||||
#workflow-type: WDL
|
||||
workflow-type: WDL
|
||||
|
||||
# When a workflow type version is not provided on workflow submission, this specifies the default type version.
|
||||
workflow-type-version: "draft-2"
|
||||
|
|
@ -193,58 +193,6 @@ call-caching {
|
|||
# }
|
||||
}
|
||||
|
||||
# Google configuration
|
||||
google {
|
||||
|
||||
#application-name = "cromwell"
|
||||
|
||||
# Default: just application default
|
||||
#auths = [
|
||||
|
||||
# Application default
|
||||
#{
|
||||
# name = "application-default"
|
||||
# scheme = "application_default"
|
||||
#},
|
||||
|
||||
# Use a static service account
|
||||
#{
|
||||
# name = "service-account"
|
||||
# scheme = "service_account"
|
||||
# Choose between PEM file and JSON file as a credential format. They're mutually exclusive.
|
||||
# PEM format:
|
||||
# service-account-id = "my-service-account"
|
||||
# pem-file = "/path/to/file.pem"
|
||||
# JSON format:
|
||||
# json-file = "/path/to/file.json"
|
||||
#}
|
||||
|
||||
# Use service accounts provided through workflow options
|
||||
#{
|
||||
# name = "user-service-account"
|
||||
# scheme = "user_service_account"
|
||||
#}
|
||||
#]
|
||||
}
|
||||
|
||||
docker {
|
||||
hash-lookup {
|
||||
# Set this to match your available quota against the Google Container Engine API
|
||||
#gcr-api-queries-per-100-seconds = 1000
|
||||
|
||||
# Time in minutes before an entry expires from the docker hashes cache and needs to be fetched again
|
||||
#cache-entry-ttl = "20 minutes"
|
||||
|
||||
# Maximum number of elements to be kept in the cache. If the limit is reached, old elements will be removed from the cache
|
||||
#cache-size = 200
|
||||
|
||||
# How should docker hashes be looked up. Possible values are "local" and "remote"
|
||||
# "local": Lookup hashes on the local docker daemon using the cli
|
||||
# "remote": Lookup hashes on docker hub, gcr, gar, quay
|
||||
#method = "remote"
|
||||
}
|
||||
}
|
||||
|
||||
engine {
|
||||
# This instructs the engine which filesystems are at its disposal to perform any IO operation that it might need.
|
||||
# For instance, WDL variables declared at the Workflow level will be evaluated using the filesystems declared here.
|
||||
|
|
@ -261,7 +209,7 @@ engine {
|
|||
# project = "google-billing-project"
|
||||
# }
|
||||
local {
|
||||
#enabled: true
|
||||
enabled: true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -373,7 +321,7 @@ backend {
|
|||
# `script-epilogue` configures a shell command to run after the execution of every command block.
|
||||
#
|
||||
# If this value is not set explicitly, the default value is `sync`, equivalent to:
|
||||
script-epilogue = ""
|
||||
# script-epilogue = ""
|
||||
#
|
||||
# To turn off the default `sync` behavior set this value to an empty string:
|
||||
# script-epilogue = ""
|
||||
|
|
|
|||
|
|
@ -136,13 +136,13 @@ while (<IN>) {
|
|||
$hgvs =~ s/exon(\d+)/intron$intron;exon$exon/;
|
||||
$line[9] = join(":", ($gene, $hgvs));
|
||||
}
|
||||
elsif ($gene eq "MET") {
|
||||
$line[9] = join(":", ($gene, "NM_000245", "exon14", "c.xxx"));
|
||||
$line[8] = 'skipping'
|
||||
}
|
||||
else {
|
||||
push @reason, 'not_need_spl';
|
||||
}
|
||||
if ($gene eq "MET" ) {
|
||||
$line[9] = join(":", ($gene, "NM_000245", "exon14", "c.xxx"));
|
||||
$line[8] = 'skipping'
|
||||
}
|
||||
$protein = 'Truncating Mutations';
|
||||
}
|
||||
else {
|
||||
|
|
@ -175,7 +175,7 @@ while (<IN>) {
|
|||
|
||||
# tmb 流程去掉 不过滤但是修改 hgvs
|
||||
if ($pipeline eq 'tmb') {
|
||||
@reason = grep(!/synonymous|benign/, @reason);
|
||||
@reason = grep(!/synonymous/, @reason);
|
||||
if (($freq < 0.05) and ($sample_type eq 't')) {
|
||||
push @reason, 'lowfreq_tissue_tmb';
|
||||
}
|
||||
|
|
|
|||
|
|
@ -369,7 +369,7 @@ class PostProcess:
|
|||
res = df.to_dict('records')[0]
|
||||
msi_res['msi_count'] = res['Total_Number_of_Sites']
|
||||
msi_res['msi_value'] = res['%']
|
||||
if msi_res['msi_value'] >= 0.3:
|
||||
if msi_res['msi_value'] >= 30:
|
||||
msi_res['msi_result'] = 'MSI-H'
|
||||
msi_res['msi_predict'] = '对免疫检查点抑制剂可能敏感'
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -94,9 +94,9 @@ def run(barcode, normal, umi, input_dir, output_dir, project, cancer, probe, wdl
|
|||
# f'{"-Dcall-caching.enabled=false " if uncache else ""}'
|
||||
# f'-Dconfig.file=/home/zhangchao/project/pipeline/workflow/script/cromwell.examples.conf ' \
|
||||
|
||||
cmd4 = f'/home/install/product/workflow/software/jdk-17.0.7+7/bin/java -DLOG_MODE=standard ' \
|
||||
cmd4 = f'/usr/bin/java -DLOG_MODE=standard ' \
|
||||
f'-Dconfig.file=$WORKFLOW/codes/cromwell.examples.conf ' \
|
||||
f'-jar $WORKFLOW/software/cromwell-86.jar run {wdl} --inputs {jsfile_path} '
|
||||
f'-jar $WORKFLOW/software/cromwell-51.jar run {wdl} --inputs {jsfile_path} '
|
||||
# cmd = f'{cmd1}; {cmd2}; {cmd3}; {cmd4}'
|
||||
cmd = f'{cmd3}; {cmd4}'
|
||||
|
||||
|
|
|
|||
33
pipeline.wdl
33
pipeline.wdl
|
|
@ -1,18 +1,18 @@
|
|||
# pipeline
|
||||
|
||||
import "wdl/qc.wdl"
|
||||
import "wdl/alignment.wdl"
|
||||
import "wdl/call_mutation.wdl"
|
||||
import "wdl/fusion.wdl"
|
||||
import "wdl/statistics.wdl"
|
||||
import "wdl/cnv.wdl"
|
||||
import "wdl/msi.wdl"
|
||||
import "wdl/chemo.wdl"
|
||||
import "wdl/hereditary.wdl"
|
||||
import "wdl/pollution.wdl"
|
||||
import "wdl/tmb.wdl"
|
||||
import "wdl/postprocess.wdl"
|
||||
import "wdl/neoantigen.wdl"
|
||||
|
||||
import "wdl/qc.wdl" as qc
|
||||
import "wdl/alignment.wdl" as alignment
|
||||
import "wdl/call_mutation.wdl" as call_mutation
|
||||
import "wdl/fusion.wdl" as fusion
|
||||
import "wdl/statistics.wdl" as statistics
|
||||
import "wdl/cnv.wdl" as cnv
|
||||
import "wdl/msi.wdl" as msi
|
||||
import "wdl/chemo.wdl" as chemo
|
||||
import "wdl/hereditary.wdl" as hereditary
|
||||
import "wdl/pollution.wdl" as pollution
|
||||
import "wdl/tmb.wdl" as tmb
|
||||
import "wdl/postprocess.wdl" as postprocess
|
||||
import "wdl/neoantigen.wdl" as neoantigen
|
||||
|
||||
workflow pipeline {
|
||||
|
||||
|
|
@ -199,6 +199,7 @@ workflow pipeline {
|
|||
fusion=call_fusion.fusion_vcf,
|
||||
cnv=call_cnv.cnv_filter,
|
||||
msi=call_msi.msi_txt,
|
||||
tmb=call_tmb.tmb_txt,
|
||||
hereditary=call_hereditary.hereditary_txt,
|
||||
chemo=call_chemo.chemo_res,
|
||||
neoantigen=call_neoantigen.neoantigen_txt,
|
||||
|
|
@ -209,4 +210,8 @@ workflow pipeline {
|
|||
cancer=cancer,
|
||||
project=project
|
||||
}
|
||||
|
||||
output {
|
||||
String result = "${output_dir}/report/${tumor}.merged_file.xlsx"
|
||||
}
|
||||
}
|
||||
|
|
@ -115,49 +115,84 @@ workflow alignment {
|
|||
String output_dir
|
||||
|
||||
if (run) {
|
||||
scatter(name in [tumor, normal]) {
|
||||
if (defined(name)) {
|
||||
call bwa {
|
||||
# 单样本
|
||||
if (!defined(normal)) {
|
||||
call bwa as bwa_tumor {
|
||||
input:
|
||||
name=tumor,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
read1=tumor_r1,
|
||||
read2=tumor_r2
|
||||
}
|
||||
|
||||
if (umi) {
|
||||
call markduplicates_genecore as tumor_markduplicates_genecore {
|
||||
input:
|
||||
name=name,
|
||||
name=tumor,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
read1=if name==tumor then tumor_r1 else normal_r1,
|
||||
read2=if name==tumor then tumor_r2 else normal_r2
|
||||
}
|
||||
if (name==tumor) {
|
||||
if (umi) {
|
||||
call markduplicates_genecore as tumor_markduplicates_genecore {
|
||||
input:
|
||||
name=name,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa.sorted_bam,
|
||||
}
|
||||
}
|
||||
if (!umi) {
|
||||
call markduplicates_picard as tumor_markduplicates_picard {
|
||||
input:
|
||||
name=name,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa.sorted_bam,
|
||||
}
|
||||
}
|
||||
sorted_bam=bwa_tumor.sorted_bam,
|
||||
}
|
||||
}
|
||||
|
||||
if (name==select_first([normal, 'None'])) {
|
||||
call markduplicates_picard as normal_markduplicates_picard {
|
||||
input:
|
||||
name=name,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa.sorted_bam,
|
||||
}
|
||||
if (!umi) {
|
||||
call markduplicates_picard as tumor_markduplicates_picard {
|
||||
input:
|
||||
name=tumor,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa_tumor.sorted_bam,
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
# 双样本
|
||||
if (defined(normal)) {
|
||||
call bwa as bwa_tumor_control {
|
||||
input:
|
||||
name=tumor,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
read1=tumor_r1,
|
||||
read2=tumor_r2
|
||||
}
|
||||
call bwa as bwa_normal_control {
|
||||
input:
|
||||
name=normal,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
read1=normal_r1,
|
||||
read2=normal_r2
|
||||
}
|
||||
call markduplicates_picard as tumor_markduplicates_picard_control {
|
||||
input:
|
||||
name=tumor,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa_tumor_control.sorted_bam,
|
||||
}
|
||||
|
||||
if (umi) {
|
||||
call markduplicates_genecore as normal_markduplicates_genecore {
|
||||
input:
|
||||
name=normal,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa_normal_control.sorted_bam,
|
||||
}
|
||||
}
|
||||
|
||||
if (!umi) {
|
||||
call markduplicates_picard as normal_markduplicates_picard {
|
||||
input:
|
||||
name=normal,
|
||||
ref=ref,
|
||||
output_dir=output_dir,
|
||||
sorted_bam=bwa_normal_control.sorted_bam,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
output {
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# mutation
|
||||
|
||||
task mutation_calling_umi {
|
||||
String name
|
||||
|
|
@ -266,7 +267,7 @@ task mutation_calling_tissue_control {
|
|||
vcf_add_tag_msi.pl ${output_dir}/mutation/${name}.raw.snp_indel.vcf ${output_dir}/mutation/${name}.raw.addtagmsi.snp_indel.vcf ${probe} t
|
||||
|
||||
vcf_filter.py -i ${output_dir}/mutation/${name}.raw.addtagmsi.snp_indel.vcf \
|
||||
-o ${output_dir}/mutation/${name}.snp_indel.somatic.vcf \
|
||||
-o ${output_dir}/mutation/${name}.snp_indel.somatic.vcf \AF[0] > 3*FORMAT/AF[1]
|
||||
-e 'INFO/STATUS="StrongSomatic" | ( INFO/STATUS="LikelySomatic" && FORMAT/AF[0] > 3*FORMAT/AF[1] )'
|
||||
|
||||
vcf_filter.py -i ${output_dir}/mutation/${name}.raw.snp_indel.vcf \
|
||||
|
|
@ -718,6 +719,7 @@ workflow call_mutation {
|
|||
cancer=cancer
|
||||
}
|
||||
}
|
||||
|
||||
if (!umi) {
|
||||
call mutation_calling_tissue_control {
|
||||
input:
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# chemo
|
||||
|
||||
task run_chemo {
|
||||
String name
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# cnv
|
||||
|
||||
task cnv_single {
|
||||
String name
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
|
||||
task rmdup_picard {
|
||||
String name
|
||||
String sorted_bam
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# hereditary
|
||||
|
||||
task run_hereditary {
|
||||
String name
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# msi
|
||||
|
||||
task msi_single {
|
||||
String name
|
||||
|
|
@ -89,6 +90,3 @@ workflow call_msi {
|
|||
String msi_txt = "${output_dir}/msi/${tumor}.msi.txt"
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
|
||||
task run_pollution {
|
||||
String name
|
||||
String output_dir
|
||||
|
|
|
|||
|
|
@ -1,9 +1,11 @@
|
|||
# postprocess
|
||||
|
||||
task run_post {
|
||||
String? mutation
|
||||
String? fusion
|
||||
String? cnv
|
||||
String? msi
|
||||
String? msi
|
||||
String? tmb
|
||||
String? hereditary
|
||||
String? chemo
|
||||
String? neoantigen
|
||||
|
|
@ -38,6 +40,7 @@ workflow call_postprocess {
|
|||
String? fusion
|
||||
String? cnv
|
||||
String? msi
|
||||
String? tmb
|
||||
String? hereditary
|
||||
String? pollution
|
||||
String? chemo
|
||||
|
|
@ -55,6 +58,7 @@ workflow call_postprocess {
|
|||
fusion=fusion,
|
||||
cnv=cnv,
|
||||
msi=msi,
|
||||
tmb=tmb,
|
||||
hereditary=hereditary,
|
||||
chemo=chemo,
|
||||
neoantigen=neoantigen,
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
#qc
|
||||
|
||||
task runqc {
|
||||
String name
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# statistics
|
||||
|
||||
task run_statistics {
|
||||
String name
|
||||
|
|
@ -17,7 +18,7 @@ task run_statistics {
|
|||
samtools stats --reference ${ref} -t ${bed} -@ 10 ${rmdupBam} > ${output_dir}/qc/${name}.rmdup.stat
|
||||
bamdst -p ${bed} -o ${output_dir}/qc/${name}_bamdst ${rmdupBam}
|
||||
qc_stat.py ${output_dir}/qc/${name}.json ${output_dir}/qc/${name}_bamdst/ ${output_dir}/qc/${name}_qc.txt
|
||||
#
|
||||
|
||||
# InsertAndDepthStat.R \
|
||||
# ${output_dir}/qc/${name}_InsertAndDepthStat \
|
||||
# ${output_dir}/qc/${name}_bamdst/insertsize.plot \
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
# tmb
|
||||
|
||||
task run_tmb {
|
||||
String name
|
||||
|
|
|
|||
Loading…
Reference in New Issue