Difference between revisions of "Tassel 5 GBS v2 Pipeline sample script for calling SNPs using reference genome"

From Poland Lab Wiki
Jump to: navigation, search
(Created page with "==== For this script to work properly, you should have 'gbs' folder in your home directory, and 'jobs' and 'projects' folders inside 'gbs' ==== Once you have the full script...")
 
 
(47 intermediate revisions by the same user not shown)
Line 1: Line 1:
==== For this script to work properly, you should have 'gbs' folder in your home directory, and 'jobs' and 'projects' folders inside 'gbs' ====
+
==== For this script to work properly, you should have <code>gbs</code> folder in your home directory, and <code>jobs</code> and <code>projects</code> folders inside <code>gbs</code> ====
  
Once you have the full script copied in a file with extension '.sh', the 'name' variable should be replaced with something more explicit, such as '''hessian_F3''' for a Hessian fly project with F3 population. To do this in a semi-automatic fashion, use 'find and replace' function in your text editor and replace 'name' variable with 'hessian_F3' or any other project name.
+
* Once you have the full script copied in a simple text file with extension <code>.sh</code>, the <code>name</code> variable should be replaced with something more explicit, such as your project name.
  
 +
* Keyfile should have these 4 mandatory headers:  'Flowcell'  'Lane'  'Barcode'  'FullSampleName'
  
''Start your script with the following piece of code. First line is called Shebang and is required for a shell script. The 'PATH' variable can be changed if the software is installed elsewhere, otherwise, leave it as it is''
+
<blockquote>
 +
'''''To keep everything organized, I recommend using the same base name for the project and the files, for example'''''
  
<pre>
+
<code>name</code> = projectName
#!/bin/bash
+
export PATH=$PATH:/homes/nss470/usr/bin:/homes/nss470/usr/bin/bin
+
</pre>
+
  
 +
Keyfile name = projectName.txt
  
''Update the ''<code>user</code> ''variable with your K-State eID''
+
Shell script name = projectName.sh
<pre>
+
</blockquote>
user=eID
+
</pre>
+
  
 +
* Once the Keyfile and shell script are ready, put them in <code>jobs</code> folder and run <code> sbatch projectName.sh </code>
  
''Requesting beocat resources''
 
<pre>
 
#$ -l h_rt=60:00:00
 
#$ -l mem=64G
 
#$ -M your_email -m aes
 
#$ -N name
 
#$ -cwd
 
</pre>
 
  
 +
<syntaxhighlight lang="bash">
 +
#!/bin/bash -l
  
''Path to keyfile --> '''keyfile''' should have following 4 mandatory headers''
+
# Update beocat resources request
 +
#SBATCH --mem-per-cpu=64G  # Memory per core, use --mem= for memory per node
 +
#SBATCH --time=02-00:00:00  # Use the form DD-HH:MM:SS
 +
#SBATCH --mail-user=eID@ksu.edu --mail-type=ALL  # same as =BEGIN,FAIL,END
 +
#SBATCH --job-name=projectName
  
'Flowcell' 'Lane' 'Barcode' 'FullSampleName'
+
# Update the 'user' and 'name' variables, 'eID' is your K-State eID.
 +
user=eID
 +
name=projectName
  
''Place the keyfile in your 'jobs' folder. It should be renamed to the what you are replacing the name variable with, for example 'hessian_F3.txt'''
+
## #######################################
<pre>
+
## NO NEED TO CHANGE ANYTHING FROM HERE ON
keyFile=/homes/$user/gbs/jobs/name.txt
+
## #######################################
</pre>
+
  
 +
# Load Java module and set JAVA VM Version to 1.8 (if default is different)
 +
module load Java
 +
 +
keyFile=/homes/$user/gbs/jobs/${name}.txt
  
''Path to sequence directory''
 
<pre>
 
 
seqDir=/bulk/jpoland/sequence
 
seqDir=/bulk/jpoland/sequence
</pre>
+
dbPath=/bulk/nss470/genomes/CS_NRGene/pseudomolecules_v1.0/161010_Chinese_Spring_v1.0_pseudomolecules_parts
 
+
 
+
''Database path (reference genome)''
+
<pre>
+
dbPath=/bulk/jpoland/genome/ChineseSpring/pseudomolecules_v1.0/161010_Chinese_Spring_v1.0_pseudomolecules_parts
+
</pre>
+
 
+
 
+
''TASSEL5 path''
+
<pre>
+
 
tasselPath=/homes/nss470/softwares/tassel5/run_pipeline.pl
 
tasselPath=/homes/nss470/softwares/tassel5/run_pipeline.pl
</pre>
 
  
 +
mkdir /homes/$user/gbs/projects/${name}
 +
mkdir /homes/$user/gbs/projects/${name}/keyFileSh
 +
cd /homes/$user/gbs/projects/${name}
  
''Create required directories for output''
+
# Path for required software
<pre>
+
export PATH=$PATH:/homes/nss470/usr/bin:/homes/nss470/usr/bin/bin
mkdir /homes/$user/gbs/projects/name
+
mkdir /homes/$user/gbs/projects/name/keyFileSh
+
cd /homes/$user/gbs/projects/name
+
</pre>
+
 
+
  
''Running TASSEL 5 SNP calling pipeline in series of steps. Each step uses mostly the default settings that can be changed if desired''
 
<syntaxhighlight lang="java">
 
 
## GBSSeqToTagDBPlugin - RUN Tags to DB
 
## GBSSeqToTagDBPlugin - RUN Tags to DB
 
$tasselPath -Xms64G -Xmx64G -fork1 -GBSSeqToTagDBPlugin -e PstI-MspI \
 
$tasselPath -Xms64G -Xmx64G -fork1 -GBSSeqToTagDBPlugin -e PstI-MspI \
 
     -i $seqDir \
 
     -i $seqDir \
     -db name.db \
+
     -db ${name}.db \
 
     -k $keyFile \
 
     -k $keyFile \
 
     -kmerLength 64 -minKmerL 20 -mnQS 20 -mxKmerNum 250000000 \
 
     -kmerLength 64 -minKmerL 20 -mnQS 20 -mxKmerNum 250000000 \
     -endPlugin -runfork1 >> z_name_GBSSeqToTagDB.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## TagExportToFastqPlugin - export Tags
 
## TagExportToFastqPlugin - export Tags
 
$tasselPath -fork1 -TagExportToFastqPlugin \
 
$tasselPath -fork1 -TagExportToFastqPlugin \
     -db name.db \
+
     -db ${name}.db \
     -o name_tagsForAlign.fq -c 1 \
+
     -o ${name}_tagsForAlign.fa.gz -c 10 \
     -endPlugin -runfork1 >> z_name_TagExportToFastq.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## RUN BOWTIE
 
## RUN BOWTIE
bowtie2 -p 15 --very-sensitive-local \
+
bowtie2 -p 20 --end-to-end \
 
     -x $dbPath \
 
     -x $dbPath \
     -U name_tagsForAlign.fq \
+
     -U ${name}_tagsForAlign.fa.gz \
     -S name.sam >> z_name_bowtie2.out
+
     -S ${name}.sam >> z_pipeline.out
  
 
## SAMToGBSdbPlugin - SAM to DB
 
## SAMToGBSdbPlugin - SAM to DB
 
$tasselPath -Xms64G -Xmx64G -fork1 -SAMToGBSdbPlugin \
 
$tasselPath -Xms64G -Xmx64G -fork1 -SAMToGBSdbPlugin \
     -i name.sam \
+
     -i ${name}.sam \
     -db name.db \
+
     -db ${name}.db \
 
     -aProp 0.0 -aLen 0 \
 
     -aProp 0.0 -aLen 0 \
     -endPlugin -runfork1 >> z_name_SAMToGBSdb.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## DiscoverySNPCallerPluginV2 - RUN DISCOVERY SNP CALLER
 
## DiscoverySNPCallerPluginV2 - RUN DISCOVERY SNP CALLER
 
$tasselPath -Xms64G -Xmx64G -fork1 -DiscoverySNPCallerPluginV2 \
 
$tasselPath -Xms64G -Xmx64G -fork1 -DiscoverySNPCallerPluginV2 \
     -db name.db \
+
     -db ${name}.db \
 
     -mnLCov 0.1 -mnMAF 0.01 -deleteOldData true \
 
     -mnLCov 0.1 -mnMAF 0.01 -deleteOldData true \
     -endPlugin -runfork1 >> z_name_DiscoverySNPCaller.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## SNPQualityProfilerPlugin - RUN QUALITY PROFILER
 
## SNPQualityProfilerPlugin - RUN QUALITY PROFILER
 
$tasselPath -Xms64G -Xmx64G -fork1 -SNPQualityProfilerPlugin \
 
$tasselPath -Xms64G -Xmx64G -fork1 -SNPQualityProfilerPlugin \
     -db name.db \
+
     -db ${name}.db \
     -statFile name_SNPqual_stats.txt \
+
     -statFile ${name}_SNPqual_stats.txt \
     -endPlugin -runfork1 >> z_name_SNPQualityProfiler.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## UpdateSNPPositionQualityPlugin - UPDATE DATABASE WITH QUALITY SCORE
 
## UpdateSNPPositionQualityPlugin - UPDATE DATABASE WITH QUALITY SCORE
 
$tasselPath -Xms64G -Xmx64G -fork1 -UpdateSNPPositionQualityPlugin \
 
$tasselPath -Xms64G -Xmx64G -fork1 -UpdateSNPPositionQualityPlugin \
     -db name.db \
+
     -db ${name}.db \
     -qsFile name_SNPqual_stats.txt \
+
     -qsFile ${name}_SNPqual_stats.txt \
    -endPlugin -runfork1 >> z_name_UpdateSNPPositionQuality.out
+
     -endPlugin -runfork1 >> z_pipeline.out
 
+
## ProductionSNPCallerPluginV2 - RUN PRODUCTION PIPELINE - output .h5
+
$tasselPath -Xms64G -Xmx64G -fork1 -ProductionSNPCallerPluginV2 \
+
    -db name.db \
+
    -i $seqDir \
+
    -k $keyFile \
+
    -o name.h5 \
+
    -e PstI-MspI -kmerLength 64 \
+
     -endPlugin -runfork1 >> z_name_ProductionSNPCaller.out
+
  
 
## ProductionSNPCallerPluginV2 - RUN PRODUCTION PIPELINE - output .vcf
 
## ProductionSNPCallerPluginV2 - RUN PRODUCTION PIPELINE - output .vcf
 
$tasselPath -Xms64G -Xmx64G -fork1 -ProductionSNPCallerPluginV2 \
 
$tasselPath -Xms64G -Xmx64G -fork1 -ProductionSNPCallerPluginV2 \
     -db name.db \
+
     -db ${name}.db \
 
     -i $seqDir \
 
     -i $seqDir \
 
     -k $keyFile \
 
     -k $keyFile \
     -o name.vcf \
+
     -o ${name}.vcf \
 
     -e PstI-MspI -kmerLength 64 \
 
     -e PstI-MspI -kmerLength 64 \
     -endPlugin -runfork1 >> z_name_ProductionSNPCaller.out
+
     -endPlugin -runfork1 >> z_pipeline.out
  
 
## Convert to Hapmap format
 
## Convert to Hapmap format
$tasselPath -Xms64G -Xmx64G -fork1 -vcf name.vcf \
+
$tasselPath -Xms64G -Xmx64G -fork1 -vcf ${name}.vcf \
-export name -exportType Hapmap
+
    -export ${name} -exportType Hapmap
</syntaxhighlight>
+
  
 +
mv /homes/$user/gbs/jobs/${name}.* keyFileSh/
 +
</syntaxhighlight>
  
''Copy keyfile and .sh file for backup''
 
<pre>
 
mv /homes/$user/gbs/jobs/name.* keyFileSh/
 
</pre>
 
  
 +
If everything ran correctly, you should get a folder named '''projectName''' in your <code>gbs/projects</code> folder with all the output files including SNPs containing '''projectName.vcf''' and '''projectName.hmp.txt''' files that can be used for further analyses
  
''If everything ran correctly, you should get a folder named 'hessian_F3' in your gbs/projects folder with all the output files including SNP containing '''.vcf''' and '''.hmp.txt''' that can be used for further analyses''
 
  
==== End ====
+
If you have any question or it doesn't work, please contact me [mailto:nss470@ksu.edu?Subject=TASSEL5%20GBS%20v2%20pipeline%20question here].

Latest revision as of 20:01, 14 March 2018

For this script to work properly, you should have gbs folder in your home directory, and jobs and projects folders inside gbs

  • Once you have the full script copied in a simple text file with extension .sh, the name variable should be replaced with something more explicit, such as your project name.
  • Keyfile should have these 4 mandatory headers: 'Flowcell' 'Lane' 'Barcode' 'FullSampleName'

To keep everything organized, I recommend using the same base name for the project and the files, for example

name = projectName

Keyfile name = projectName.txt

Shell script name = projectName.sh

  • Once the Keyfile and shell script are ready, put them in jobs folder and run sbatch projectName.sh


#!/bin/bash -l
 
# Update beocat resources request
#SBATCH --mem-per-cpu=64G   # Memory per core, use --mem= for memory per node
#SBATCH --time=02-00:00:00   # Use the form DD-HH:MM:SS
#SBATCH --mail-user=eID@ksu.edu --mail-type=ALL   # same as =BEGIN,FAIL,END
#SBATCH --job-name=projectName
 
# Update the 'user' and 'name' variables, 'eID' is your K-State eID.
user=eID
name=projectName
 
## #######################################
## NO NEED TO CHANGE ANYTHING FROM HERE ON
## #######################################
 
# Load Java module and set JAVA VM Version to 1.8 (if default is different)
module load Java
 
keyFile=/homes/$user/gbs/jobs/${name}.txt
 
seqDir=/bulk/jpoland/sequence
dbPath=/bulk/nss470/genomes/CS_NRGene/pseudomolecules_v1.0/161010_Chinese_Spring_v1.0_pseudomolecules_parts
tasselPath=/homes/nss470/softwares/tassel5/run_pipeline.pl
 
mkdir /homes/$user/gbs/projects/${name}
mkdir /homes/$user/gbs/projects/${name}/keyFileSh
cd /homes/$user/gbs/projects/${name}
 
# Path for required software
export PATH=$PATH:/homes/nss470/usr/bin:/homes/nss470/usr/bin/bin
 
## GBSSeqToTagDBPlugin - RUN Tags to DB
$tasselPath -Xms64G -Xmx64G -fork1 -GBSSeqToTagDBPlugin -e PstI-MspI \
    -i $seqDir \
    -db ${name}.db \
    -k $keyFile \
    -kmerLength 64 -minKmerL 20 -mnQS 20 -mxKmerNum 250000000 \
    -endPlugin -runfork1 >> z_pipeline.out
 
## TagExportToFastqPlugin - export Tags
$tasselPath -fork1 -TagExportToFastqPlugin \
    -db ${name}.db \
    -o ${name}_tagsForAlign.fa.gz -c 10 \
    -endPlugin -runfork1 >> z_pipeline.out
 
## RUN BOWTIE
bowtie2 -p 20 --end-to-end \
    -x $dbPath \
    -U ${name}_tagsForAlign.fa.gz \
    -S ${name}.sam >> z_pipeline.out
 
## SAMToGBSdbPlugin - SAM to DB
$tasselPath -Xms64G -Xmx64G -fork1 -SAMToGBSdbPlugin \
    -i ${name}.sam \
    -db ${name}.db \
    -aProp 0.0 -aLen 0 \
    -endPlugin -runfork1 >> z_pipeline.out
 
## DiscoverySNPCallerPluginV2 - RUN DISCOVERY SNP CALLER
$tasselPath -Xms64G -Xmx64G -fork1 -DiscoverySNPCallerPluginV2 \
    -db ${name}.db \
    -mnLCov 0.1 -mnMAF 0.01 -deleteOldData true \
    -endPlugin -runfork1 >> z_pipeline.out
 
## SNPQualityProfilerPlugin - RUN QUALITY PROFILER
$tasselPath -Xms64G -Xmx64G -fork1 -SNPQualityProfilerPlugin \
    -db ${name}.db \
    -statFile ${name}_SNPqual_stats.txt \
    -endPlugin -runfork1 >> z_pipeline.out
 
## UpdateSNPPositionQualityPlugin - UPDATE DATABASE WITH QUALITY SCORE
$tasselPath -Xms64G -Xmx64G -fork1 -UpdateSNPPositionQualityPlugin \
    -db ${name}.db \
    -qsFile ${name}_SNPqual_stats.txt \
    -endPlugin -runfork1 >> z_pipeline.out
 
## ProductionSNPCallerPluginV2 - RUN PRODUCTION PIPELINE - output .vcf
$tasselPath -Xms64G -Xmx64G -fork1 -ProductionSNPCallerPluginV2 \
    -db ${name}.db \
    -i $seqDir \
    -k $keyFile \
    -o ${name}.vcf \
    -e PstI-MspI -kmerLength 64 \
    -endPlugin -runfork1 >> z_pipeline.out
 
## Convert to Hapmap format
$tasselPath -Xms64G -Xmx64G -fork1 -vcf ${name}.vcf \
    -export ${name} -exportType Hapmap
 
mv /homes/$user/gbs/jobs/${name}.* keyFileSh/


If everything ran correctly, you should get a folder named projectName in your gbs/projects folder with all the output files including SNPs containing projectName.vcf and projectName.hmp.txt files that can be used for further analyses


If you have any question or it doesn't work, please contact me here.