job-name=ron-rosM

#!/bin/bash
## Job Name
#SBATCH --job-name=ron-rosM
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=15-00:00:00
## Memory per node
#SBATCH --mem=100G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/sr320/030521-ronrosM
 
 
 
# Directories and programs
bismark_dir="/gscratch/srlab/programs/Bismark-0.21.0"
bowtie2_dir="/gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/"
samtools="/gscratch/srlab/programs/samtools-1.9/samtools"
reads_dir="/gscratch/srlab/sr320/data/cg/"
genome_folder="/gscratch/srlab/sr320/data/Cgig-genome/roslin_M/"
 
source /gscratch/srlab/programs/scripts/paths.sh
 
 
 
${bismark_dir}/bismark_genome_preparation \
--verbose \
--parallel 28 \
--path_to_aligner ${bowtie2_dir} \
${genome_folder}
 
 
#/zr3644_11_R2.fastp-trim.20201206.fq.gz
 
find ${reads_dir}*_R1.fastp-trim.20201202.fq.gz \
| xargs basename -s _R1.fastp-trim.20201202.fq.gz | xargs -I{} ${bismark_dir}/bismark \
--path_to_bowtie ${bowtie2_dir} \
-genome ${genome_folder} \
-p 8 \
-score_min L,0,-0.6 \
--non_directional \
-1 ${reads_dir}{}_R1.fastp-trim.20201202.fq.gz \
-2 ${reads_dir}{}_R2.fastp-trim.20201202.fq.gz \
 
 
 
find *.bam | \
xargs basename -s .bam | \
xargs -I{} ${bismark_dir}/deduplicate_bismark \
--bam \
--paired \
{}.bam
 
 
 
${bismark_dir}/bismark_methylation_extractor \
--bedGraph --counts --scaffolds \
--multicore 28 \
--buffer_size 75% \
*deduplicated.bam
 
 
 
# Bismark processing report
 
${bismark_dir}/bismark2report
 
#Bismark summary report
 
${bismark_dir}/bismark2summary
 
 #run multiqc
/gscratch/srlab/programs/anaconda3/bin/multiqc . 
 
 
# Sort files for methylkit and IGV
 
find *deduplicated.bam | \
xargs basename -s .bam | \
xargs -I{} ${samtools} \
sort --threads 28 {}.bam \
-o {}.sorted.bam
 
# Index sorted files for IGV
# The "-@ 16" below specifies number of CPU threads to use.
 
find *.sorted.bam | \
xargs basename -s .sorted.bam | \
xargs -I{} ${samtools} \
index -@ 28 {}.sorted.bam
 
 
 


find *deduplicated.bismark.cov.gz \
| xargs basename -s _bismark_bt2_pe.deduplicated.bismark.cov.gz \
| xargs -I{} ${bismark_dir}/coverage2cytosine \
--genome_folder ${genome_folder} \
-o {} \
--merge_CpG \
--zero_based \
{}_bismark_bt2_pe.deduplicated.bismark.cov.gz


#creating bedgraphs post merge

for f in *merged_CpG_evidence.cov
do
  STEM=$(basename "${f}" .CpG_report.merged_CpG_evidence.cov)
  cat "${f}" | awk -F $'\t' 'BEGIN {OFS = FS} {if ($5+$6 >= 10) {print $1, $2, $3, $4}}' \
  > "${STEM}"_10x.bedgraph
done



for f in *merged_CpG_evidence.cov
do
  STEM=$(basename "${f}" .CpG_report.merged_CpG_evidence.cov)
  cat "${f}" | awk -F $'\t' 'BEGIN {OFS = FS} {if ($5+$6 >= 5) {print $1, $2, $3, $4}}' \
  > "${STEM}"_5x.bedgraph
done


#creating tab files with raw count for glms

for f in *merged_CpG_evidence.cov
do
  STEM=$(basename "${f}" .CpG_report.merged_CpG_evidence.cov)
  cat "${f}" | awk -F $'\t' 'BEGIN {OFS = FS} {if ($5+$6 >= 10) {print $1, $2, $3, $4, $5, $6}}' \
  > "${STEM}"_10x.tab
done


for f in *merged_CpG_evidence.cov
do
  STEM=$(basename "${f}" .CpG_report.merged_CpG_evidence.cov)
  cat "${f}" | awk -F $'\t' 'BEGIN {OFS = FS} {if ($5+$6 >= 5) {print $1, $2, $3, $4, $5, $6}}' \
  > "${STEM}"_5x.tab
done

#bismark, #creating, #run, #sbatch

[code]cat 20190814_BmrkCalig.sh #!/bin/bash ## Job...

cat 20190814_BmrkCalig.sh
#!/bin/bash
## Job Name
#SBATCH --job-name=BismarkAlign_Calig
## Allocation Definition 
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes 
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=14-23:30:00
## Memory per node
#SBATCH --mem=100G
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=strigg@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/strigg/analyses/20190814_Calig
#SBATCH --constraint="skylake|broadwell"

#align with bismark

%%bash

find /gscratch/scrubbed/strigg/TRIMG_adapt_5bp/TRIM_cat/Sealice*R1_001_val_1.fq.gz \
| xargs basename -s _R1_001_val_1.fq.gz| xargs -I{} /gscratch/srlab/programs/Bismark-0.19.0/bismark \
--path_to_bowtie /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64 \
--samtools_path /gscratch/srlab/programs/samtools-1.9 \
--score_min L,0,-0.6 \
-p 4 \
--non_directional \
--dovetail \
--genome /gscratch/srlab/strigg/data/Caligus/GENOMES \
-1 /gscratch/scrubbed/strigg/TRIMG_adapt_5bp/TRIM_cat/{}_R1_001_val_1.fq.gz \
-2 /gscratch/scrubbed/strigg/TRIMG_adapt_5bp/TRIM_cat/{}_R2_001_val_2.fq.gz \
-o /gscratch/scrubbed/strigg/analyses/20190814_Calig

#run deduplicaiton
%%bash
/gscratch/srlab/programs/Bismark-0.19.0/deduplicate_bismark \
--bam -p \
/gscratch/scrubbed/strigg/analyses/20190814_Calig/*.bam \
-o /gscratch/scrubbed/strigg/analyses/20190814_Calig/ \
2> /gscratch/scrubbed/strigg/analyses/20190814_Calig/dedup.err \
--samtools_path /gscratch/srlab/programs/samtools-1.9/


#create summary report
cat /gscratch/scrubbed/strigg/analyses/20190814_Calig/*PE_report.txt | \
grep -E 'Mapping\ efficiency\:|paired-end|Sequence|C methylated' \
cat - /gscratch/scrubbed/strigg/analyses/20190814_Calig/*.deduplication_report.txt | \
grep 'Mapping\ efficiency\:\|removed' \
> /gscratch/scrubbed/strigg/analyses/20190814_Calig/mapping_dedup_summary.txt

#run methylation extractor
/gscratch/srlab/programs/Bismark-0.19.0/bismark_methylation_extractor \
--paired-end --bedGraph --counts --scaffolds \
--multicore 28 \
/gscratch/scrubbed/strigg/analyses/20190814_Calig/*deduplicated.bam \
-o /gscratch/scrubbed/strigg/analyses/20190814_Calig/ \
--samtools /gscratch/srlab/programs/samtools-1.9/samtools \
2> /gscratch/scrubbed/strigg/analyses/20190814_Calig/bme.err

#create bismark reports for individual samlpes
/gscratch/srlab/programs/Bismark-0.19.0/bismark2report

#create bismark summary report for all samples
/gscratch/srlab/programs/Bismark-0.19.0/bismark2summary

#Run coverage2cytosine command to generate cytosine coverage files
find /gscratch/scrubbed/strigg/analyses/20190814_Calig/*.cov.gz \
| xargs basename -s _R1_001_val_1_bismark_bt2_pe.deduplicated.bismark.cov.gz \
| xargs -I{} /gscratch/srlab/programs/Bismark-0.19.0/coverage2cytosine --gzip \
--genome_folder /gscratch/srlab/strigg/data/Caligus/GENOMES \
-o /gscratch/scrubbed/strigg/analyses/20190814_Calig/{}_cytosine_CpG_cov_report \
/gscratch/scrubbed/strigg/analyses/20190814_Calig/{}_R1_001_val_1__bismark_bt2_pe.deduplicated.bismark.cov.gz

#compile and sort bams for methylkit
find /gscratch/scrubbed/strigg/analyses/20190814_Calig/*deduplicated.bam| \
xargs basename -s _R1_001_val_1_bismark_bt2_pe.deduplicated.bam | xargs -I{} /gscratch/srlab/programs/samtools-1.9/samtools \
sort /gscratch/scrubbed/strigg/analyses/20190814_Calig/{}_R1_001_val_1_bismark_bt2_pe.deduplicated.bam \
-o /gscratch/scrubbed/strigg/analyses/20190814_Calig/{}.dedup.sorted.bam



#align, #compile, #create, #run, #sbatch