Merge pull request #112 from Cristianetaniguti/develop

Develop
Cristianetaniguti · Jan 8, 2024 · 000e48c · 000e48c
2 parents cf879bb + 0b4ffbe
commit 000e48c
Show file tree

Hide file tree

Showing 12 changed files with 312 additions and 122 deletions.
diff --git a/.dockerfiles/reads2map/Dockerfile b/.dockerfiles/reads2map/Dockerfile
@@ -60,4 +60,4 @@ RUN Rscript -e 'remotes::install_github("Cristianetaniguti/onemap")'
 # Still privates
 RUN Rscript -e 'remotes::install_github("Cristianetaniguti/simuscopR")'
 RUN Rscript -e 'remotes::install_github("Cristianetaniguti/Reads2MapTools")'
-RUN Rscript -e 'remotes::install_github("Cristianetaniguti/MAPpoly")'
+RUN Rscript -e 'remotes::install_github("Cristianetaniguti/MAPpoly" )'
diff --git a/pipelines/EmpiricalMaps/EmpiricalMaps.changelog.md b/pipelines/EmpiricalMaps/EmpiricalMaps.changelog.md
@@ -1,3 +1,9 @@
+# 1.3.1
+
+* Make EmpiricalMaps for polyploids compatible with Reads2MapApp v0.0.2
+* Polyploid map quality diagnostic by resampling
+* Adapt regenotyping memory usage
+
 # 1.3.0
 
 * Add MAPpoly new functions framework_map and update_framework_map
@@ -7,7 +13,7 @@
 
 # 1.2.5
 
-* more flexibility to choose the probability to be used in the HMM: 
+* more flexibility to choose the probability to be used in the HMM:
 
 * new parameters:
 - global_errors: array with global errors to be tested

diff --git a/pipelines/EmpiricalMaps/EmpiricalMaps.wdl b/pipelines/EmpiricalMaps/EmpiricalMaps.wdl
@@ -36,6 +36,8 @@ workflow Maps {
         Array[String] global_errors = ["0.05"]
         Boolean genoprob_error = true
         Array[String] genoprob_global_errors = ["0.05"]
+        Int? repetitions 
+        Int? sample_size 
     }
 
     if (defined(filters)) {
@@ -190,7 +192,9 @@ workflow Maps {
                         ploidy = ploidy,
                         prob_thres = prob_thres,
                         filt_segr = filt_segr,
-                        global_errors = global_errors
+                        global_errors = global_errors,
+                        repetitions = repetitions,
+                        sample_size = sample_size
                 }
             }
 
@@ -208,7 +212,9 @@ workflow Maps {
                         ploidy = ploidy,
                         prob_thres = prob_thres,
                         filt_segr = filt_segr,
-                        global_errors = global_errors
+                        global_errors = global_errors,
+                        repetitions = repetitions,
+                        sample_size = sample_size
                 }
             }
 
@@ -226,7 +232,9 @@ workflow Maps {
                         ploidy = ploidy,
                         prob_thres = prob_thres,
                         filt_segr = filt_segr,
-			global_errors = global_errors
+                        global_errors = global_errors,
+                        repetitions = repetitions,
+                        sample_size = sample_size
                 }
             }
 
@@ -243,7 +251,9 @@ workflow Maps {
                         ploidy = ploidy,
                         prob_thres = prob_thres,
                         filt_segr = filt_segr,
-                        global_errors = global_errors
+                        global_errors = global_errors,
+                        repetitions = repetitions,
+                        sample_size = sample_size
                 }
             }
         }

diff --git a/pipelines/EmpiricalReads2Map/EmpiricalReads2Map.changelog.md b/pipelines/EmpiricalReads2Map/EmpiricalReads2Map.changelog.md
@@ -1,3 +1,12 @@
+# 1.5.1
+
+* Make EmpiricalMaps for polyploids compatible with Reads2MapApp v0.0.2
+* Polyploid map quality diagnostic by resampling
+* Adapt regenotyping memory usage
+* Make BarcodeFaker task work for input files that do not finish with .fasta or .fq
+* Adapt BarcodeFaker required memory and time
+* Adapt STACKs required memory
+
 # 1.5.0
 
 * Adapt tassel and stacks tasks also for polyploids

diff --git a/pipelines/EmpiricalSNPCalling/EmpiricalSNPCalling.changelog.md b/pipelines/EmpiricalSNPCalling/EmpiricalSNPCalling.changelog.md
@@ -1,3 +1,9 @@
+# 1.4.4
+
+* Make BarcodeFaker task work for input files that do not finish with .fasta or .fq
+* Adapt BarcodeFaker required memory and time
+* Adapt STACKs required memory
+
 # 1.4.3
 
 * Adapt tassel and stacks tasks also for polyploids
@@ -32,7 +38,7 @@
 # 1.2.0
 
 * Run freebayes parallelizing in nodes according to chromosomes and cores splitting in genomic regions
-* Adjust runtimes 
+* Adjust runtimes
 * Add polyploid dataset for tests
 
 # 1.1.0

diff --git a/subworkflows/mappoly_maps_empirical.wdl b/subworkflows/mappoly_maps_empirical.wdl
@@ -1,10 +1,10 @@
 version 1.0
 
+
 import "../tasks/utilsR.wdl" as utilsR
 import "../tasks/mappoly.wdl" as mappolyTasks
 
 workflow MappolyMapsEmp {
-
   input {
     File vcf_file
     String SNPCall_program
@@ -14,6 +14,8 @@ workflow MappolyMapsEmp {
     String parent1
     String parent2
     Float? prob_thres
+    Int? repetitions 
+    Int? sample_size 
     Int max_cores
     Int ploidy
     String? filt_segr
@@ -45,11 +47,13 @@ workflow MappolyMapsEmp {
       ploidy = ploidy,
       prob_thres = prob_thres,
       filt_segr = filt_segr,
-      global_errors = global_errors
+      global_errors = global_errors,
+      repetitions = repetitions,
+      sample_size = sample_size
   }
 
    output {
       File tar_gz_report = MappolyReport.results
       File regeno_vcf = ReGenotyping.regeno_vcf
    }
-}
+}
diff --git a/tasks/freebayes.wdl b/tasks/freebayes.wdl
@@ -12,7 +12,7 @@ task RunFreebayes {
   }
 
   Int disk_size = ceil(size(reference, "GiB") + size(bam, "GiB") +  50)
-  Int memory_size = ceil(size(bam, "MiB") * 4 * max_cores + 10000)
+  Int memory_size = 350000
 
   command <<<