Skip to content

Instantly share code, notes, and snippets.

@jerowe
Created February 23, 2016 05:06
Show Gist options
  • Select an option

  • Save jerowe/db1c4b1c911a40bbe24e to your computer and use it in GitHub Desktop.

Select an option

Save jerowe/db1c4b1c911a40bbe24e to your computer and use it in GitHub Desktop.
---
global:
- indir: data/raw
- outdir: data/Analysis
- reference: /scratch/Reference_Genomes/Public/Vertebrate_other/Anolis_Carolinensis/AnoCar2.0/anoCar2.fa
- bowtie_tmp_dir: "data/Analysis/{$sample}/Bowtie2/tmp"
- file_rule: (Sample.*)$
- by_sample_outdir: 1
- find_by_dir: 1
rules:
- Bowtie2:
local:
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 bowtie/2.2.6
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=bowtie2
#
process: |
#NOTE job_tags={$sample}
bowtie2 -p 12 -x {$self->reference} -1 {$self->indir}/{$sample}_TRIMMOMATIC/{$sample}_read1_trimmomatic_1PE.gz -2 {$self->indir}/{$sample}_TRIMMOMATIC/{$sample}_read2_trimmomatic_2PE.gz -S {$self->outdir}/{$sample}_aligned.sam
- samtools_view:
local:
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=samtools_view
#
process: |
#NOTE job_tags={$sample}
samtools view -b -S {$self->indir}/{$sample}_aligned.sam > {$self->indir}/{$sample}_aligned.bam
- samtools_sort:
local:
- indir: "data/Analysis/{$sample}/Bowtie2"
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=samtools_sort
#
process: |
#NOTE job_tags={$sample}
samtools sort -@ 6 {$self->indir}/{$sample}_aligned.bam -f {$self->indir}/{$sample}_aligned.sorted.bam
- samtools_index:
local:
- indir: "data/Analysis/{$sample}/Bowtie2"
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2
#HPC mem=40GB
#HPC walltime=05:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=samtools_index
#
process: |
#NOTE job_tags={$sample}
samtools index {$self->indir}/{$sample}_aligned.sorted.bam
- picard_cleansam:
local:
- indir: "data/Analysis/{$sample}/Bowtie2"
- outdir: "data/Analysis/{$sample}/Picard"
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 jdk/1.8.0_31
#HPC mem=40GB
#HPC walltime=05:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=picard_cleansam
#
process: |
#NOTE job_tags={$sample}
java -Xmx2g -jar /share/apps/picard/1.82/CleanSam.jar INPUT={$self->indir}/{$sample}_aligned.bam O={$self->outdir}/{$sample}_cleaned.aligned.bam TMP_DIR={$self->bowtie_tmp_dir}
- picard_sortsam:
local:
- indir: "data/Analysis/{$sample}/Picard"
- outdir: "data/Analysis/{$sample}/Picard"
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 jdk/1.8.0_31
#HPC mem=40GB
#HPC walltime=05:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=picard_sortsam
#
process: |
#NOTE job_tags={$sample}
java -Xmx2g -jar /share/apps/picard/1.82/SortSam.jar INPUT={$self->indir}/{$sample}_cleaned.aligned.bam O={$self->outdir}/{$sample}_csorted.cleaned.aligned.bam SO=coordinate TMP_DIR={$self->bowtie_tmp_dir}
- picard_markdups:
local:
- indir: "data/Analysis/{$sample}/Picard"
- outdir: "data/Analysis/{$sample}/Picard"
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 jdk/1.8.0_31
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=picard_markdups
#
process: |
#NOTE job_tags={$sample}
java -Xmx2g -jar /share/apps/picard/1.82/MarkDuplicates.jar M={$self->indir}/{$sample}_markDup_metrics_file.txt I={$self->indir}/{$sample}_csorted.cleaned.aligned.bam O={$self->outdir}/{$sample}_mdup.csorted.cleaned.aligned.bam TMP_DIR={$self->bowtie_tmp_dir} MAX_FILE_HANDLES_FOR_READ_ENDS_MAP=100
- picard_bamindex:
local:
- indir: "data/Analysis/{$sample}/Picard"
- outdir: "data/Analysis/{$sample}/Picard"
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 jdk/1.8.0_31
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=picard_bamindex
#
process: |
#NOTE job_tags={$sample}
java -Xmx2g -jar /share/apps/picard/1.82/BuildBamIndex.jar I={$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.bam TMP_DIR={$self->bowtie_tmp_dir}
- samtools_mpileup:
local:
- indir: "data/Analysis/{$sample}/Picard"
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 htslib
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=samtools_mpileup
#
process: |
#NOTE job_tags={$sample}
samtools mpileup -ugf {$self->reference} {$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.bam | bcftools call -vmO z -o {$self->outdir}/{$sample}_mdup.csorted.cleaned.aligned.vcf.gz
- tabix_index:
local:
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 htslib
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=tabix_index
#
process: |
#NOTE job_tags={$sample}
tabix -p vcf {$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.vcf.gz
- bcftools_stats:
local:
- indir: "data/Analysis/{$sample}/samtools_mpileup"
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 htslib
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=bcftools_stats
#
process: |
#NOTE job_tags={$sample}
bcftools stats -F {$self->reference} -s - {$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.vcf.gz > {$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.vcf.stats
- bcftools_filter:
local:
- indir: "data/Analysis/{$sample}/samtools_mpileup"
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 htslib
#HPC mem=40GB
#HPC walltime=10:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=1
#HPC jobname=bcftools_filter
#
process: |
#NOTE job_tags={$sample}
bcftools filter -O z -o {$self->indir}/{$sample}_filteredQ10.mdup.csorted.cleaned.aligned.vcf.gz -s LOWQUAL -i'%QUAL>10' {$self->indir}/{$sample}_mdup.csorted.cleaned.aligned.vcf.gz
- remove_tmp:
local:
- create_outdir: 0
- before_meta: |
HPC THINGS
#
#HPC module=NYUAD/2.0 gcc/4.9.1 zlib/1.2.8 openssl/1.0.1i anyenv/1 ncurses samtools/1.2 bcftools/1.2 htslib
#HPC mem=40GB
#HPC walltime=01:00:00
#HPC cpus_per_task=12
#HPC queue=adserial
#HPC commands_per_node=12
#HPC jobname=remove_tmp
#
process: |
#NOTE job_tags={$sample}
rm -rf {$self->bowtie_tmp_dir}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment