= Script templates = == Implemented components based on the Groningen pipeline == Template (grid component) === Alignment, realignment, recalibration, stats === * pe0--fastqc.ftl (FastqToFastQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/quality/Workflow/FastqToFastQC.gwendia) * pe00-bwa-align-pair1.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) * pe01-bwa-align-pair2.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) * pe02-bwa-sampe.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) * pe03-sam-to-bam.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) * pe04a-!HsMetrics.ftl (!CalculateHsMetrics, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/CalculateHsMetrics.gwendia) * pe04b-picardQC.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) * pe04-sam-sort.ftl (!SamSort, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/SamSort.gwendia) * pe05-mark-duplicates.ftl (!MarkDuplicates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/MarkDuplicates.gwendia) * pe06-realign.ftl (!ReAlign, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/ReAlign.gwendia) * pe07-fixmates.ftl (!FixMates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/FixMates.gwendia) * pe08-covariates-before.ftl (!GatkRecalibrateAllSteps, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrateAllSteps.gwendia) * pe09-recalibrate.ftl (!GatkRecalibrateAllSteps, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrateAllSteps.gwendia) * pe10-sam-sort.ftl (!GatkRecalibrateAllSteps, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrateAllSteps.gwendia) * pe11-covariates-after.ftl (!GatkRecalibrateAllSteps, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrateAllSteps.gwendia) * pe12-analyze-covariates.ftl (!GatkRecalibrateAllSteps, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrateAllSteps.gwendia) === Merge bam per sample and perform SNP and indel calling === * vc00a-unified-genotyper.ftl '''to do''' * vc00b-variant-filtration.ftl '''to do''' * vc00c-variant-eval.ftl '''to do''' * vc00d-picardMetrics.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) * vc00-merge.ftl '''to do''' * vc00.merge.ftl '''to do''' * vc01-coverage.ftl '''to do''' * vc01.unified_genotyper.ftl '''to do''' * vc02.picardQC.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) * vc02-realigner-target-creator.ftl '''to do''' * vc03.coverage.ftl '''to do''' * vc03-realign.ftl (!ReAlign, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/ReAlign.gwendia) * vc04-fixmates.ftl (!FixMates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/FixMates.gwendia) * vc05-indel-genotyper-v2.ftl '''to do''' * vc06-filter-indels.ftl '''to do''' * vc07-unified-genotyper.ftl '''to do''' * vc08-make-indel-mask.ftl '''to do''' * vc09-variant-filtration.ftl '''to do''' * vc10-variant-eval.ftl '''to do''' * vc11-name-sort-bam.ftl (!SamSort, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/SamSort.gwendia) * Pindel (Pindel, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/pindel/Workflows/Pindel.gwendia) == Other workflow components == This list of other workflow components are available * Splitting of fastq files * Building a BWA index on the genome sequence (base space and color space) * BWA for shotgun reads (base space and color space) It is possible to do parameter sweeps. Output is in bam format * Merge bam results * Samtools pileup * Varscan (pileup to snp, indel and cns) * Bam2coverage creates a UCSC wiggle file to display the genome coverage (per 50kbp) * Coverage-per-base determines the coverage for every base in the genome and it summarizes the results (coverage versus frequency) * Annovar (works for hg18, working on other assemblies). This is a pipeline to annotate variants (gene, dbsnp, hapmap, 1000g, conservation, etc) * FastqC