[code] [sr320@mox2 jobs]$ cat 0212_1230.sh...

[sr320@mox2 jobs]$ cat 0212_1230.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=geoy-blast
## Allocation Definition 
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1   
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=3-00:00:00
## Memory per node
#SBATCH --mem=100
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/0212

/gscratch/srlab/programs/ncbi-blast-2.6.0+/bin/blastn \
-task blastn \
-query /gscratch/srlab/sr320/data/geoduck/Pgenerosa_transcriptome_v5.fasta
-db  /gscratch/srlab/sr320/blastdb/Pgenerosa_v071 \
-out /gscratch/srlab/sr320/analyses/1119/geo-tran-v071.tab \
-evalue 1e-20 \
-max_target_seqs 1 \
-outfmt 6 \
-num_threads 28

#sbatch

Mapping quant-seq to genome

[sr320@mox2 jobs]$ cat 1117_1500.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=ls-bow
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=500G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1117/

source /gscratch/srlab/programs/scripts/paths.sh





find /gscratch/srlab/sr320/data/ls-tag/*.gz | xargs basename -s L006_R1_001.fastq.gz | xargs -I{} bowtie2 \
-x /gscratch/srlab/sr320/data/oly/Olurida_v081.bowtie-index \
-U /gscratch/srlab/sr320/data/ls-tag/{}L006_R1_001.fastq.gz \
-p 28 \
-q \
-S /gscratch/srlab/sr320/analyses/1117/{}_01_bowtie2.sam

#sbatch

[code]#!/bin/bash ## Job Name #SBATCH...

#!/bin/bash
## Job Name
#SBATCH --job-name=ks-oly-blast
## Allocation Definition 
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1   
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=3-00:00:00
## Memory per node
#SBATCH --mem=100
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1105

/gscratch/srlab/programs/ncbi-blast-2.6.0+/bin/blastn \
-task blastn \
-query /gscratch/srlab/sr320/data/oly/Trinity.fasta \
-db /gscratch/srlab/sr320/data/oly/Olurida_v081 \
-out /gscratch/srlab/sr320/analyses/1105/ks-trinity-v081.tab \
-evalue 1e-20 \
-outfmt 6 \
-num_threads 28

#sbatch

[code][sr320@mox1 jobs]$ cat 1029_1500.sh #!/bin/bash...

[sr320@mox1 jobs]$ cat 1029_1500.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=bow64
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=100G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1030

source /gscratch/srlab/programs/scripts/paths.sh


for fastq in /gscratch/scrubbed/sr320/Phred64_fqs/*1.fq.gz; do
  read1=$(echo "$fastq")
  read1_array+=("$read1")
done

for fastq in /gscratch/scrubbed/sr320/Phred64_fqs/*2.fq.gz; do
  read2=$(echo "$fastq")
  read2_array+=("$read2")
done

for pair in "${!read1_array[@]}"; do
  i=${read1_array[$pair]}
  j=${read2_array[$pair]}
  filename="${i##*/}"
  no_ext="${filename%%.*}"
  /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2 \
  -x /gscratch/srlab/sr320/data/new_genome_files/chinook_genome_masked \
  -1 "$i" \
  -2 "$j" \
  -X 2000 --sensitive  --no-mixed --phred64 --no-discordant --no-unal \
  -S /gscratch/scrubbed/sr320/cw/1017/"$no_ext"_bowtie2.sam \
  -q \
  -p 28
done

OUTPUT: /var/services/homes/charlie/out/1101

[sr320@mox1 jobs]$ cat 1029_1600.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=bow33
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=100G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1029

source /gscratch/srlab/programs/scripts/paths.sh


for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*1.fq.gz; do
  read1=$(echo "$fastq")
  read1_array+=("$read1")
done

for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*2.fq.gz; do
  read2=$(echo "$fastq")
  read2_array+=("$read2")
done

for pair in "${!read1_array[@]}"; do
  i=${read1_array[$pair]}
  j=${read2_array[$pair]}
  filename="${i##*/}"
  no_ext="${filename%%.*}"
  /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2 \
  -x /gscratch/srlab/sr320/data/new_genome_files/chinook_genome_masked \
  -1 "$i" \
  -2 "$j" \
  -X 2000 --sensitive  --no-mixed --phred33 --no-discordant --no-unal \
  -S /gscratch/scrubbed/sr320/cw/"$no_ext"_bowtie2.sam \
  -q \
  -p 28
done

OUTPUT: /var/services/homes/charlie/out/1100

#sbatch

[code][sr320@mox1 jobs]$ cat 1024_1200.sh #!/bin/bash...

[sr320@mox1 jobs]$ cat 1024_1200.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=oakl
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=00-100:00:00
## Memory per node
#SBATCH --mem=100G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1024




source /gscratch/srlab/programs/scripts/paths.sh


find /gscratch/srlab/sr320/data/oakl/*_1.fq.gz \
| xargs basename -s _s1_R1_val_1.fq.gz | xargs -I{} /gscratch/srlab/programs/Bismark-0.19.0/bismark \
--path_to_bowtie /gscratch/srlab/programs/bowtie2-2.1.0 \
--score_min L,0,-1.2 \
-genome /gscratch/srlab/sr320/data/Cvirg-genome \
-p 28 \
-1 /gscratch/srlab/sr320/data/oakl/{}_s1_R1_val_1.fq.gz \
-2 /gscratch/srlab/sr320/data/oakl/{}_s1_R2_val_2.fq.gz \

/gscratch/srlab/programs/Bismark-0.19.0/deduplicate_bismark \
--bam -p \
/gscratch/srlab/sr320/analyses/1024/*.bam


/gscratch/srlab/programs/Bismark-0.19.0/bismark_methylation_extractor \
--bedGraph --counts --scaffolds \
--multicore 14 \
/gscratch/srlab/sr320/analyses/1024/*deduplicated.bam



# Bismark processing report

/gscratch/srlab/programs/Bismark-0.19.0/bismark2report

#Bismark summary report

/gscratch/srlab/programs/Bismark-0.19.0/bismark2summary



# Sort files for methylkit and IGV

find /gscratch/srlab/sr320/analyses/1024/*deduplicated.bam | \
xargs basename -s .bam | \
xargs -I{} /gscratch/srlab/programs/samtools-1.9/samtools \
sort --threads 28 /gscratch/srlab/sr320/analyses/1024/{}.bam \
-o /gscratch/srlab/sr320/analyses/1024/{}.sorted.bam

# Index sorted files for IGV
# The "-@ 16" below specifies number of CPU threads to use.

find /gscratch/srlab/sr320/analyses/1024/*.sorted.bam | \
xargs basename -s .sorted.bam | \
xargs -I{} /gscratch/srlab/programs/samtools-1.9/samtools \
index -@ 28 /gscratch/srlab/sr320/analyses/1024/{}.sorted.bam

#bismark, #sbatch

bowtie Phred64

sr320@mox1 ~]$ cat /gscratch/srlab/sr320/jobs/1017_0800.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=bow64
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=100G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1017

source /gscratch/srlab/programs/scripts/paths.sh


for fastq in /gscratch/scrubbed/sr320/Phred64_fqs/*1.fq.gz; do
  read1=$(echo "$fastq")
  read1_array+=("$read1")
done

for fastq in /gscratch/scrubbed/sr320/Phred64_fqs/*2.fq.gz; do
  read2=$(echo "$fastq")
  read2_array+=("$read2")
done

for pair in "${!read1_array[@]}"; do
  i=${read1_array[$pair]}
  j=${read2_array[$pair]}
  filename="${i##*/}"
  no_ext="${filename%%.*}"
  /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2 \
  -x /gscratch/srlab/sr320/data/Chinook_genome_scaffold_masked/chinook_genome_masked \
  -1 "$i" \
  -2 "$j" \
  -X 2000 --sensitive  --no-mixed --phred64 --no-discordant --no-unal \
  -S /gscratch/scrubbed/sr320/cw/1017/"$no_ext"_bowtie2.sam \
  -q \
  -p 28
done

[

#sbatch

[code][sr320@mox1 1013]$ cat /gscratch/srlab/sr320/jobs/1013_1200.sh #!/bin/bash...

[sr320@mox1 1013]$ cat /gscratch/srlab/sr320/jobs/1013_1200.sh 
#!/bin/bash
## Job Name
#SBATCH --job-name=bow33
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=500G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1013

source /gscratch/srlab/programs/scripts/paths.sh


for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*1.fq.gz; do
  read1=$(echo "$fastq")
  read1_array+=("$read1")
done

for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*2.fq.gz; do
  read2=$(echo "$fastq")
  read2_array+=("$read2")
done

for pair in "${!read1_array[@]}"; do
  i=${read1_array[$pair]}
  j=${read2_array[$pair]}
  filename="${i##*/}"
  no_ext="${filename%%.*}"
  /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2 \
  -x /gscratch/srlab/sr320/data/Chinook_genome_scaffold_masked/chinook_genome_masked \
  -1 "$i" \
  -2 "$j" \
  -X 2000 --sensitive  --no-mixed --phred33 --no-discordant --no-unal \
  -S /gscratch/scrubbed/sr320/cw/"$no_ext"_bowtie2.sam \
  -q \
  -p 28
done

#sbatch

[code]#!/bin/bash ## Job Name #SBATCH...

#!/bin/bash
## Job Name
#SBATCH --job-name=bow33
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=5-100:00:00
## Memory per node
#SBATCH --mem=500G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/1013

source /gscratch/srlab/programs/scripts/paths.sh


for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*1.fq.gz; do
  read1=$(echo "$fastq")
  read1_array+=("$read1")
done

for fastq in /gscratch/scrubbed/sr320/Phred33_fqs/*2.fq.gz; do
  read2=$(echo "$fastq")
  read2_array+=("$read2")
done

for pair in "${!read1_array[@]}"; do
  i=${read1_array[$pair]}
  j=${read2_array[$pair]}
  filename="${i##*/}"
  no_ext="${filename%%.*}"
  /gscratch/srlab/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2 -x \
  /gscratch/srlab/sr320/data/Chinook_genome_scaffold_masked \
  -1 "$i" \
  -2 "$j" \
  -X 2000 --sensitive  --no-mixed --phred33 --no-discordant --no-unal \
  -S /gscratch/scrubbed/sr320/cw/"$no_ext"_bowtie2.sam \
  -q \
  -p 28
done

#sbatch

[code]#!/bin/bash ## Job Name #SBATCH...

#!/bin/bash
## Job Name
#SBATCH --job-name=Cvblastx-nomax
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=4-00:00:00
## Memory per node
#SBATCH --mem=70G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/0929c
 
 
 
 
 
source /gscratch/srlab/programs/scripts/paths.sh
 
 
/gscratch/srlab/programs/ncbi-blast-2.6.0+/bin/blastx  \
-query /gscratch/srlab/sr320/query/GCF_002022765.2_C_virginica-3.0_cds_from_genomic.fna \
-db /gscratch/srlab/sr320/blastdb/uniprot_sprot_080917 \
-evalue 1E-05 \
-outfmt 6 \
-num_threads 28 \
-out Cvcds_from_genomic_sprot.blastout

#sbatch

[code] #!/bin/bash ## Job Name...

#!/bin/bash
## Job Name
#SBATCH --job-name=Cvblastx-nomax
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Resources
## Nodes (We only get 1, so this is fixed)
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=4-00:00:00
## Memory per node
#SBATCH --mem=70G
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/srlab/sr320/analyses/0929b





source /gscratch/srlab/programs/scripts/paths.sh


/gscratch/srlab/programs/ncbi-blast-2.6.0+/bin/blastx  \
-query /gscratch/srlab/sr320/query/GCF_002022765.2_C_virginica-3.0_rna.fna \
-db /gscratch/srlab/sr320/blastdb/uniprot_sprot_080917 \
-evalue 1E-05 \
-outfmt 6 \
-num_threads 28 \
-out Cv_sprot.blastout

#sbatch