Changes between Version 79 and Version 80 of SOPs/mapping

Timestamp:

07/29/24 10:42:48 (5 months ago)

Author:

xinlei.gao

Comment:

Change bsub to sbatch

SOPs/mapping

@@ -24 +24 @@
 {{{
 # Align single-end reads
-bsub "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.fq > Mapped_reads.sai"
-bsub "bwa samse /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Mapped_reads.sai Reads.fq > Reads.bwa.sam"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.fq > Mapped_reads.sai"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa samse /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Mapped_reads.sai Reads.fq > Reads.bwa.sam"
 # Align paired-end reads
-bsub "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.1.fq > Mapped_reads.1.sai"
-bsub "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.2.fq > Mapped_reads.2.sai"
-bsub "bwa sampe /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Mapped_reads.1.sai Mapped_reads.2.sai Reads.1.fq Reads.2.fq > Reads.bwa.sam"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.1.fq > Mapped_reads.1.sai"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa aln /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Reads.2.fq > Mapped_reads.2.sai"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa sampe /nfs/genomes/mouse_gp_jul_07_no_random/bwa/mm9.fa Mapped_reads.1.sai Mapped_reads.2.sai Reads.1.fq Reads.2.fq > Reads.bwa.sam"
 }}}
 
@@ -37 +37 @@
 {{{
 # Align single-end reads
-bsub "bwa mem /nfs/genomes/sgd_2010/bwa/sacCer3.fa Reads.fq > Mapped_reads.bwa.sam"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa mem /nfs/genomes/sgd_2010/bwa/sacCer3.fa Reads.fq > Mapped_reads.bwa.sam"
 # Align paired-end reads
-bsub "bwa mem /nfs/genomes/sgd_2010/bwa/sacCer3.fa Reads.1.fq Reads.2.fq > Mapped_reads.bwa.sam"
+sbatch --partition 20 --job-name=bwa --mem=32G --wrap "bwa mem /nfs/genomes/sgd_2010/bwa/sacCer3.fa Reads.1.fq Reads.2.fq > Mapped_reads.bwa.sam"
 }}}
 
@@ -78 +78 @@
 
 {{{
-bsub "bowtie2 -x /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 -U s_7.txt | samtools view -bS - > s7_mm9.bam"
+sbatch --partition=20 --job-name=bt2 --mem=32G --wrap "bowtie2 -x /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 -U s_7.txt | samtools view -bS - > s7_mm9.bam"
 }}}
 
@@ -87 +87 @@
 Sample command:
 {{{
-bsub bowtie  -k 1 -n 2 -l 50 --best --sam --solexa1.3-quals /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 Sample_A.fq Sample_A.mm9.k1.n2.l50.best.sam
+sbatch --partition=20 --job-name=bt --mem=32G --wrap "bowtie  -k 1 -n 2 -l 50 --best --sam --solexa1.3-quals /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 Sample_A.fq Sample_A.mm9.k1.n2.l50.best.sam"
 }}}
 
@@ -124 +124 @@
 To generate genome index files for STAR:
 {{{
-bsub STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDir --genomeFastaFiles /path/to/genome/fasta1 /path/to/genome/fasta2 --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 
+sbatch --partition=20 --job-name=star_idx --cpus-per-task=8 --mem=64G --wrap "STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDir --genomeFastaFiles /path/to/genome/fasta1 /path/to/genome/fasta2 --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 "
 
 #generate index without overhang/gtf, specify these at mapping instead
-bsub STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDir --genomeFastaFiles /path/to/genome/fasta1 /path/to/genome/fasta2 --runThreadN 8 
+sbatch --partition=20 --job-name=star_idx --cpus-per-task=8 --mem=64G --wrap "STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDir --genomeFastaFiles /path/to/genome/fasta1 /path/to/genome/fasta2 --runThreadN 8 "
 
 }}}
@@ -139 +139 @@
 {{{
 # Input format: fastq ; output format: SAM
-bsub STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fastq /path/to/read2.fastq --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8
+sbatch --partition=20 --job-name=star_map --cpus-per-task=8 --mem=64G --wrap "STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fastq /path/to/read2.fastq --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8"
 # Input format: fastq.gz ; output format: BAM (sorted by position)
-bsub STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fq.gz /path/to/read2.fq.gz --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8 --readFilesCommand zcat --outSAMtype BAM SortedByCoordinate
+sbatch --partition=20 --job-name=star_map --cpus-per-task=8 --mem=64G --wrap "STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fq.gz /path/to/read2.fq.gz --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8 --readFilesCommand zcat --outSAMtype BAM SortedByCoordinate"
 
 #mapping when gtf/overhang was not specified during indexing
-bsub STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fq.gz /path/to/read2.fq.gz --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8 --readFilesCommand zcat --outSAMtype BAM SortedByCoordinate --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang readLength-1
+sbatch --partition=20 --job-name=star_map --cpus-per-task=8 --mem=64G --wrap "STAR --genomeDir /path/to/GenomeDir --readFilesIn /path/to/read1.fq.gz /path/to/read2.fq.gz --outFileNamePrefix whateverPrefix --sjdbScore 2 --runThreadN 8 --readFilesCommand zcat --outSAMtype BAM SortedByCoordinate --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang readLength-1 "
 
 }}}
@@ -176 +176 @@
 To generate FirstPass genome index files for STAR:
 {{{
-bsub STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDirFirstPass --genomeFastaFiles /path/to/genome/fasta --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 
+sbatch --partition=20 --job-name=st_1stIdx --cpus-per-task=8 --mem=64G --wrap "STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDirFirstPass --genomeFastaFiles /path/to/genome/fasta --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 "
 }}}
 
@@ -182 +182 @@
     '''Run this command within the FirstPass directory'''
 {{{
-bsub STAR --genomeDir /path/to/GenomeDirFirstPass --readFilesIn /path/to/Reads_1.fastq --outFileNamePrefix whateverPrefix --runThreadN 8
+sbatch --partition=20 --job-name=st_1stMap --cpus-per-task=8 --mem=64G --wrap "STAR --genomeDir /path/to/GenomeDirFirstPass --readFilesIn /path/to/Reads_1.fastq --outFileNamePrefix whateverPrefix --runThreadN 8"
 }}}
 
@@ -192 +192 @@
 {{{
 
-bsub STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDirSecondPass --genomeFastaFiles /path/to/genome/fasta --sjdbFileChrStartEnd /path/to/first/pass/directory/SJ.out.tab --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 
+sbatch --partition=20 --job-name=st_2ndIdx --cpus-per-task=8 --mem=64G --wrap "STAR --runMode genomeGenerate --genomeDir /path/to/GenomeDirSecondPass --genomeFastaFiles /path/to/genome/fasta --sjdbFileChrStartEnd /path/to/first/pass/directory/SJ.out.tab --sjdbGTFfile /path/to/GTF/FileName.gtf --sjdbOverhang 100 --runThreadN 8 "
 }}}
 
@@ -198 +198 @@
     '''Run this command within the SecondPass directory'''
 {{{
-Input format: fastq ; output format: SAM
-bsub STAR --genomeDir /path/to/GenomeDirSecondPass --readFilesIn /path/to/Reads_1.fastq  --outFileNamePrefix whateverPrefix --runThreadN 8
+#Input format: fastq ; output format: SAM
+sbatch --partition=20 --job-name=st_2ndMap --cpus-per-task=8 --mem=64G --wrap "STAR --genomeDir /path/to/GenomeDirSecondPass --readFilesIn /path/to/Reads_1.fastq  --outFileNamePrefix whateverPrefix --runThreadN 8"
 }}}
 
@@ -210 +210 @@
 {{{
 # Single-end reads
-bsub tophat -o s_7_tophat_out --phred64-quals --library-type fr-firststrand --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.txt
+sbatch --partition=20 --job-name=tophat --mem=32G --wrap "tophat -o s_7_tophat_out --phred64-quals --library-type fr-firststrand --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.txt"
 # Paired-end reads
 # For PE reads, specifiy expected (mean) inner distance using -r option (default is 50bp).  The inner distance, or insert size, does not include length of the reads/mates.  For example, PE run with fragments selected at 300bp, where each end is 50bp, you should set -r to be 200. 
-bsub tophat -o s_7_tophat_out --phred64-quals --library-type fr-firststrand --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.1.txt s_7.2.txt
+sbatch --partition=20 --job-name=tophat --mem=32G --wrap "tophat -o s_7_tophat_out --phred64-quals --library-type fr-firststrand --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.1.txt s_7.2.txt"
 }}}
 
@@ -249 +249 @@
 Sample command:
 {{{
-bsub tophat -o s_7_tophat_out -p 6 --phred64-quals --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.txt
+sbatch --partition=20 --job-name=tophat --cpus-per-task=6 --mem=32G --wrap "tophat -o s_7_tophat_out -p 6 --phred64-quals --segment-length 20 -I 200000 -G /nfs/genomes/mouse_gp_jul_07_no_random/gtf/Mus_musculus.NCBIM37.67_noNT.gtf --no-novel-juncs /nfs/genomes/mouse_gp_jul_07_no_random/bowtie/mm9 s_7.txt"
 }}}