From bbbe8add55a41653154719d0596a5efb9050e1ea Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:50:44 -0600
Subject: [PATCH 01/14] update to 16.15.0

---
 modules/local/datasets.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/datasets.nf b/modules/local/datasets.nf
index f38f447..b1320ba 100644
--- a/modules/local/datasets.nf
+++ b/modules/local/datasets.nf
@@ -52,7 +52,7 @@ process datasets_download {
   // because there's no way to specify threads
   label         "process_medium"
   publishDir    path: "${params.outdir}", mode: 'copy', pattern: "logs/*/*log"
-  container     'staphb/ncbi-datasets:16.10.3'
+  container     'staphb/ncbi-datasets:16.15.0'
   time          '5h'
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
   

From 6ac636d2e61d943b1092a4e50fe15bc9fa677d0a Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:51:04 -0600
Subject: [PATCH 02/14] removed flag and fixed version

---
 modules/local/drprg.nf | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/modules/local/drprg.nf b/modules/local/drprg.nf
index c831d22..1762616 100644
--- a/modules/local/drprg.nf
+++ b/modules/local/drprg.nf
@@ -8,7 +8,7 @@ process drprg {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contigs), val(flag)
+  tuple val(meta), file(contigs)
 
   output:
   tuple val(meta), val("drprg"), file("drprg/*/*.drprg.json"), emit: json
@@ -17,7 +17,7 @@ process drprg {
   path "versions.yml", emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''
@@ -35,7 +35,7 @@ process drprg {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        drprg: \$( drprg --version )
+        drprg: \$( drprg --version | awk '{print \$NF}')
     END_VERSIONS
   """
 }
\ No newline at end of file

From a7e196dd9c550e537af4d71da4dde3f47b76575a Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:51:21 -0600
Subject: [PATCH 03/14] removed flag

---
 modules/local/elgato.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/elgato.nf b/modules/local/elgato.nf
index 3b65119..adb0c8e 100755
--- a/modules/local/elgato.nf
+++ b/modules/local/elgato.nf
@@ -7,7 +7,7 @@ process elgato {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contigs), val(flag)
+  tuple val(meta), file(contigs)
 
   output:
   path "elgato/*/possible_mlsts.txt", emit: collect
@@ -15,7 +15,7 @@ process elgato {
   path "versions.yml"               , emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''

From 5abf53a84ef26d6bd91c1f6da66d8f1ecab05b47 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:51:36 -0600
Subject: [PATCH 04/14] removed flag

---
 modules/local/emmtyper.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/emmtyper.nf b/modules/local/emmtyper.nf
index 61c6845..5af6307 100644
--- a/modules/local/emmtyper.nf
+++ b/modules/local/emmtyper.nf
@@ -8,10 +8,10 @@ process emmtyper {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
   
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   input:
-  tuple val(meta), file(contigs), val(flag), file(script)
+  tuple val(meta), file(contigs), file(script)
 
   output:
   path "emmtyper/*_emmtyper.txt"   , emit: collect

From 400284db8a6e89b6721e1501475e78ff45ef3143 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:51:51 -0600
Subject: [PATCH 05/14] update to 2.3.4

---
 modules/local/iqtree2.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/iqtree2.nf b/modules/local/iqtree2.nf
index 8ae7366..a839eb7 100644
--- a/modules/local/iqtree2.nf
+++ b/modules/local/iqtree2.nf
@@ -2,7 +2,7 @@ process iqtree2 {
   tag           "Phylogenetic analysis"
   label         "process_high"
   publishDir    params.outdir, mode: 'copy', saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-  container     'staphb/iqtree2:2.3.1'
+  container     'staphb/iqtree2:2.3.4'
   time          '24h'
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
   

From 68a8488340069d2daaeb4c9536bd40b81754d673 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:52:05 -0600
Subject: [PATCH 06/14] removed flag

---
 modules/local/kaptive.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/kaptive.nf b/modules/local/kaptive.nf
index ff274ac..8019606 100644
--- a/modules/local/kaptive.nf
+++ b/modules/local/kaptive.nf
@@ -8,7 +8,7 @@ process kaptive {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contigs), val(flag)
+  tuple val(meta), file(contigs)
 
   output:
   path "kaptive/${meta.id}_table.txt", emit: collect
@@ -17,7 +17,7 @@ process kaptive {
   path "versions.yml", emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''

From f731820e46369074d4ff14bed59c9c4433d19704 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:52:16 -0600
Subject: [PATCH 07/14] removed flag

---
 modules/local/kleborate.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/kleborate.nf b/modules/local/kleborate.nf
index 177cd0d..a8d84ad 100644
--- a/modules/local/kleborate.nf
+++ b/modules/local/kleborate.nf
@@ -7,7 +7,7 @@ process kleborate {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contig), val(flag), file(script)
+  tuple val(meta), file(contig), file(script)
 
   output:
   path "kleborate/*_results.tsv"   , emit: collect, optional: true
@@ -16,7 +16,7 @@ process kleborate {
   path "versions.yml"              , emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: '--all'

From 3c3ecdb7091320ffb7444e3976a9f8fe062f9c54 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:53:57 -0600
Subject: [PATCH 08/14] removed flag

---
 modules/local/local.nf | 106 +----------------------------------------
 1 file changed, 1 insertion(+), 105 deletions(-)

diff --git a/modules/local/local.nf b/modules/local/local.nf
index d2bd91f..53f1c93 100644
--- a/modules/local/local.nf
+++ b/modules/local/local.nf
@@ -65,110 +65,6 @@ process download_sra {
   """
 }
 
-process flag {
-  tag           "${meta.id}"
-  label         "process_single"
-  //no publishDir    params.outdir, mode: 'copy'
-  container     'quay.io/biocontainers/pandas:1.5.2'
-  time          '10m'
-  errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
-
-  input:
-  tuple val(meta), file(files)
-
-  output:
-  tuple val(meta), file("${files[0]}"), env(salmonella_flag)    , emit: salmonella_flag
-  tuple val(meta), file("${files[0]}"), env(klebsiella_flag)    , emit: klebsiella_flag
-  tuple val(meta), file("${files[0]}"), env(ecoli_flag)         , emit: ecoli_flag
-  tuple val(meta), file("${files[0]}"), env(streppneu_flag)     , emit: streppneu_flag
-  tuple val(meta), file("${files[0]}"), env(legionella_flag)    , emit: legionella_flag
-  tuple val(meta), file("${files[0]}"), env(klebacin_flag)      , emit: klebacin_flag
-  tuple val(meta), file("${files[0]}"), env(strepa_flag)        , emit: strepa_flag
-  tuple val(meta), file("${files[0]}"), env(vibrio_flag)        , emit: vibrio_flag
-  tuple val(meta), file("${files[0]}"), env(myco_flag)          , emit: myco_flag
-  tuple val(meta), file("${files[0]}"), env(genus), env(species), emit: organism
-  path "flag/*_flag.csv", emit: collect
-  path "logs/${task.process}/*.log", emit: log_files
-
-  shell:
-  def prefix = task.ext.prefix ?: "${meta.id}"
-  """
-    mkdir -p flag logs/${task.process}
-    log_file=logs/${task.process}/${prefix}.${workflow.sessionId}.log
-
-    if [ -f "${prefix}_fastani.csv" ]
-    then 
-      awk -F "," '{if (\$4 > 90) print \$0}' ${prefix}_fastani.csv > smaller_fastani.csv
-      genus=\$(head   -n 2 ${prefix}_fastani.csv | tail -n 1 | cut -f 3 -d , | cut -f 1 -d "_")
-      species=\$(head -n 2 ${prefix}_fastani.csv | tail -n 1 | cut -f 3 -d , | cut -f 2 -d "_")
-    else
-      touch smaller_fastani.csv
-      genus="unknown"
-      species="unknown"
-    fi
-
-    touch ${prefix}_reads_summary_kraken2.csv  ${prefix}.summary.mash.csv ${prefix}_blobtools.txt
-
-    files="smaller_fastani.csv ${prefix}_reads_summary_kraken2.csv ${prefix}.summary.mash.csv ${prefix}_blobtools.txt"
-
-    echo "Looking for Salmonella:" >> \$log_file
-    salmonella_flag=''
-    find_salmonella=\$(head -n 10 \$files | grep "Salmonella" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_salmonella" ] ; then salmonella_flag="found" ; else salmonella_flag="not" ; fi
-    
-    echo "Looking for E. coli and Shigella:" >> \$log_file
-    ecoli_flag=''
-    find_ecoli=\$(head -n 10 \$files | grep -e "Escherichia" -e "Shigella" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_ecoli" ] ; then ecoli_flag="found" ; else ecoli_flag="not" ; fi
-
-    echo "Looking for Klebsiella:" >> \$log_file
-    klebsiella_flag=''
-    find_klebsiella=\$(head -n 10 \$files | grep -e "Klebsiella" -e "Enterobacter" -e "Serratia" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_klebsiella" ] ; then klebsiella_flag="found" ; else klebsiella_flag="not" ; fi
-    
-    echo "Looking for Strep A organisms:" >> \$log_file
-    strepa_flag=''
-    find_strepa=\$(head -n 10 \$files | grep "Streptococcus" | grep -e "pyogenes" -e "dysgalactiae" -e "anginosus" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_strepa" ] ; then strepa_flag='found' ; else strepa_flag='not' ; fi
-
-    echo "Looking for Streptococcus pneumoniae organisms:" >> \$log_file
-    streppneu_flag_flag=''
-    find_streppneu=\$(head -n 10 \$files | grep "Streptococcus" | grep "pneumoniae" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_streppneu" ] ; then streppneu_flag='found' ; else streppneu_flag='not' ; fi
-  
-    echo "Looking for Legionella organisms:" >> \$log_file
-    legionella_flag=''
-    find_legionella=\$(head -n 10 \$files | grep "Legionella" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_legionella" ] ; then legionella_flag='found' ; else legionella_flag='not' ; fi
-
-    echo "Looking for Vibrio organisms:" >> \$log_file
-    vibrio_flag=''
-    find_vibrio=\$(head -n 10 \$files | grep "Vibrio" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_vibrio" ] ; then vibrio_flag='found' ; else vibrio_flag='not' ; fi
-
-    echo "Looking for Klebsiella or Acinetobacter:" >> \$log_file
-    klebacin_flag=''
-    if [ -n "\$find_klebsiella" ]
-    then
-      klebacin_flag='found'
-    else
-      find_acin=\$(head -n 10 \$files | grep "Acinetobacter" | tee -a \$log_file | head -n 1 )
-      if [ -n "\$find_acin" ] ; then klebacin_flag='found' ; else klebacin_flag='not' ; fi
-    fi
-
-    echo "Looking for Mycobacterium/Mycobacteria"
-    myco_flag=''
-    find_myco=\$(head -n 10 \$files | grep "Mycobacteri" | tee -a \$log_file | head -n 1 )
-    if [ -n "\$find_myco" ] ; then myco_flag='found' ; else myco_flag='not' ; fi
-
-    if [ -z "\$genus" ]   ; then genus=unknown   ; fi
-    if [ -z "\$species" ] ; then species=unknown ; fi
-
-    echo "sample,genus,species,salmonella_flag,ecoli_flag,klebsiella_flag,klebacin_flag,myco_flag,strepa_flag,streppneu_flag,legionella_flag,vibrio_flag" > flag/${prefix}_flag.csv
-    echo "${prefix},\$genus,\$species,\$salmonella_flag,\$ecoli_flag,\$klebsiella_flag,\$klebacin_flag,\$myco_flag,\$strepa_flag,\$streppneu_flag,\$legionella_flag,\$vibrio_flag" >> flag/${prefix}_flag.csv
-  """
-}
-
 process json_convert {
   tag       "${meta.id}"
   label     "process_single"
@@ -278,7 +174,7 @@ process references {
   tag       "Preparing references"
   // no publishDir
   label     "process_single"
-  container 'quay.io/uphl/grandeur_ref:2024-03-07'
+  container 'quay.io/uphl/grandeur_ref:2024-06-26'
   time      '10m'
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 

From ed4635b65208a1552e8904cc8f02ea8ac727d1de Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:54:20 -0600
Subject: [PATCH 09/14] added errorStrategy

---
 modules/local/bbduk.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/bbduk.nf b/modules/local/bbduk.nf
index 44fd3b7..3536873 100644
--- a/modules/local/bbduk.nf
+++ b/modules/local/bbduk.nf
@@ -3,7 +3,7 @@ process bbduk {
   label         "process_medium"
   publishDir    params.outdir, mode: 'copy', saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
   container     'staphb/bbtools:39.01'
-  //errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
+  errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
   time          '10m'
 
   input:

From b596fe0f07b2fb8ede157ff051cb8a61ccccf9f0 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:54:46 -0600
Subject: [PATCH 10/14] update to 2.23.0-2024-06-01

---
 modules/local/mlst.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/local/mlst.nf b/modules/local/mlst.nf
index 6710565..43b069b 100644
--- a/modules/local/mlst.nf
+++ b/modules/local/mlst.nf
@@ -2,7 +2,7 @@ process mlst {
   tag           "${meta.id}"
   label         "process_medium"
   publishDir    params.outdir, mode: 'copy', saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-  container     'staphb/mlst:2.23.0-2024-05-01'
+  container     'staphb/mlst:2.23.0-2024-06-01'
   maxForks      10
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
   time          '10m'

From d46878d03770504f66fabacea0bf32780a661911 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:55:00 -0600
Subject: [PATCH 11/14] added errorStrategy

---
 modules/local/mykrobe.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/local/mykrobe.nf b/modules/local/mykrobe.nf
index 5a4d757..e5ed3af 100644
--- a/modules/local/mykrobe.nf
+++ b/modules/local/mykrobe.nf
@@ -8,7 +8,7 @@ process mykrobe {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contigs), val(flag)
+  tuple val(meta), file(contigs)
 
   output:
   path "mykrobe/*.csv", emit: collect
@@ -17,7 +17,7 @@ process mykrobe {
   path "versions.yml", emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''

From 6f9084375c141cd083e7539fd6dda06a200c429a Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:55:32 -0600
Subject: [PATCH 12/14] removed flag

---
 modules/local/pbptyper.nf       | 4 ++--
 modules/local/seqsero2.nf       | 4 ++--
 modules/local/serotypefinder.nf | 4 ++--
 modules/local/shigatyper.nf     | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/modules/local/pbptyper.nf b/modules/local/pbptyper.nf
index 97e8aea..9cb85d5 100644
--- a/modules/local/pbptyper.nf
+++ b/modules/local/pbptyper.nf
@@ -8,7 +8,7 @@ process pbptyper {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(contigs), val(flag)
+  tuple val(meta), file(contigs)
 
   output:
   path "pbptyper/${meta.id}.tsv"   , emit: collect
@@ -17,7 +17,7 @@ process pbptyper {
   path "versions.yml"              , emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''
diff --git a/modules/local/seqsero2.nf b/modules/local/seqsero2.nf
index ce619de..41849e1 100644
--- a/modules/local/seqsero2.nf
+++ b/modules/local/seqsero2.nf
@@ -7,7 +7,7 @@ process seqsero2 {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}
 
   input:
-  tuple val(meta), file(file), val(flag)
+  tuple val(meta), file(file)
 
   output:
   path "seqsero2/*/*"                                    , emit: files
@@ -16,7 +16,7 @@ process seqsero2 {
   path  "versions.yml"                          , emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args = task.ext.args     ?: '-m a -b mem'
diff --git a/modules/local/serotypefinder.nf b/modules/local/serotypefinder.nf
index 1628b72..a4d6193 100644
--- a/modules/local/serotypefinder.nf
+++ b/modules/local/serotypefinder.nf
@@ -8,7 +8,7 @@ process serotypefinder {
   errorStrategy { task.attempt < 2 ? 'retry' : 'ignore'}  
 
   input:
-  tuple val(meta), file(file), val(flag), file(script)
+  tuple val(meta), file(file), file(script)
 
   output:
   path "serotypefinder/*/*"                 , emit: files
@@ -17,7 +17,7 @@ process serotypefinder {
   path "versions.yml"                       , emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args   = task.ext.args   ?: ''
diff --git a/modules/local/shigatyper.nf b/modules/local/shigatyper.nf
index d222509..46ed8d0 100644
--- a/modules/local/shigatyper.nf
+++ b/modules/local/shigatyper.nf
@@ -8,7 +8,7 @@ process shigatyper {
   time          '10m'
   
   input:
-  tuple val(meta), file(input), val(flag), file(script)
+  tuple val(meta), file(input), file(script)
 
   output:
   path "shigatyper/*_shigatyper.tsv", optional: true, emit: files
@@ -17,7 +17,7 @@ process shigatyper {
   path "versions.yml", emit: versions
 
   when:
-  (task.ext.when == null || task.ext.when) && flag =~ 'found'
+  (task.ext.when == null || task.ext.when)
 
   shell:
   def args = task.ext.args ?: ''

From f7c147e607a239a567d285dae4cae3599d51c856 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:56:10 -0600
Subject: [PATCH 13/14] version change to 4.5.240626

---
 nextflow.config | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nextflow.config b/nextflow.config
index 2fe1277..8669790 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -3,7 +3,7 @@ manifest {
   author                          = 'Erin Young'
   homePage                        = 'https://github.com/UPHL-BioNGS/Grandeur'
   mainScript                      = 'main.nf'
-  version                         = '4.4.240521'
+  version                         = '4.5.240626'
   defaultBranch                   = 'main'
   description                     = 'Grandeur is short-read de novo assembly pipeline with serotyping.'
   nextflowVersion                 = '!>=22.10.1'

From 1a343859ea9eb13852c63cdb053162d45d4c9b59 Mon Sep 17 00:00:00 2001
From: eriny <erin.olde@gmail.com>
Date: Wed, 26 Jun 2024 16:56:25 -0600
Subject: [PATCH 14/14] replaced flag process with functions

---
 subworkflows/information.nf | 229 ++++++++++++++++++++++++++++++------
 1 file changed, 194 insertions(+), 35 deletions(-)

diff --git a/subworkflows/information.nf b/subworkflows/information.nf
index b39ceee..a2d78d4 100644
--- a/subworkflows/information.nf
+++ b/subworkflows/information.nf
@@ -2,7 +2,6 @@ include { amrfinderplus }  from '../modules/local/amrfinderplus'  addParams(para
 include { drprg }          from '../modules/local/drprg'          addParams(params)
 include { elgato }         from '../modules/local/elgato'         addParams(params)
 include { emmtyper }       from '../modules/local/emmtyper'       addParams(params)
-include { flag }           from '../modules/local/local'          addParams(params)
 include { json_convert }   from '../modules/local/local'          addParams(params)
 include { kaptive }        from '../modules/local/kaptive'        addParams(params)
 include { kleborate }      from '../modules/local/kleborate'      addParams(params)
@@ -12,6 +11,101 @@ include { seqsero2 }       from '../modules/local/seqsero2'       addParams(para
 include { serotypefinder } from '../modules/local/serotypefinder' addParams(params)
 include { shigatyper }     from '../modules/local/shigatyper'     addParams(params)
 
+def flagOrg(org_files, phrases) {
+  def found = false
+  org_files.each { org_file ->
+    if (org_file && org_file.exists()) {
+      def count = 0
+      org_file.withReader { reader ->
+        while (reader.ready() && count < 10 && !found) {
+          def line = reader.readLine()
+          count++
+          phrases.each { phrase ->
+            if (line.toString().contains(phrase)) {
+              if (org_file.getName().contains('fastani')) {
+                def columns = line.split(',')
+                if (columns.size() >= 4 && columns[3].toFloat() > 90) {
+                  found = true
+                }
+              } else {
+                found = true
+              }
+            }     
+          }
+        }
+      }
+    }
+  }
+  return found
+}
+
+def topOrg(org_files) {
+  def fastani_file = org_files[0]
+  def blobtools_file = org_files[1]
+  def kraken2_file = org_files[2]
+  def mash_file = org_files[3]
+  
+  def genus   = 'unknown'
+  def species = 'unknown'
+
+  if (fastani_file && fastani_file.exists() && genus == 'unknown') {
+    def lines = fastani_file.readLines()
+    if (lines.size() > 1) {
+      def secondLine = lines[1].split(',')
+      if (secondLine.size() >= 4 && secondLine[3].toFloat() > 90) {
+        hit     = secondLine[2].trim()+ '_unknown'
+        genus   = hit.split('_')[0]
+        species = hit.split('_')[1]
+      }
+    }
+  } 
+  
+  if (blobtools_file && blobtools_file.exists() && genus == 'unknown') {
+    blobtools_file.withReader { reader -> 
+      while(reader.ready()) {
+        def line = reader.readLine()
+        def columns = line.split('\t')
+        if (columns.size() > 1) {
+          hit = columns[1].trim()
+          if (!['name', 'all', 'no-hit', 'undel'].contains(hit)) {
+            if (columns.size() == 14 && columns[-1].toFloat() > 50) {
+              name    = hit + '_unknown'
+              genus   = name.split('_')[0]
+              species = name.split('_')[1]
+              return
+            }
+          }
+        }
+      }
+    }
+  }
+  
+  if (kraken2_file && kraken2_file.exists() && genus == 'unknown') {
+    def lines = kraken2_file.readLines()
+    if (lines.size() > 1) {
+      def secondLine = lines[1].split(',')
+      if (secondLine.size() >= 2 && secondLine[1].toFloat() > 50) {
+        hit     = secondLine[-1].trim() + '_unknown'
+        genus   = hit.split('_')[0]
+        species = hit.split('_')[1]
+      }
+    }
+  } 
+  
+  if (mash_file && mash_file.exists() && genus == 'unknown') {
+    def lines = mash_file.readLines()
+    if (lines.size() > 1) {
+      def secondLine = lines[1].split(',')
+      if (secondLine.size() >= 4 && secondLine[3].toFloat() < 0.1) {
+        hit     = secondLine[-1].trim() + '_unknown'
+        genus   = hit.split('_')[0]
+        species = hit.split('_')[1]
+      }
+    }
+  }
+  return [genus, species]
+}
+
 workflow information {
   take:
     ch_contigs
@@ -31,35 +125,107 @@ workflow information {
         fastani:   it[1] =~ /fastani.csv/
       }
       .set { ch_flag_branch }
-    
+  
+
     ch_contigs
       .filter{it[1] != null}
+      .join(ch_flag_branch.fastani,   by:0, failOnMismatch: false, remainder: true)
       .join(ch_flag_branch.blobtools, by:0, failOnMismatch: false, remainder: true)
       .join(ch_flag_branch.kraken2,   by:0, failOnMismatch: false, remainder: true)
       .join(ch_flag_branch.mash,      by:0, failOnMismatch: false, remainder: true)
-      .join(ch_flag_branch.fastani,   by:0, failOnMismatch: false, remainder: true)
       .filter{it[1] != null}
-      .map{ it -> tuple(it[0],[it[1], it[2], it[3], it[4], it[5]])}
+      .map{ it -> tuple(it[0], it[1], [it[2], it[3], it[4], it[5]])}
       .set {ch_for_flag}
 
-    flag(ch_for_flag)
+    // Yersinia
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Yersinia'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_yersinia}
 
-    amrfinderplus(flag.out.organism)
-    drprg(flag.out.myco_flag)
-    emmtyper(flag.out.strepa_flag.combine(summfle_script)) 
-    kaptive(flag.out.vibrio_flag)      
-    kleborate(flag.out.klebsiella_flag.combine(summfle_script))
-    elgato(flag.out.legionella_flag)
-    mykrobe(flag.out.myco_flag)
-    pbptyper(flag.out.streppneu_flag)
-    seqsero2(flag.out.salmonella_flag)
-    serotypefinder(flag.out.ecoli_flag.combine(summfle_script))
-    shigatyper(flag.out.ecoli_flag.combine(summfle_script))
+    // Salmonella
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Salmonella'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_salmonella}
+
+    // E. coli and Shigella
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Escherichia', 'Shigella'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_ecoli}
+
+    // Klebsiella
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Klebsiella', 'Enterobacter', 'Serratia'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_kleb}
+
+    // Group A Strep
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Streptococcus'])}
+      .filter{flagOrg(it[2], ['pyogenes', 'dysgalactiae', 'anginosus'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_gas}
+
+    // Streptococcus pneumoniae
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Streptococcus'])}
+      .filter{flagOrg(it[2], ['pneumoniae'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_strep}
+
+    // Legionella
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Legionella'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_legionella}
+
+    // Vibrio
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Vibrio'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_vibrio}
+
+    // Acinetobacter
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Acinetobacter'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_acinetobacter}
+
+    // Mycobacterium/Mycobacteria
+    ch_for_flag
+      .filter{flagOrg(it[2], ['Mycobacteri'])}
+      .map { it -> tuple(it[0], it[1])}
+      .set {ch_myco}
+
+    // Getting the top organism for each sample
+    // for amrfinderplus
+    // for prokka
+    ch_for_flag
+      .map {
+        it ->
+          genus_species = topOrg(it[2])
+          tuple (it[0], it[1], genus_species[0], genus_species[1])
+      }
+      .set { ch_organism }
+
+    amrfinderplus(ch_organism)
+    drprg(ch_myco)
+    emmtyper(ch_gas.combine(summfle_script)) 
+    kaptive(ch_vibrio)      
+    kleborate(ch_kleb.combine(summfle_script))
+    elgato(ch_legionella)
+    mykrobe(ch_myco)
+    pbptyper(ch_strep)
+    seqsero2(ch_salmonella)
+    serotypefinder(ch_ecoli.combine(summfle_script))
+    shigatyper(ch_ecoli.combine(summfle_script))
 
     json_convert(drprg.out.json.combine(jsoncon_script))
 
     amrfinderplus.out.collect
-      .collectFile(name: "amrfinderplus.txt",
+      .collectFile(name: 'amrfinderplus.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/ncbi-AMRFinderplus")
@@ -67,84 +233,77 @@ workflow information {
 
     json_convert.out.collect
       .filter( ~/.*drprg.tsv/ )
-      .collectFile(name: "drprg_summary.tsv",
+      .collectFile(name: 'drprg_summary.tsv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/drprg")
       .set{ drprg_summary }
 
     elgato.out.collect
-      .collectFile(name: "elgato_summary.tsv",
+      .collectFile(name: 'elgato_summary.tsv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/elgato")
       .set{ elgato_summary }
 
     emmtyper.out.collect
-      .collectFile(name: "emmtyper_summary.tsv",
+      .collectFile(name: 'emmtyper_summary.tsv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/emmtyper")
       .set{ emmtyper_summary }
 
-    flag.out.collect
-      .collectFile(name: "flag_summary.csv",
-        keepHeader: true,
-        sort: {file -> file.text },
-        storeDir: "${params.outdir}/flag")
-      .set { flag_summary }
-
     kaptive.out.collect
-      .collectFile(name: "kaptive_summary.txt",
+      .collectFile(name: 'kaptive_summary.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/kaptive")
       .set{ kaptive_summary }
     
     kleborate.out.collect
-      .collectFile(name: "kleborate_results.tsv",
+      .collectFile(name: 'kleborate_results.tsv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/kleborate")
       .set{ kleborate_summary }
 
     mykrobe.out.collect
-      .collectFile(name: "mykrobe_summary.csv",
+      .collectFile(name: 'mykrobe_summary.csv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/mykrobe")
       .set{ mykrobe_summary }
 
     pbptyper.out.collect
-      .collectFile(name: "pbptyper_summary.tsv",
+      .collectFile(name: 'pbptyper_summary.tsv',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/pbptyper")
       .set{ pbptyper_summary }
 
     seqsero2.out.collect
-      .collectFile(name: "seqsero2_results.txt",
+      .collectFile(name: 'seqsero2_results.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/seqsero2")
       .set{ seqsero2_summary }
 
     serotypefinder.out.collect
-      .collectFile(name: "serotypefinder_results.txt",
+      .collectFile(name: 'serotypefinder_results.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/serotypefinder")
       .set{ serotypefinder_summary }
 
     shigatyper.out.collect
-      .collectFile(name: "shigatyper_hits.txt",
+      .collectFile(name: 'shigatyper_hits.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/shigatyper")
       .set{ shigatyper_hits }
 
     shigatyper.out.files
-      .collectFile(name: "shigatyper_summary.txt",
+      .collectFile(name: 'shigatyper_summary.txt',
         keepHeader: true,
         sort: { file -> file.text },
         storeDir: "${params.outdir}/shigatyper")