add flu outputs to gather scatter

theiagen · Oct 28, 2024 · 48a26a2 · 48a26a2
1 parent b0498ae
commit 48a26a2
Show file tree

Hide file tree

Showing 3 changed files with 47 additions and 17 deletions.
diff --git a/tasks/utilities/data_handling/task_gather_scatter.wdl b/tasks/utilities/data_handling/task_gather_scatter.wdl
@@ -59,7 +59,23 @@ task gather_scatter {
     File? nextclade_aa_dels_flu_na
     File? nextclade_clade_flu_na
     File? nextclade_qc_flu_na
+    # IRMA outputs
+    File? irma_version
+    File? irma_docker
+    File? irma_type
+    File? irma_subtype
+    File? irma_subtype_notes
+    # GenoFLU outputs
+    File? genoflu_version
+    File? genoflu_genotype
+    File? genoflu_all_segments
+    # abricate outputs
+    File? abricate_flu_type
+    File? abricate_flu_subtype
+    File? abricate_flu_database
+    File? abricate_flu_version
 
+    # runtime parameters
     String docker = "us-docker.pkg.dev/general-theiagen/theiagen/terra-tools:2023-03-16"
     Int disk_size = 50
     Int cpu = 2
@@ -83,6 +99,8 @@ task gather_scatter {
         return None
 
     df = pd.DataFrame()
+    
+    # organism-agnostic columns
     df = load_json_data("~{taxon_ids}", "taxon_ids", df)
     df = load_json_data("~{organism}", "organism", df)
     df = load_json_data("~{extracted_read1}", "extracted_read1", df)
@@ -105,6 +123,8 @@ task gather_scatter {
     df = load_json_data("~{number_Degenerate}", "number_Degenerate", df)
     df = load_json_data("~{number_Total}", "number_Total", df)
     df = load_json_data("~{percent_reference_coverage}", "percent_reference_coverage", df)
+    
+    # organism-specific columns
     df = load_json_data("~{pango_lineage}", "pango_lineage", df)
     df = load_json_data("~{pango_lineage_expanded}", "pango_lineage_expanded", df)
     df = load_json_data("~{pangolin_conflicts}", "pangolin_conflicts", df)
@@ -130,6 +150,20 @@ task gather_scatter {
     df = load_json_data("~{nextclade_aa_dels_flu_na}", "nextclade_aa_dels_flu_na", df)
     df = load_json_data("~{nextclade_clade_flu_na}", "nextclade_clade_flu_na", df)
     df = load_json_data("~{nextclade_qc_flu_na}", "nextclade_qc_flu_na", df)
+    df = load_json_data("~{irma_version}", "irma_version", df)
+    df = load_json_data("~{irma_docker}", "irma_docker", df)
+    df = load_json_data("~{irma_type}", "irma_type", df)
+    df = load_json_data("~{irma_subtype}", "irma_subtype", df)
+    df = load_json_data("~{irma_subtype_notes}", "irma_subtype_notes", df)
+    df = load_json_data("~{genoflu_version}", "genoflu_version", df)
+    df = load_json_data("~{genoflu_genotype}", "genoflu_genotype", df)
+    df = load_json_data("~{genoflu_all_segments}", "genoflu_all_segments", df)
+    df = load_json_data("~{abricate_flu_type}", "abricate_flu_type", df)
+    df = load_json_data("~{abricate_flu_subtype}", "abricate_flu_subtype", df)
+    df = load_json_data("~{abricate_flu_database}", "abricate_flu_database", df)
+    df = load_json_data("~{abricate_flu_version}", "abricate_flu_version", df)
+
+    # add samplename column
     df.insert(0, "samplename" , "~{samplename}")
     
     # print(df)

diff --git a/workflows/theiameta/wf_theiameta_panel_illumina_pe.wdl b/workflows/theiameta/wf_theiameta_panel_illumina_pe.wdl
@@ -164,7 +164,19 @@ workflow theiameta_panel_illumina_pe {
       nextclade_aa_subs_flu_na = write_json(morgana_magic.nextclade_aa_subs_flu_na),
       nextclade_aa_dels_flu_na = write_json(morgana_magic.nextclade_aa_dels_flu_na),
       nextclade_clade_flu_na = write_json(morgana_magic.nextclade_clade_flu_na),
-      nextclade_qc_flu_na = write_json(morgana_magic.nextclade_qc_flu_na)
+      nextclade_qc_flu_na = write_json(morgana_magic.nextclade_qc_flu_na),
+      irma_version = write_json(morgana_magic.irma_version),
+      irma_docker = write_json(morgana_magic.irma_docker),
+      irma_type = write_json(morgana_magic.irma_type),
+      irma_subtype = write_json(morgana_magic.irma_subtype),
+      irma_subtype_notes = write_json(morgana_magic.irma_subtype_notes),
+      genoflu_version = write_json(morgana_magic.genoflu_version),
+      genoflu_genotype = write_json(morgana_magic.genoflu_genotype),
+      genoflu_all_segments = write_json(morgana_magic.genoflu_all_segments),
+      abricate_flu_type = write_json(morgana_magic.abricate_flu_type),
+      abricate_flu_subtype = write_json(morgana_magic.abricate_flu_subtype),
+      abricate_flu_database = write_json(morgana_magic.abricate_flu_database),
+      abricate_flu_version = write_json(morgana_magic.abricate_flu_version)
   } 
   output {
     # versioning outputs

diff --git a/workflows/utilities/wf_morgana_magic.wdl b/workflows/utilities/wf_morgana_magic.wdl
@@ -148,15 +148,6 @@ workflow morgana_magic {
         memory = nextclade_output_parser_memory
     }
   }
-  ##### is running quasitools even something we want to do????
-  if (organism_parameters.standardized_organism == "HIV") {
-    call quasitools.quasitools as quasitools_illumina_pe {
-      input:
-        read1 = read1,
-        read2 = read2,
-        samplename = samplename
-    }
-  }
   output {
     String organism = organism_parameters.standardized_organism
     # Consensus QC outputs
@@ -222,12 +213,5 @@ workflow morgana_magic {
     File? abricate_flu_results = flu_track.abricate_flu_results
     String? abricate_flu_database =  flu_track.abricate_flu_database
     String? abricate_flu_version = flu_track.abricate_flu_version
-    # HIV Outputs
-    String? quasitools_version = quasitools_illumina_pe.quasitools_version
-    String? quasitools_date = quasitools_illumina_pe.quasitools_date
-    File? quasitools_coverage_file = quasitools_illumina_pe.coverage_file
-    File? quasitools_dr_report = quasitools_illumina_pe.dr_report
-    File? quasitools_hydra_vcf = quasitools_illumina_pe.hydra_vcf
-    File? quasitools_mutations_report = quasitools_illumina_pe.mutations_report
   }
 }