genefish 18:28 on March 30
Tags: SBATCH

job-name=cg-spur

#!/bin/bash
## Job Name
#SBATCH --job-name=cg-spur
## Allocation Definition
#SBATCH --account=coenv 
#SBATCH --partition=coenv
## Resources Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=4-12:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL 
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/sr320/033021-roslin-spur


# Load Python Mox module for Python module availability

module load intel-python3_2017




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



/gscratch/srlab/programs/ncbi-blast-2.10.1+/bin/blastx \
-query /gscratch/srlab/sr320/data/cg/rna.fna \
-db /gscratch/srlab/sr320/blastdb/ProteinsSpur5.0 \
-out /gscratch/scrubbed/sr320/033021-roslin-spur/CgRNA-blastx-spur.tab \
-num_threads 40 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt "6 qaccver saccver evalue"

genefish 18:17 on March 26
Tags: SBATCH

-job-name=cg-spur

#!/bin/bash
## Job Name
#SBATCH --job-name=cg-spur
## Allocation Definition
#SBATCH --account=coenv 
#SBATCH --partition=coenv
## Resources Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=4-12:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL 
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/sr320/032621-roslin-spur


# Load Python Mox module for Python module availability

module load intel-python3_2017




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



/gscratch/srlab/programs/ncbi-blast-2.10.1+/bin/blastx \
-query /gscratch/srlab/sr320/data/Cgig-genome/roslin_M/cgigas_uk_roslin_v1_genomic-mito.fa \
-db /gscratch/srlab/sr320/blastdb/ProteinsSpur5.0 \
-out /gscratch/scrubbed/sr320/032621-roslin-spur/Cg-blastx-spur.tab \
-num_threads 40 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt "6 qaccver saccver evalue"

genefish 16:42 on March 5
Tags: Bismark ( 9 ), creating ( 2 ), run ( 2 ), SBATCH

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

genefish 16:54 on February 19
Tags: --parallel ( 2 ), --path_to_aligner ( 2 ), --verbose ( 2 ), Bismark ( 9 ), SBATCH

job-name=hw-bsnlP

#!/bin/bash
## Job Name
#SBATCH --job-name=hw-bsnlP
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=10-00:00:00
## 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/sr320/021921-hw-bsnP
 
 
 
# 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/Crassostrea_gigas.oyster_v9.dna_sm.toplevel/"
 
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.20201206.fq.gz \
| xargs basename -s _R1.fastp-trim.20201206.fq.gz | xargs -n 1 -P 6 -I{} ${bismark_dir}/bismark \
--path_to_bowtie ${bowtie2_dir} \
-genome ${genome_folder} \
-p 4 \
--non_directional \
-1 ${reads_dir}{}_R1.fastp-trim.20201206.fq.gz \
-2 ${reads_dir}{}_R2.fastp-trim.20201206.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 14 \
--buffer_size 75% \
*deduplicated.bam
 
 
 
# Bismark processing report
 
${bismark_dir}/bismark2report
 
#Bismark summary report
 
${bismark_dir}/bismark2summary
 
 
 
# 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

#parallel, #path_to_aligner, #verbose, #bismark, #sbatch

genefish 19:30 on February 13
Tags: --parallel ( 2 ), --path_to_aligner ( 2 ), --verbose ( 2 ), Bismark ( 9 ), creating ( 2 ), SBATCH

job-name=hw-bs

#!/bin/bash
## Job Name
#SBATCH --job-name=hw-bs
## Allocation Definition
#SBATCH --account=srlab
#SBATCH --partition=srlab
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=20-00:00:00
## 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/sr320/021321-hw-bs



# 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/Crassostrea_gigas.oyster_v9.dna_sm.toplevel/"

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.20201206.fq.gz \
| xargs basename -s _R1.fastp-trim.20201206.fq.gz | xargs -I{} ${bismark_dir}/bismark \
--path_to_bowtie ${bowtie2_dir} \
-genome ${genome_folder} \
-p 4 \
-score_min L,0,-0.6 \
--non_directional \
-1 ${reads_dir}{}_R1.fastp-trim.20201206.fq.gz \
-2 ${reads_dir}{}_R2.fastp-trim.20201206.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 14 \
--buffer_size 75% \
*deduplicated.bam



# Bismark processing report

${bismark_dir}/bismark2report

#Bismark summary report

${bismark_dir}/bismark2summary



# 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 _R1_001_val_1_bismark_bt2_pe.deduplicated.bismark.cov.gz \
# | xargs -I{} ${bismark_dir}/coverage2cytosine \
# --genome_folder ${genome_folder} \
# -o {} \
# --merge_CpG \
# --zero_based \
# {}_R1_001_val_1_bismark_bt2_pe.deduplicated.bismark.cov.gz
# 
# 
# #creating bedgraphs post merge
# 
# for f in *merged_CpG_evidence.cov
# do
#   STEM=$(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

#parallel, #path_to_aligner, #verbose, #bismark, #creating, #sbatch

genefish 17:57 on February 13
Tags: SBATCH

job-name=cg-spur

#!/bin/bash
## Job Name
#SBATCH --job-name=cg-spur
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=4-12:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/sr320/021321-cgig-spur


# Load Python Mox module for Python module availability

module load intel-python3_2017




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



/gscratch/srlab/programs/ncbi-blast-2.10.1+/bin/blastx \
-query /gscratch/srlab/sr320/data/cg/GCF_000297895.1_oyster_v9_cds_from_genomic.fna \
-db /gscratch/srlab/sr320/blastdb/ProteinsSpur5.0  \
-out /gscratch/scrubbed/sr320/021321-cgig-spur/Cg-blastx-spur.tab \
-num_threads 40 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt "6 qaccver saccver evalue"

genefish 23:12 on February 8
Tags: SBATCH

Mox Job – blastx

#!/bin/bash
## Job Name
#SBATCH --job-name=blasts
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=0-12:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=sr320@uw.edu
## Specify the working directory for this job
#SBATCH --chdir=/gscratch/scrubbed/sr320/020821-cgig-sp


# Load Python Mox module for Python module availability

module load intel-python3_2017




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



/gscratch/srlab/programs/ncbi-blast-2.8.1+/bin/blastx \
-query /gscratch/srlab/sr320/data/cg/GCF_000297895.1_oyster_v9_cds_from_genomic.fna \
-db /gscratch/srlab/blastdbs/UniProtKB_20190109/uniprot_sprot.fasta  \
-out /gscratch/scrubbed/sr320/020821-cgig-sp/Cg-blastx-sp.tab \
-evalue 1E-05 \
-num_threads 40 \
-max_target_seqs 1 \
-max_hsps 1 \
-outfmt "6 qaccver saccver evalue"

genefish 21:18 on December 17
Tags: Bismark ( 9 ), SBATCH

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

#!/bin/bash
## Job Name
#SBATCH --job-name=re-duck
## 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=30-00:00:00
## 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/sr320/1217/



# 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/strigg/data/Pgenr/FASTQS/"
genome_folder="/gscratch/srlab/sr320/data/geoduck/v01/"

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



${bismark_dir}/bismark_genome_preparation \
--verbose \
--parallel 28 \
--path_to_aligner ${bowtie2_dir} \
${genome_folder}


find ${reads_dir}*_R1_001_val_1.fq.gz \
| xargs basename -s _R1_001_val_1.fq.gz | xargs -I{} ${bismark_dir}/bismark \
--path_to_bowtie ${bowtie2_dir} \
-genome /gscratch/srlab/sr320/data/geoduck/v01 \
-p 4 \
-score_min L,0,-0.6 \
-1 /gscratch/srlab/strigg/data/Pgenr/FASTQS/{}_R1_001_val_1.fq.gz \
-2 /gscratch/srlab/strigg/data/Pgenr/FASTQS/{}_R2_001_val_2.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 14 \
--buffer_size 75% \
*deduplicated.bam



# Bismark processing report

${bismark_dir}/bismark2report

#Bismark summary report

${bismark_dir}/bismark2summary



# 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 _R1_001_val_1_bismark_bt2_pe.deduplicated.bismark.cov.gz \
| xargs -I{} ${bismark_dir}/coverage2cytosine \
--genome_folder ${genome_folder} \
-o {} \
--merge_CpG \
--zero_based \
{}_R1_001_val_1_bismark_bt2_pe.deduplicated.bismark.cov.gz

#bismark, #sbatch

genefish 21:17 on December 17
Tags: -q ( 2 ), -U ( 2 ), -x ( 2 ), bowtie2 ( 2 ), conduct ( 2 ), do ( 2 ), done ( 2 ), echo ( 2 ), Explanation ( 2 ), for ( 3 ), SBATCH

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

#!/bin/bash
## Job Name
#SBATCH --job-name=el_01
## 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=3-12:00:00
## 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/sr320/1117c/


# Eleni 20191107
# The purpose of this script is to align fastq files to a genome, and output the # alignments as bam files, whose mapping quality is greater than 30. 
# to run this script, place in same folder as the files you want to move and write ./bowtie2_cluster.sh in terminal 

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



find /gscratch/scrubbed/sr320/eleni/*.fq | xargs basename -s .fq | xargs -I{} bowtie2 \
-x /gscratch/scrubbed/sr320/eleni/GCA_900700415 \
-U /gscratch/scrubbed/sr320/eleni/{}.fq \
-p 28 \
-S /gscratch/scrubbed/sr320/1117c/{}.sam



find /gscratch/scrubbed/sr320/1117/*.sam | \
xargs basename -s .sam | \
xargs -I{} /gscratch/srlab/programs/samtools-1.9/samtools \
view -b -q 30 /gscratch/scrubbed/sr320/1117c/{}.sam -o /gscratch/scrubbed/sr320/1117c/{}.bam


#for file in $files
#do
    #echo ${file} # print the filename to terminal screen
    #bowtie2 -q -x GCA_900700415 -U ${file}.fq|samtools view -b -q 30 > ${file}.bam #conduct the alignment and output the file
#done




#Explanation of terms:
#bowtie2 -q -x <bt2-idx> -U <r> -S <sam>
#-q query input files are in fastq format
#-x <bt2-idx> Indexed "reference genome" filename prefix (minus trailing .X.bt2).
#-U <r> Files with unpaired reads.

# The default of bowtie2, is to write the output of the alignment to the terminal. 
# Also, bowtie does not write BAM files directly, but SAM output can be converted to BAM on the fly by piping bowtie's output to samtools view. 
# samtools options
#  -b       output BAM
# -q <integer> : discards reads whose mapping quality is below this number


#for file in $files
#do
    #echo ${file} # print the filename to terminal screen
    #bowtie2 -q -x GCA_900700415 -U ${file}.fq|samtools view -b -q 30 > ${file}.bam #conduct the alignment and output the file
#done

#q, #u, #x, #bowtie2, #conduct, #do, #done, #echo, #explanation, #for, #sbatch

genefish 14:45 on November 18
Tags: -q ( 2 ), -U ( 2 ), -x ( 2 ), bowtie2 ( 2 ), conduct ( 2 ), do ( 2 ), done ( 2 ), echo ( 2 ), Explanation ( 2 ), for ( 3 ), SBATCH

bowtie

#!/bin/bash
## Job Name
#SBATCH --job-name=el_01
## 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=3-12:00:00
## 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/sr320/1117c/


# Eleni 20191107
# The purpose of this script is to align fastq files to a genome, and output the # alignments as bam files, whose mapping quality is greater than 30. 
# to run this script, place in same folder as the files you want to move and write ./bowtie2_cluster.sh in terminal 

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



find /gscratch/scrubbed/sr320/eleni/*.fq | xargs basename -s .fq | xargs -I{} bowtie2 \
-x /gscratch/scrubbed/sr320/eleni/GCA_900700415 \
-U /gscratch/scrubbed/sr320/eleni/{}.fq \
-p 28 \
-S /gscratch/scrubbed/sr320/1117c/{}.sam



find /gscratch/scrubbed/sr320/1117/*.sam | \
xargs basename -s .sam | \
xargs -I{} /gscratch/srlab/programs/samtools-1.9/samtools \
view -b -q 30 /gscratch/scrubbed/sr320/1117c/{}.sam -o /gscratch/scrubbed/sr320/1117c/{}.bam


#for file in $files
#do
    #echo ${file} # print the filename to terminal screen
    #bowtie2 -q -x GCA_900700415 -U ${file}.fq|samtools view -b -q 30 > ${file}.bam #conduct the alignment and output the file
#done




#Explanation of terms:
#bowtie2 -q -x <bt2-idx> -U <r> -S <sam>
#-q query input files are in fastq format
#-x <bt2-idx> Indexed "reference genome" filename prefix (minus trailing .X.bt2).
#-U <r> Files with unpaired reads.

# The default of bowtie2, is to write the output of the alignment to the terminal. 
# Also, bowtie does not write BAM files directly, but SAM output can be converted to BAM on the fly by piping bowtie's output to samtools view. 
# samtools options
#  -b       output BAM
# -q <integer> : discards reads whose mapping quality is below this number


#for file in $files
#do
    #echo ${file} # print the filename to terminal screen
    #bowtie2 -q -x GCA_900700415 -U ${file}.fq|samtools view -b -q 30 > ${file}.bam #conduct the alignment and output the file
#done

#q, #u, #x, #bowtie2, #conduct, #do, #done, #echo, #explanation, #for, #sbatch

s: search
c: compose new post
r: reply
e: edit
t: go to top
j: go to the next post or comment
k: go to the previous post or comment
o: toggle comment visibility
esc: cancel edit post or comment