Changes between Version 58 and Version 59 of SnpCallingPipeline

Timestamp:

Dec 16, 2010 3:51:22 PM (14 years ago)

Author:

Leon Mei

Comment:

--

SnpCallingPipeline

@@ -8 +8 @@
  * Workflow 3: SnpCallingPipeline/VariantCalling
 
+''To install and test this pipeline, you could follow this instruction:''''' '''[wiki:SNPPipelineTestManual]
+
 == Schematic Overview ==
 This simplified overview this schema hides intermediate sort and indexing steps and only shows data inputs/outputs first time they occur.
@@ -15 +17 @@
 digraph g {
 
-  size="10,10" node [shape=box,style=filled,color=white] "dbsnp" "reference.fasta" "realign.intervals" "indelcalls.vcf" "chr[1-24]  .fasta" "flowcell_lane.1.fq.gz" "flowcell_lane.2.fq.gz" "flowcell_lane.aligned.bam" "flowcell_lane2.aligned.bam" "flowcell_lane3.aligned.bam" "sample.aligned.bam" "sample QC reports" "sample_chr[1-24]  .vcf"
+  size="10,10" node [shape=box,style=filled,color=white] "dbsnp" "reference.fasta" "realign.intervals" "indelcalls.vcf" "chr[1-24]   .fasta" "flowcell_lane.1.fq.gz" "flowcell_lane.2.fq.gz" "flowcell_lane.aligned.bam" "flowcell_lane2.aligned.bam" "flowcell_lane3.aligned.bam" "sample.aligned.bam" "sample QC reports" "sample_chr[1-24]   .vcf"
 
   node [shape=ellipse,color=yellow]
@@ -22 +24 @@
     style=filled; color=lightgrey;
 
-  "reference.fasta" -> RealignerTargetCreator   -> "realign.intervals" "indelcalls.vcf"-> RealignerTargetCreator    "reference.fasta"->Split->"chr[1-24]  .fasta"  dbsnp -> RealignerTargetCreator    label = "Per genome (1)";
+  "reference.fasta" -> RealignerTargetCreator    -> "realign.intervals" "indelcalls.vcf"-> RealignerTargetCreator     "reference.fasta"->Split->"chr[1-24]   .fasta"  dbsnp -> RealignerTargetCreator     label = "Per genome (1)";
 
 }
 
   subgraph cluster_1 {
-    style=filled; color=lightgrey; "flowcell_lane.1.fq.gz" -> align1 -> alignPE "chr[1-24]  .fasta" -> align1 "chr[1-24]  .fasta" -> align2 "chr[1-24]  .fasta" -> alignPE "flowcell_lane.2.fq.gz" -> align2 -> alignPE -> MarkDuplicates   -> "IndelRealigner   & \n FixMateInformation   (knownsOnly)" ->"Quality Recalibration"->"flowcell_lane.aligned.bam" "realign.intervals" -> "IndelRealigner   & \n FixMateInformation   (knownsOnly)"    label = "Per Lane (750*3=2250) ";
+    style=filled; color=lightgrey; "flowcell_lane.1.fq.gz" -> align1 -> alignPE "chr[1-24]   .fasta" -> align1 "chr[1-24]   .fasta" -> align2 "chr[1-24]   .fasta" -> alignPE "flowcell_lane.2.fq.gz" -> align2 -> alignPE -> MarkDuplicates    -> "IndelRealigner    & \n FixMateInformation    (knownsOnly)" ->"Quality Recalibration"->"flowcell_lane.aligned.bam" "realign.intervals" -> "IndelRealigner    & \n FixMateInformation    (knownsOnly)"    label = "Per Lane (750*3=2250) ";
   }
 
   subgraph cluster_2 {
-    style=filled; color=lightgrey; "flowcell_lane.aligned.bam" -> Merge -> "sample.aligned.bam" -> "IndelRealigner   & FixMateInformation  " "flowcell_lane2.aligned.bam" -> Merge "flowcell_lane3.aligned.bam" -> Merge "IndelRealigner   & FixMateInformation  " -> IndelGenotyperV2 -> FilterSingleCalls   -> UnifiedGenotyper   -> Filtration -> VariantEval   -> "sample QC reports"
+    style=filled; color=lightgrey; "flowcell_lane.aligned.bam" -> Merge -> "sample.aligned.bam" -> "IndelRealigner    & FixMateInformation   " "flowcell_lane2.aligned.bam" -> Merge "flowcell_lane3.aligned.bam" -> Merge "IndelRealigner    & FixMateInformation   " -> IndelGenotyperV2 -> FilterSingleCalls    -> UnifiedGenotyper    -> Filtration -> VariantEval    -> "sample QC reports"
 
 Filtration -> "sample_chr[1-24].vcf"
@@ -42 +44 @@
     style=filled; color=lightgrey;
 
-  "sample.aligned.bam" -> "UnifiedGenotype   (without realign)"->"QC against arrays and BGI"
+  "sample.aligned.bam" -> "UnifiedGenotype    (without realign)"->"QC against arrays and BGI"
 
   label = "QC per sample";
@@ -87 +89 @@
 == Optimization? ==
 ==== Current ====
-Step    Cores    Memory (gb)    Time (hh.mm)[[BR]]BWA alignment    1    ± 6    10.05[[BR]]BWA spe    1        3.35[[BR]]Sam-Bam    1        12.3[[BR]]Sam sort    1        5.05[[BR]]Mark Duplicates    1    4    1.55[[BR]]Realignment (knowns only)    1    8 (*can be lowered)    5.2[[BR]]Fix mates    1    6 (*)    3.05[[BR]]Covariates bef.    1    2    12.35[[BR]]Recalibrate    1    4    7.3[[BR]]Sam sort    1        4.5[[BR]]Covariates aft.    1    2    11.2[[BR]]Analyze Covar.    1    4    < 00.01
+Step    Cores    Memory (gb)    Time (hh.mm)[[BR]]BWA alignment    1    ± 6    10.05[[BR]]BWA spe    1        3.35[[BR]]Sam-Bam    1        12.3[[BR]]Sam sort    1        5.05[[BR]]Mark Duplicates    1    4    1.55[[BR]]Realignment (knowns only)    1    8 (*can be lowered)    5.2[[BR]]Fix mates    1    6 (*)    3.05[[BR]]Covariates bef.    1    2    12.35[[BR]]Recalibrate    1    4    7.3[[BR]]Sam sort    1        4.5[[BR]]Covariates aft.    1    2    11.2[[BR]]Analyze Covar.    1    4    < 00.01
 
 ==== Disk ====