From d4e7d5a1233cc7ed579c4d601498864c469f6c42 Mon Sep 17 00:00:00 2001
From: Kaitlyn Jiayi Li <kli@lanl.gov>
Date: Tue, 30 Jul 2024 14:33:48 -0700
Subject: [PATCH 1/5] bumped rfam mem and made variable

---
 rfam.wdl | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/rfam.wdl b/rfam.wdl
index cbd4057..d1499c5 100755
--- a/rfam.wdl
+++ b/rfam.wdl
@@ -43,6 +43,7 @@ task run {
         String claninfo_tsv
         String feature_lookup_tsv
         Int    threads
+        Int    memory = 100
         String container
         String rfam_version_file = "rfam_version.txt"
     }
@@ -67,8 +68,9 @@ task run {
 
   runtime {
     time: "1:00:00"
-    memory: "86G"
     docker: container
+    cpu: threads
+    memory: "~{memory} GiB"
   }
 
   output {

From 20f5409f38b9ca2def5f60d2a0a2c8d871bdbf03 Mon Sep 17 00:00:00 2001
From: Kaitlyn Jiayi Li <kli@lanl.gov>
Date: Tue, 30 Jul 2024 15:50:47 -0700
Subject: [PATCH 2/5] also fixed some warnings from jaws validate

---
 annotation_full.wdl       | 14 ++-----
 functional-annotation.wdl | 30 +--------------
 structural-annotation.wdl | 80 +++++++++++++++++++--------------------
 3 files changed, 44 insertions(+), 80 deletions(-)

diff --git a/annotation_full.wdl b/annotation_full.wdl
index c763075..4e37bc1 100644
--- a/annotation_full.wdl
+++ b/annotation_full.wdl
@@ -6,11 +6,11 @@ import "./functional-annotation.wdl" as fa
 workflow annotation {
 input {
   String  proj
-  String  input_file
+  File  input_file
   String  imgap_project_id
   String  database_location="/refdata/img/"
   String  imgap_project_type="metagenome"
-  String?  gm_license="/refdata/licenses/.gmhmmp2_key"
+  String  gm_license="/refdata/licenses/.gmhmmp2_key"
   Int     additional_threads=16
   String  container="microbiomedata/img-omics@sha256:d5f4306bf36a97d55a3710280b940b89d7d4aca76a343e75b0e250734bc82b71"
 
@@ -148,9 +148,7 @@ input {
   call finish_ano {
     input:
       container=container,
-      input_file=make_map_file.out_fasta,
       proj=proj,
-      start=stage.start,
       ano_info_file=make_info_file.imgap_info,
       proteins_faa = merge_outputs.proteins_faa,
       structural_gff = merge_outputs.structural_gff,
@@ -235,7 +233,7 @@ task stage {
     input {
         String container
         String target="input.fasta"
-        String input_file
+        File   input_file
     }
 
    command <<<
@@ -300,7 +298,7 @@ task make_map_file {
 task split {
     input {
        File infile
-       String blocksize=100
+       Int blocksize=100
        String zfile="zscore.txt"
        String cmzfile="cmzscore.txt"
        String container
@@ -504,8 +502,6 @@ task make_info_file {
         String fa_version_file = "fa_tool_version.txt"
         String fa_db_version_file = "fa_db_version.txt"
         String rfam_version_file = "rfam_version.txt"
-        String sa_version_file = "sa_tool_version.txt"
-        String sa_db_version_file = "sa_db_version.txt"
     }
   command <<<
     set -euo pipefail
@@ -618,9 +614,7 @@ task finish_ano {
        String container
        String proj
        String prefix=sub(proj, ":", "_")
-       String start
        File ano_info_file
-       File input_file
        File proteins_faa
        File structural_gff
        File functional_gff
diff --git a/functional-annotation.wdl b/functional-annotation.wdl
index 9edcfa5..1d392ff 100755
--- a/functional-annotation.wdl
+++ b/functional-annotation.wdl
@@ -15,15 +15,11 @@ workflow f_annotate {
         Int?    par_hmm_inst
         Int?    approx_num_proteins
         String  smart_db="~{database_location}"+"/SMART/01_06_2016/SMART.hmm"
-        String  hmmsearch_bin="/opt/omics/bin/hmmsearch"
-        String  frag_hits_filter_bin="/opt/omics/bin/functional_annotation/hmmsearch_fragmented_hits_filter.py"
         String  cog_db="~{database_location}"+"/COG/HMMs/2003/COG.hmm"
         String  tigrfam_db="~{database_location}"+"/TIGRFAM/v15.0/TIGRFAM.hmm"
-        String  hit_selector_bin="/opt/omics/bin/functional_annotation/hmmsearch_hit_selector.py"
         String  superfam_db="~{database_location}"+"/SuperFamily/v1.75/supfam.hmm"
         String  pfam_db="~{database_location}"+"/Pfam/Pfam-A/v34.0/Pfam-A.v34.0.hmm"
         String  pfam_claninfo_tsv="~{database_location}"+"/Pfam/Pfam-A/v34.0/Pfam-A.clans.tsv"
-        String  pfam_clan_filter="/opt/omics/bin/functional_annotation/pfam_clan_filter.py"
         String  cath_funfam_db="~{database_location}"+"/Cath-FunFam/v4.2.0/funfam.hmm"
         #  Boolean signalp_execute=true
         #  String  signalp_gram_stain="GRAM_STAIN"
@@ -61,8 +57,6 @@ workflow f_annotate {
         par_hmm_inst = par_hmm_inst,
         approx_num_proteins = approx_num_proteins,
         smart_db = smart_db,
-        hmmsearch = hmmsearch_bin,
-        frag_hits_filter = frag_hits_filter_bin,
         container=hmm_container
     }
 
@@ -74,8 +68,6 @@ workflow f_annotate {
         par_hmm_inst = par_hmm_inst,
         approx_num_proteins = approx_num_proteins,
         cog_db = cog_db,
-        hmmsearch = hmmsearch_bin,
-        frag_hits_filter = frag_hits_filter_bin,
         container=hmm_container
     }
 
@@ -87,8 +79,6 @@ workflow f_annotate {
         par_hmm_inst = par_hmm_inst,
         approx_num_proteins = approx_num_proteins,
         tigrfam_db = tigrfam_db,
-        hmmsearch = hmmsearch_bin,
-        hit_selector = hit_selector_bin,
         container=hmm_container
     }
 
@@ -100,8 +90,6 @@ workflow f_annotate {
         par_hmm_inst = par_hmm_inst,
         approx_num_proteins = approx_num_proteins,
         superfam_db = superfam_db,
-        hmmsearch = hmmsearch_bin,
-        frag_hits_filter = frag_hits_filter_bin,
         container=hmm_container
     }
 
@@ -114,8 +102,6 @@ workflow f_annotate {
         approx_num_proteins = approx_num_proteins,
         pfam_db = pfam_db,
         pfam_claninfo_tsv = pfam_claninfo_tsv,
-        pfam_clan_filter = pfam_clan_filter,
-        hmmsearch = hmmsearch_bin,
         container=hmm_container
     }
 
@@ -127,8 +113,6 @@ workflow f_annotate {
         par_hmm_inst = par_hmm_inst,
         approx_num_proteins = approx_num_proteins,
         cath_funfam_db = cath_funfam_db,
-        hmmsearch = hmmsearch_bin,
-        frag_hits_filter = frag_hits_filter_bin,
         container=hmm_container
     }
 
@@ -256,8 +240,6 @@ task smart {
         Float  min_domain_eval_cutoff = 0.01
         Float  aln_length_ratio = 0.7
         Float  max_overlap_ratio = 0.1
-        String hmmsearch
-        String frag_hits_filter
         String base=basename(input_fasta)
         String container
         String hmmsearch_version_file = "hmmsearch_version.txt"
@@ -304,8 +286,6 @@ task cog {
         Float  min_domain_eval_cutoff = 0.01
         Float  aln_length_ratio = 0.7
         Float  max_overlap_ratio = 0.1
-        String hmmsearch
-        String frag_hits_filter
         String base=basename(input_fasta)
         String container
         String hmmsearch_version_file = "hmmsearch_version.txt"
@@ -351,8 +331,6 @@ task tigrfam {
       Int    approx_num_proteins = 0
       Float  aln_length_ratio = 0.7
       Float  max_overlap_ratio = 0.1
-      String hmmsearch
-      String hit_selector
       String base=basename(input_fasta)
       String container
       String hmmsearch_version_file = "hmmsearch_version.txt"
@@ -400,8 +378,6 @@ task superfam {
         Float  min_domain_eval_cutoff = 0.01
         Float  aln_length_ratio = 0.7
         Float  max_overlap_ratio = 0.1
-        String hmmsearch
-        String frag_hits_filter
         String base=basename(input_fasta)
         String container
         String hmmsearch_version_file =  "hmmsearch_version.txt"
@@ -447,8 +423,6 @@ task pfam {
         Int    threads = 62
         Int    par_hmm_inst = 15
         Int    approx_num_proteins = 0
-        String hmmsearch
-        String pfam_clan_filter
         String base=basename(input_fasta)
         String container
         String hmmsearch_version_file = "hmmsearch_version.txt"
@@ -495,8 +469,6 @@ task cath_funfam {
         Float  min_domain_eval_cutoff = 0.01
         Float  aln_length_ratio = 0.7
         Float  max_overlap_ratio = 0.1
-        String hmmsearch
-        String frag_hits_filter
         String base=basename(input_fasta)
         String container
         String hmmsearch_version_file = "hmmsearch_version.txt"
@@ -529,7 +501,7 @@ task cath_funfam {
   }
 }
 
-task signalp {
+task run_signalp {
     input {
         String project_id
         String prefix=sub(project_id, ":", "_")
diff --git a/structural-annotation.wdl b/structural-annotation.wdl
index 207ccc2..4435088 100755
--- a/structural-annotation.wdl
+++ b/structural-annotation.wdl
@@ -27,7 +27,7 @@ workflow s_annotate {
     # }
 
 
-    call trnascan.trnascan {
+    call trnascan.trnascan as ts{
       input:
         imgap_input_fasta = imgap_input_fasta,
         imgap_project_id = imgap_project_id,
@@ -36,7 +36,7 @@ workflow s_annotate {
     }
 
 
-    call rfam.rfam {
+    call rfam.rfam as rf{
       input:
         cmzscore = cmzscore,
         imgap_input_fasta = imgap_input_fasta,
@@ -47,7 +47,7 @@ workflow s_annotate {
     }
 
 
-    call crt.crt {
+    call crt.crt as ct {
       input:
         imgap_input_fasta = imgap_input_fasta,
         imgap_project_id = imgap_project_id,
@@ -56,7 +56,7 @@ workflow s_annotate {
 
 
 
-     call cds_prediction.cds_prediction {
+     call cds_prediction.cds_prediction as cds{
        input:
          imgap_input_fasta = imgap_input_fasta,
          imgap_project_id = imgap_project_id,
@@ -72,10 +72,10 @@ workflow s_annotate {
       input:
         input_fasta = imgap_input_fasta,
         project_id = imgap_project_id,
-        rfam_gff = rfam.rfam_gff,
-        trna_gff = trnascan.gff,
-        crt_gff = crt.gff,
-        cds_gff = cds_prediction.gff,
+        rfam_gff = rf.rfam_gff,
+        trna_gff = ts.gff,
+        crt_gff = ct.gff,
+        cds_gff = cds.gff,
         container = container
     }
 
@@ -84,8 +84,8 @@ workflow s_annotate {
        # input_fasta = imgap_input_fasta,
         project_id = imgap_project_id,
         final_gff = gff_merge.final_gff,
-        cds_genes = cds_prediction.genes,
-        cds_proteins = cds_prediction.proteins,
+        cds_genes = cds.genes,
+        cds_proteins = cds.proteins,
         container = container
     }
 
@@ -94,7 +94,6 @@ workflow s_annotate {
     call gff_and_fasta_stats {
       input:
         input_fasta = imgap_input_fasta,
-        project_id = imgap_project_id,
         final_gff = gff_merge.final_gff,
         container = container
     }
@@ -104,24 +103,24 @@ workflow s_annotate {
 
   output {
     File  gff = gff_merge.final_gff 
-    File crt_gff = crt.gff
-    File crisprs = crt.crisprs
-    File crt_out = crt.crt_out
-    File genemark_gff = cds_prediction.genemark_gff
-    File genemark_genes = cds_prediction.genemark_genes
-    File genemark_proteins = cds_prediction.genemark_proteins
-    File prodigal_gff = cds_prediction.prodigal_gff
-    File prodigal_genes = cds_prediction.prodigal_genes
-    File prodigal_proteins = cds_prediction.prodigal_proteins
-    File cds_gff = cds_prediction.gff
-    File cds_proteins = cds_prediction.proteins
-    File cds_genes = cds_prediction.genes
-    File trna_gff = trnascan.gff
-    File trna_bacterial_out = trnascan.bacterial_out
-    File trna_archaeal_out = trnascan.archaeal_out
-    File rfam_gff = rfam.rfam_gff
-    File rfam_tbl = rfam.rfam_tbl
-    String rfam_version = rfam.rfam_version
+    File crt_gff = ct.gff
+    File crisprs = ct.crisprs
+    File crt_out = ct.crt_out
+    File genemark_gff = cds.genemark_gff
+    File genemark_genes = cds.genemark_genes
+    File genemark_proteins = cds.genemark_proteins
+    File prodigal_gff = cds.prodigal_gff
+    File prodigal_genes = cds.prodigal_genes
+    File prodigal_proteins = cds.prodigal_proteins
+    File cds_gff = cds.gff
+    File cds_proteins = cds.proteins
+    File cds_genes = cds.genes
+    File trna_gff = ts.gff
+    File trna_bacterial_out = ts.bacterial_out
+    File trna_archaeal_out = ts.archaeal_out
+    File rfam_gff = rf.rfam_gff
+    File rfam_tbl = rf.rfam_tbl
+    String rfam_version = rf.rfam_version
     File proteins = fasta_merge.final_proteins
     File genes = fasta_merge.final_genes
   }
@@ -138,28 +137,28 @@ task pre_qc {
         Int    seqs_per_million_bp_cutoff = 500
         Int    min_seq_length = 150
         String container
-        File tmp_fasta="~{input_fasta}.tmp"
-        File qced_fasta="~{prefix}_contigs.fna"
+        String tmp_fasta="~{input_fasta}.tmp"
+        String qced_fasta="~{prefix}_contigs.fna"
     }
 
   command <<<
     set -euo pipefail
     echo ~{tmp_fasta}
     grep -v '^\s*$' ~{input_fasta} | tr -d '\r' | \
-    sed 's/^>[[:blank:]]*/>/g' > $tmp_fasta
-    acgt_count=`grep -v '^>' $tmp_fasta | grep -o [acgtACGT] | wc -l`
-    n_count=`grep -v '^>' $tmp_fasta | grep -o '[^acgtACGT]' | wc -l`
+    sed 's/^>[[:blank:]]*/>/g' > ~{tmp_fasta}
+    acgt_count=`grep -v '^>' ~{tmp_fasta} | grep -o [acgtACGT] | wc -l`
+    n_count=`grep -v '^>' ~{tmp_fasta} | grep -o '[^acgtACGT]' | wc -l`
     n_ratio=`echo ~n_count $acgt_count | awk '{printf "%f", $1 / $2}'`
     if (( $(echo "~n_ratio >= ~{n_ratio_cutoff}" | bc) ))
     then
-        rm $tmp_fasta
+        rm ~{tmp_fasta}
         exit 1
     fi
 
     if [[ ~{project_type} == "isolate" ]]
     then
-        seq_count=`grep -c '^>' ~tmp_fasta`
-        bp_count=`grep -v '^>' ~tmp_fasta | tr -d '\n' | wc -m`
+        seq_count=`grep -c '^>' ~{tmp_fasta}`
+        bp_count=`grep -v '^>' ~{tmp_fasta} | tr -d '\n' | wc -m`
         seqs_per_million_bp=$seq_count
         if (( $bp_count > 1000000 ))
         then
@@ -169,13 +168,13 @@ task pre_qc {
         fi
         if (( $(echo "~seqs_per_million_bp > ~{seqs_per_million_bp_cutoff}" | bc) ))
         then
-            rm $tmp_fasta
+            rm ~{tmp_fasta}
             exit 1
         fi
     fi
     ~{bin} -v
-    ~{bin} ~tmp_fasta ~qced_fasta -l ~{min_seq_length}
-    rm ~tmp_fasta
+    ~{bin} ~{tmp_fasta} ~{qced_fasta} -l ~{min_seq_length}
+    rm ~{tmp_fasta}
   >>>
 
   runtime {
@@ -265,7 +264,6 @@ task gff_and_fasta_stats {
     input {
         String bin="/opt/omics/bin/structural_annotation/gff_and_final_fasta_stats.py"
         File   input_fasta
-        String project_id
         File   final_gff
         String container
     }

From 04d39de557744eeca600972cad6398c5a256b3f9 Mon Sep 17 00:00:00 2001
From: Kaitlyn Jiayi Li <kli@lanl.gov>
Date: Tue, 30 Jul 2024 15:59:01 -0700
Subject: [PATCH 3/5] brought additional memory parameter out to metaT level

---
 annotation_full.wdl       | 4 +++-
 rfam.wdl                  | 4 +++-
 structural-annotation.wdl | 4 +++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/annotation_full.wdl b/annotation_full.wdl
index 4e37bc1..0395635 100644
--- a/annotation_full.wdl
+++ b/annotation_full.wdl
@@ -12,6 +12,7 @@ input {
   String  imgap_project_type="metagenome"
   String  gm_license="/refdata/licenses/.gmhmmp2_key"
   Int     additional_threads=16
+  Int     additional_memory = 100
   String  container="microbiomedata/img-omics@sha256:d5f4306bf36a97d55a3710280b940b89d7d4aca76a343e75b0e250734bc82b71"
 
   # structural annotation
@@ -49,7 +50,8 @@ input {
           imgap_project_type = imgap_project_type,
           database_location = database_location,
           container=container,
-          gm_license=gm_license
+          gm_license=gm_license,
+          additional_memory = additional_memory
       }
 
 
diff --git a/rfam.wdl b/rfam.wdl
index d1499c5..54124f1 100755
--- a/rfam.wdl
+++ b/rfam.wdl
@@ -5,6 +5,7 @@ workflow rfam {
         File imgap_input_fasta
         String imgap_project_id
         Int    additional_threads
+        Int    additional_memory
         String database_location="/refdata/img/"
         String cm="~{database_location}"+"Rfam/13.0/Rfam.cm"
         String claninfo_tsv="~{database_location}"+"Rfam/13.0/Rfam.claninfo"
@@ -21,7 +22,8 @@ workflow rfam {
       feature_lookup_tsv = feature_lookup_tsv,
       claninfo_tsv = claninfo_tsv,
       threads = additional_threads,
-      container=container
+      container=container,
+      memory = additional_memory
   }
 
   output {
diff --git a/structural-annotation.wdl b/structural-annotation.wdl
index 4435088..95982e4 100755
--- a/structural-annotation.wdl
+++ b/structural-annotation.wdl
@@ -12,6 +12,7 @@ workflow s_annotate {
       String  imgap_project_id
       String  imgap_project_type
       Int     additional_threads
+      Int     additional_memory
       Int? imgap_structural_annotation_translation_table
       String  database_location
       String  container
@@ -43,7 +44,8 @@ workflow s_annotate {
         imgap_project_id = imgap_project_id,
         database_location = database_location,
         additional_threads = additional_threads,
-        container=container
+        container=container,
+        additional_memory = additional_memory
     }
 
 

From ee2956f2c751b5eb2c154960995bfa962147db77 Mon Sep 17 00:00:00 2001
From: Kaitlyn Jiayi Li <kli@lanl.gov>
Date: Tue, 6 Aug 2024 09:59:55 -0700
Subject: [PATCH 4/5] version bump

---
 version.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/version.txt b/version.txt
index 0f1acbd..c641220 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-v1.1.2
+v1.1.4

From 62fd2774211f1899010048e7fbf8135209873a68 Mon Sep 17 00:00:00 2001
From: Kaitlyn Jiayi Li <kli@lanl.gov>
Date: Thu, 8 Aug 2024 14:06:22 -0700
Subject: [PATCH 5/5] revert file to string

---
 annotation_full.wdl | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/annotation_full.wdl b/annotation_full.wdl
index 0395635..00a2f12 100644
--- a/annotation_full.wdl
+++ b/annotation_full.wdl
@@ -6,7 +6,7 @@ import "./functional-annotation.wdl" as fa
 workflow annotation {
 input {
   String  proj
-  File  input_file
+  String  input_file
   String  imgap_project_id
   String  database_location="/refdata/img/"
   String  imgap_project_type="metagenome"
@@ -235,7 +235,7 @@ task stage {
     input {
         String container
         String target="input.fasta"
-        File   input_file
+        String   input_file
     }
 
    command <<<