-
Notifications
You must be signed in to change notification settings - Fork 3
/
star_driver_generic.sh
83 lines (66 loc) · 3.29 KB
/
star_driver_generic.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
#!/bin/bash
#$ -V
#$ -cwd
#$ -S /bin/bash
#$ -N myoAus_map
#$ -o $JOB_NAME.o$JOB_ID
#$ -e $JOB_NAME.e$JOB_ID
#$ -q Yoda
#$ -pe fill 6
#$ -P communitycluster
#I had trouble running this on any queues other than Yoda. The problem seems to be associated with memory. I also had trouble if I tried to use more than 6 processors. It still runs in a few hours with a reasonable amount of data.
BASEDIR=/lustre/scratch/daray/Ray_low_cov_work/star-mAus
WORKDIR=$BASEDIR/output
cd $WORKDIR
THREADS=5
RAW_READS_HOME=$BASEDIR/reads #the location of your raw data. Not needed but legacied from other scripts
PROCESSED_READS_HOME=$BASEDIR/processed_reads #The paired and unpaired read files generated by trimmomatic from the raw data
DRAFTS_HOME=$BASEDIR/drafts #the location of the genome draft(s). Should at least house the genome draft you are mapping to.
GENOME_HOME=$BASEDIR/genome #the location of your genome indexes to be generated by STAR
######
#set up alias' for major programs
######
BWA_HOME=/lustre/work/apps/bwa-0.7.12
SAMTOOLS_HOME=/lustre/work/apps/samtools-1.2
SAMTOOLS1_8_HOME=/lustre/work/apps/samtools-0.1.18
PICARD_HOME=/lustre/work/apps/picard-tools-1.91
BCFTOOLS_HOME=/lustre/work/apps/samtools-0.1.18/bcftools
RAY_SOFTWARE=/lustre/work/daray/software
TRIM_HOME=/lustre/work/apps/Trimmomatic-0.27
FASTX_HOME=/lustre/work/apps/fastx_toolkit-0.0.14/bin
VCFTOOLS_HOME=/lustre/work/daray/software/vcftools_0.1.12b/bin
BEDTOOLS_HOME=/lustre/work/apps/bedtools-2.17.0/bin
TOPHAT_HOME=/lustre/work/apps/tophat-2.1.0.Linux_x86_64
CUFFLINKS_HOME=/lustre/work/apps/cufflinks-2.2.1/bin
BOWTIE2_HOME=/lustre/work/apps/bowtie2-2.0.5
STAR_HOME=/lustre/work/apps/STAR-2.4/bin
################################################################################
# 1 Generate index for genome with STAR
#~~~~~~~~~~~
GENOME=M8132 #Identifier for your genome draft
DRAFT=myoAus # taxon dexignation for your genome draft
RNASEQ_TAXON=myoVel # taxon origin for your RNAseq data. May or may not be the same as your draft taxon
$STAR_HOME/STAR \
--runThreadN $THREADS \
--runMode genomeGenerate \
--genomeDir $GENOME_HOME \
--genomeFastaFiles $DRAFTS_HOME/$GENOME"_mem.fa"
echo $DRAFT"_index_finished" | mailx -s $DRAFT"_index_finished" [email protected]
################################################################################
# 2 Map RNA-Seq reads to genome with STAR
#~~~~~~~~~~~
SAMPLE1=11750X4 #Use these to designate your paired reads for --readFilesIn
SAMPLE2=11750X11
SAMPLE3=11750X12
SAMPLE4=11750X14
$STAR_HOME/STAR \
--runThreadN $THREADS \
--genomeDir $GENOME_HOME \
--readFilesIn \
$PROCESSED_READS_HOME/$SAMPLE1"_R1_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE2"_R1_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE3"_R1_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE4"_R1_paired.fastq.gz" $PROCESSED_READS_HOME/$SAMPLE1"_R2_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE2"_R2_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE3"_R2_paired.fastq.gz",$PROCESSED_READS_HOME/$SAMPLE4"_R2_paired.fastq.gz" \
--readFilesCommand zcat \
--outFileNamePrefix $DRAFT"_v_"$RNASEQ_TAXON \
--outSAMtype BAM SortedByCoordinate \
--outBAMsortingThreadN $THREADS
echo $DRAFT"_v_"$RNASEQ_TAXON"_mapping_finished" | mailx -s $DRAFT"_v_"$RNASEQ_TAXON"_mapping_finished" [email protected]
sleep 5