| | 1 | = Script templates = |
| | 2 | |
| | 3 | == Implemented components based on the Groningen pipeline == |
| | 4 | |
| | 5 | Template (grid component) |
| | 6 | |
| | 7 | === Alignment, realignment, recalibration, stats === |
| | 8 | * pe0--fastqc.ftl (FastqToFastQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/quality/Workflow/FastqToFastQC.gwendia) |
| | 9 | * pe00-bwa-align-pair1.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) |
| | 10 | * pe01-bwa-align-pair2.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) |
| | 11 | * pe02-bwa-sampe.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) |
| | 12 | * pe03-sam-to-bam.ftl (!BwaIllumina, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/BwaIllumina.gwendia) |
| | 13 | * pe04a-!HsMetrics.ftl (!CalculateHsMetrics, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/CalculateHsMetrics.gwendia) |
| | 14 | * pe04b-picardQC.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) |
| | 15 | * pe04-sam-sort.ftl (!SamSort, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/SamSort.gwendia) |
| | 16 | * pe05-mark-duplicates.ftl (!MarkDuplicates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/MarkDuplicates.gwendia) |
| | 17 | * pe06-realign.ftl (!ReAlign, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/ReAlign.gwendia) |
| | 18 | * pe07-fixmates.ftl (!FixMates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/FixMates.gwendia) |
| | 19 | * pe08-covariates-before.ftl (!GatkCovariates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkCovariates.gwendia) |
| | 20 | * pe09-recalibrate.ftl (!GatkRecalibrate, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkRecalibrate.gwendia) |
| | 21 | * pe10-sam-sort.ftl (!SamSort, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/SamSort.gwendia) |
| | 22 | * pe11-covariates-after.ftl (!GatkCovariates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkCovariates.gwendia) |
| | 23 | * pe12-analyze-covariates.ftl (!GatkAnalyzeCovariates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/GatkAnalyzeCovariates.gwendia) |
| | 24 | |
| | 25 | === Merge bam per sample and perform SNP and indel calling === |
| | 26 | * vc00a-unified-genotyper.ftl '''to do''' |
| | 27 | * vc00b-variant-filtration.ftl '''to do''' |
| | 28 | * vc00c-variant-eval.ftl '''to do''' |
| | 29 | * vc00d-picardMetrics.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) |
| | 30 | * vc00-merge.ftl '''to do''' |
| | 31 | * vc00.merge.ftl '''to do''' |
| | 32 | * vc01-coverage.ftl '''to do''' |
| | 33 | * vc01.unified_genotyper.ftl '''to do''' |
| | 34 | * vc02.picardQC.ftl (PicardQC, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/PicardQC.gwendia) |
| | 35 | * vc02-realigner-target-creator.ftl '''to do''' |
| | 36 | * vc03.coverage.ftl '''to do''' |
| | 37 | * vc03-realign.ftl (!ReAlign, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/ReAlign.gwendia) |
| | 38 | * vc04-fixmates.ftl (!FixMates, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/FixMates.gwendia) |
| | 39 | * vc05-indel-genotyper-v2.ftl '''to do''' |
| | 40 | * vc06-filter-indels.ftl '''to do''' |
| | 41 | * vc07-unified-genotyper.ftl '''to do''' |
| | 42 | * vc08-make-indel-mask.ftl '''to do''' |
| | 43 | * vc09-variant-filtration.ftl '''to do''' |
| | 44 | * vc10-variant-eval.ftl '''to do''' |
| | 45 | * vc11-name-sort-bam.ftl (!SamSort, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/gvnl/Workflows/SamSort.gwendia) |
| | 46 | * Pindel (Pindel, lfn://lfc.grid.sara.nl:5010/grid/vlemed/AMC-e-BioScience/Sequence_WF/pindel/Workflows/Pindel.gwendia) |
| | 47 | |
| | 48 | |
| | 49 | == Other workflow components == |
| | 50 | |
| | 51 | This list of other workflow components are available |
| | 52 | |
| | 53 | * Splitting of fastq files |
| | 54 | * Building a BWA index on the genome sequence (base space and color space) |
| | 55 | * BWA for shotgun reads (base space and color space) It is possible to do parameter sweeps. Output is in bam format |
| | 56 | * Merge bam results |
| | 57 | * Samtools pileup |
| | 58 | * Varscan (pileup to snp, indel and cns) |
| | 59 | * Bam2coverage creates a UCSC wiggle file to display the genome coverage (per 50kbp) |
| | 60 | * Coverage-per-base determines the coverage for every base in the genome and it summarizes the results (coverage versus frequency) |
| | 61 | * Annovar (works for hg18, working on other assemblies). This is a pipeline to annotate variants (gene, dbsnp, hapmap, 1000g, conservation, etc) |
| | 62 | * FastqC |
