Search Docs by Keyword

Table of Contents


module load bio/rcngs_v1
module load bio/rcngs_v1
# load all NGS related modules at one

Bowtie Alignment
module load bio/bowtie-0.12.7
bowtie # inspect command line options
bowtie-build genome.fasta genome.binary
# create binary genome (replace genome.fasta with your genome)
bowtie -q genome.binary query.fastq output.bowtie
# align query to genome and store output (replace ~/query.fastq with your query sequences
# and ~/genome.binary with the genome you built in the previous step)
bowtie -q genome.binary query.fastq output.bowtie
bowtie-inspect --names /n/bioseq/bowtie/mm9/mm9

BWA Alignment
module load bio/bwa-0.5.9
bwa index -a is genome.fasta # index reference genome
bwa aln genome.fasta query.fastq > output.sai # perform alignment
bwa samse -n -1 genome.fasta output.sai query.fastq > output.sam # generate SAM formatted alignment output
module load bio/samtools-0.1.12a
samtools view -bST genome.fasta output.sam -o output.bam #use samtools to generate bam file

SOAP Alignment
module load bio/soap-2.20
soap # inspect command line options
2bwt-builder genome.fasta
# create binary of reference genome
soap -a query.fastq -D genome.fasta.index -o output.soap
# align query to genome and store output

Tophat and Cufflinks
module load bio/tophat-1.1.4
tophat -o my_topHat --solexa1.3-quals --library-type fr-unstranded --solexa1.3-quals -G /n/bioseq/bowtie/mm9/GTF/mm9.ensembl.gtf --no-novel-juncs /n/bioseq/bowtie/mm9/mm9 my_sequence.fastq
module load bio/cufflinks-0.9.3
cufflinks -o mycuff_folder -L s5 -G /n/bioseq/bowtie/mm9/GTF/mm9.ensembl.gtf -r /n/bioseq/bowtie/mm9/mm9.fa  -N --library-type fr-unstranded accepted_hits.bam
# tophat: TopHat maps short sequences from spliced transcripts to whole genomes.
# Cufflinks assembles transcripts, estimates their abundances, and tests for differential expression and regulation in RNA-Seq samples

module load bio/soap-2.20
module load hpc/velvet_1.1.06
bsub -q bigmem velveth sillyDirectory 21 -fastq -shortPaired data/test_reads.fa
#make a cm.bsub script since ulimit used
----here is the cm.bsub file
#BSUB -q bigmem
#BSUB -x
ulimit -v $(( $(cat /proc/meminfo | grep MemTotal | awk '{print $2}')* 95/100))
velvetg sillyDirectory
------end of cm.bsub
bsub#velvetg has unusual demand for memory
#bigmem queue has 32GB RAM to 128GB RAM
#exclusive use and limit to 95% of the total available memory

© The President and Fellows of Harvard College
Except where otherwise noted, this content is licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.