Dockerized STAR Align

From Array Suite Wiki

Revision as of 08:15, 21 April 2020 by Joseph (Talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

In this example, a large set of resource files is specified, but referred to with %ResourceFolder% in the command. Note that this example uses a Dockerized version of STAR from a public repository, indicating the flexibility of this Docker implementation.

Dockerized STAR Alignment

Begin Macro;
@NSLOTS@ 8;
@readlength@ 100;
@UseCloud@ True;
End;
Begin RunEScript /RunOnServer=True;
Resources
"/CloudFolderSupport/Users/joe.pearson/STARIndex/SAindex"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/chrLength.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/chrName.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/chrNameLength.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/chrStart.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/exonGeTrInfo.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/exonInfo.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/geneInfo.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/Genome"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/genomeParameters.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/sjdbInfo.txt"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/sjdbList.fromGTF.out.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/sjdbList.out.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/transcriptInfo.tab"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/Genome"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/SA"
"/CloudFolderSupport/Users/joe.pearson/STARIndex/transcriptInfo.tab";
Files
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521461_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521461_2.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521462_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521462_2.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521463_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521463_2.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521522_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521522_2.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521523_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521523_2.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521524_1.fastq.gz"
"/CloudFolderSupport/TestDatasets/HumanRNASeqPaired/Tutorial2013_5p/SRR521524_2.fastq.gz";
EScriptName StarTest;
Command STAR --runMode alignReads --runThreadN @NSLOTS@ --genomeDir "%ResourceFolder%" --readFilesIn %FilePath1% %FilePath2% --outSAMattrRGline "ID:%PairName%" --outSAMtype BAM SortedByCoordinate --outSAMattributes RG NM NH --outSAMunmapped Within --outSAMorder Paired --outFilterMultimapNmax 10 --outFilterType Normal --outFilterIntronMotifs None --outFileNamePrefix "%OutputFolder%/%PairName%" --readNameSeparator "." --readFilesCommand zcat;
Options /ParallelJobNumber=6 /ThreadNumberPerJob=8 /Mode=Paired /ErrorOnStdErr=False /ErrorOnMissingOutput=True /RunOnDocker=True /ImageName="quay.io/biocontainers/star:2.7.3a--0" /UseCloud=@UseCloud@ /OutputFolder="/CloudFolderSupport/Users/joe.pearson/STARAlign" /InstanceType=m4.2xlarge /VolumeRatio=4;
End;