From 53346745c2efb18c14ff8fa72237a70ee90a88b1 Mon Sep 17 00:00:00 2001
From: Miller <millerd15@email.chop.edu>
Date: Tue, 2 Jun 2020 16:09:37 -0400
Subject: [PATCH] :dollar: added runtime estimates

:wrench: explicit secondaryFile for cwltool

:wrench: remove double alt
---
 README.md                                              |  3 +++
 tools/bwa_index.cwl                                    |  2 +-
 tools/gatk_indexfeaturefile.cwl                        |  2 +-
 workflow/kfdrc_jointgenotyping_refinement_workflow.cwl | 10 +++++-----
 workflow/kfdrc_single_sample_genotyping_workflow.cwl   | 10 +++++-----
 5 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/README.md b/README.md
index 943edec..680fde4 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,9 @@ Kids First Data Resource Center Joint Genotyping Workflow (cram-to-deNovoGVCF).
 
 Using existing gVCFs, likely from GATK Haplotype Caller, we follow this workflow: [Germline short variant discovery (SNPs + Indels)](https://software.broadinstitute.org/gatk/best-practices/workflow?id=11145), to create family joint calling and joint trios (typically mother-father-child) variant calls. Peddy is run to raise any potential issues in family relation definitions and sex assignment.
 
+### Runtime Estimates
+- Single 5 GB gVCF Input: 90 Minutes & $2.25
+- Trio of 6 GB gVCFs Input: 240 Minutes & $3.25 
 
 ### Tips To Run:
 
diff --git a/tools/bwa_index.cwl b/tools/bwa_index.cwl
index c611502..47e6e3c 100644
--- a/tools/bwa_index.cwl
+++ b/tools/bwa_index.cwl
@@ -10,7 +10,7 @@ requirements:
   - class: ShellCommandRequirement
   - class: ResourceRequirement
   - class: InitialWorkDirRequirement
-    listing: [$(inputs.input_alt),$(inputs.input_alt),$(inputs.input_amb),$(inputs.input_ann),$(inputs.input_bwt),$(inputs.input_pac),$(inputs.input_sa)]
+    listing: [$(inputs.input_alt),$(inputs.input_amb),$(inputs.input_ann),$(inputs.input_bwt),$(inputs.input_pac),$(inputs.input_sa)]
   - class: DockerRequirement
     dockerPull: 'kfdrc/bwa:0.7.17-dev'
   - class: InlineJavascriptRequirement
diff --git a/tools/gatk_indexfeaturefile.cwl b/tools/gatk_indexfeaturefile.cwl
index c652c5a..ea8d2c3 100644
--- a/tools/gatk_indexfeaturefile.cwl
+++ b/tools/gatk_indexfeaturefile.cwl
@@ -35,4 +35,4 @@ outputs:
     type: File
     outputBinding:
       glob: $(inputs.input_file.basename)
-    secondaryFiles: ${if (inputs.input_file.nameext == '.vcf') {return inputs.input_file.basename+'.idx'} else if (inputs.input_file.nameext == '.gz') {return inputs.input_file.basename+'.tbi'}}
+    secondaryFiles: [.idx] 
diff --git a/workflow/kfdrc_jointgenotyping_refinement_workflow.cwl b/workflow/kfdrc_jointgenotyping_refinement_workflow.cwl
index e343f4e..a99bf48 100644
--- a/workflow/kfdrc_jointgenotyping_refinement_workflow.cwl
+++ b/workflow/kfdrc_jointgenotyping_refinement_workflow.cwl
@@ -79,7 +79,7 @@ steps:
       input_dict: reference_dict
     out: [indexed_fasta,reference_dict]
   index_axiomPoly:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: axiomPoly_resource_vcf
       input_index: axiomPoly_resource_tbi
@@ -91,25 +91,25 @@ steps:
       input_index: dbsnp_idx
     out: [output]
   index_hapmap:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: hapmap_resource_vcf
       input_index: hapmap_resource_tbi
     out: [output]
   index_mills:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: mills_resource_vcf
       input_index: mills_resource_tbi
     out: [output]
   index_omni:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: omni_resource_vcf
       input_index: omni_resource_tbi
     out: [output]
   index_1k:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: one_thousand_genomes_resource_vcf
       input_index: one_thousand_genomes_resource_tbi
diff --git a/workflow/kfdrc_single_sample_genotyping_workflow.cwl b/workflow/kfdrc_single_sample_genotyping_workflow.cwl
index 17cefd1..fb5cdbb 100644
--- a/workflow/kfdrc_single_sample_genotyping_workflow.cwl
+++ b/workflow/kfdrc_single_sample_genotyping_workflow.cwl
@@ -72,7 +72,7 @@ steps:
       input_dict: reference_dict
     out: [indexed_fasta,reference_dict]
   index_axiomPoly:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: axiomPoly_resource_vcf
       input_index: axiomPoly_resource_tbi
@@ -84,25 +84,25 @@ steps:
       input_index: dbsnp_idx
     out: [output]
   index_hapmap:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: hapmap_resource_vcf
       input_index: hapmap_resource_tbi
     out: [output]
   index_mills:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: mills_resource_vcf
       input_index: mills_resource_tbi
     out: [output]
   index_omni:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: omni_resource_vcf
       input_index: omni_resource_tbi
     out: [output]
   index_1k:
-    run: ../tools/gatk_indexfeaturefile.cwl
+    run: ../tools/tabix_index.cwl
     in:
       input_file: one_thousand_genomes_resource_vcf
       input_index: one_thousand_genomes_resource_tbi