From 3eab77927a93d8444996a8b017af6d19f1086aaf Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Fri, 2 Dec 2022 13:07:42 -0800
Subject: [PATCH 01/13] remove assemdir artifact

---
 jgi_assembly.wdl | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 4fbaf65..3382d1b 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -135,10 +135,10 @@ task finish_asm {
         # ln ${agp} ${prefix}_assembly.agp
 
         ##RE-ID
-        cat ${fasta} | sed ${sed} > ${assemdir}/${prefix}_contigs.fna
-        cat ${scaffold} | sed ${sed} > ${assemdir}/${prefix}_scaffolds.fna
-        cat ${covstats} | sed ${sed} > ${assemdir}/${prefix}_covstats.txt
-        cat ${agp} | sed ${sed} > ${assemdir}/${prefix}_assembly.agp
+        cat ${fasta} | sed ${sed} > {prefix}_contigs.fna
+        cat ${scaffold} | sed ${sed} > ${prefix}_scaffolds.fna
+        cat ${covstats} | sed ${sed} > ${prefix}_covstats.txt
+        cat ${agp} | sed ${sed} > ${prefix}_assembly.agp
 
        ## Bam file     
        samtools view -h ${bam} | sed ${sed} | \

From 85ca52b918eb2868d4724f84122b5be16dd40ed3 Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Wed, 7 Dec 2022 12:21:26 -0800
Subject: [PATCH 02/13] change origin of input for finish_asm

---
 jgi_assembly.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 3382d1b..3184709 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -43,7 +43,7 @@ workflow jgi_metaASM {
         container="microbiomedata/workflowmeta:1.1.0",
         informed_by=informed_by,
         resource=resource,
-        input_file=stage.assembly_input,
+        input_file=input_file,
         fasta=create_agp.outcontigs,
         scaffold=create_agp.outscaffolds,
         agp=create_agp.outagp,

From cfec1c4d5f6e849f2cad4255982e01673e9cf17b Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Wed, 7 Dec 2022 12:54:14 -0800
Subject: [PATCH 03/13] add url inline for finish_asm

---
 jgi_assembly.wdl | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 3184709..c3d01de 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -161,15 +161,15 @@ task finish_asm {
                 ended_at_time=$end \
                 execution_resource=${resource} \
                 git_url=${git_url} \
-             --url ${url_root}${proj}/assembly/ \
-             --extra stats.json \
-             --inputs ${input_file} \
-             --outputs \
-             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
-             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
-             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\
-             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP"\
-             ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
+            --url ${url_root}${proj}/assembly/ \
+            --extra stats.json \
+            --inputs ${input_file} \
+            --outputs \
+            ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
+            ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
+            ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\
+            ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP"\
+            ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
 
     >>>
     output {

From 2240c3c805ce913079e0be86eb106c3d778d96a7 Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Wed, 7 Dec 2022 13:16:02 -0800
Subject: [PATCH 04/13] fix indentations

---
 jgi_assembly.wdl | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index c3d01de..4cd9764 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -152,19 +152,20 @@ task finish_asm {
 
 
        /scripts/generate_object_json.py \
-            --type "nmdc:MetagenomeAssembly" \
-            --set metagenome_assembly_set \ 
-            --part ${proj} \
+             --type "nmdc:MetagenomeAssembly" \
+             --set metagenome_assembly_set \ 
+             --part ${proj} \
              -p "name=Metagenome Assembly Activity for ${proj}" \
                 was_informed_by=${informed_by} \
                 started_at_time=${start} \
                 ended_at_time=$end \
                 execution_resource=${resource} \
                 git_url=${git_url} \
-            --url ${url_root}${proj}/assembly/ \
-            --extra stats.json \
-            --inputs ${input_file} \
-            --outputs \
+            
+             --url ${url_root}${proj}/qa/ \
+             --extra stats.json \
+             --inputs ${input_file} \
+             --outputs \
             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\

From 3237049809183e60890fe85eae7497718afb8d9e Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Wed, 7 Dec 2022 13:17:28 -0800
Subject: [PATCH 05/13] fix indentation for outputs

---
 jgi_assembly.wdl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 4cd9764..58f8cca 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -166,11 +166,11 @@ task finish_asm {
              --extra stats.json \
              --inputs ${input_file} \
              --outputs \
-            ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
-            ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
-            ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\
-            ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP"\
-            ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
+             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
+             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
+             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\
+             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP"\
+             ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
 
     >>>
     output {

From 53003d70f65a2a44a98aa157653fc9d1651c5f64 Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Thu, 8 Dec 2022 06:48:25 -0800
Subject: [PATCH 06/13] add version to werkflow

---
 jgi_assembly.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 58f8cca..fec2d8d 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -161,7 +161,7 @@ task finish_asm {
                 ended_at_time=$end \
                 execution_resource=${resource} \
                 git_url=${git_url} \
-            
+                version="v1.0.3-beta" \
              --url ${url_root}${proj}/qa/ \
              --extra stats.json \
              --inputs ${input_file} \

From e3b00e5a8a08830d43d746f81e3c5a6e25e1767b Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Thu, 8 Dec 2022 07:13:37 -0800
Subject: [PATCH 07/13] fix prefix reference

---
 jgi_assembly.wdl | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index fec2d8d..aa8d07c 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -135,7 +135,7 @@ task finish_asm {
         # ln ${agp} ${prefix}_assembly.agp
 
         ##RE-ID
-        cat ${fasta} | sed ${sed} > {prefix}_contigs.fna
+        cat ${fasta} | sed ${sed} > ${prefix}_contigs.fna
         cat ${scaffold} | sed ${sed} > ${prefix}_scaffolds.fna
         cat ${covstats} | sed ${sed} > ${prefix}_covstats.txt
         cat ${agp} | sed ${sed} > ${prefix}_assembly.agp
@@ -162,14 +162,14 @@ task finish_asm {
                 execution_resource=${resource} \
                 git_url=${git_url} \
                 version="v1.0.3-beta" \
-             --url ${url_root}${proj}/qa/ \
+             --url ${url_root}${proj}/assembly/ \
              --extra stats.json \
              --inputs ${input_file} \
              --outputs \
-             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs"\
-             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds"\
-             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats"\
-             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP"\
+             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" \
+             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" \
+             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats" \
+             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP" \
              ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
 
     >>>

From 2e2db28992ee465cf229352f306031ebe0652738 Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Thu, 8 Dec 2022 07:58:06 -0800
Subject: [PATCH 08/13] update metaworkflow version

---
 jgi_assembly.wdl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index aa8d07c..d737724 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -40,10 +40,10 @@ workflow jgi_metaASM {
         start=stage.start,
         git_url=git_url,
         url_root=url_root,
-        container="microbiomedata/workflowmeta:1.1.0",
+        container="microbiomedata/workflowmeta:1.1.1",
         informed_by=informed_by,
         resource=resource,
-        input_file=input_file,
+        input_file=stage.assembly_input,
         fasta=create_agp.outcontigs,
         scaffold=create_agp.outscaffolds,
         agp=create_agp.outagp,
@@ -106,7 +106,7 @@ task stage {
 }
 
 task finish_asm {
-    String input_file
+    Array[File] input_file
     File fasta
     File scaffold
     File? agp
@@ -153,7 +153,7 @@ task finish_asm {
 
        /scripts/generate_object_json.py \
              --type "nmdc:MetagenomeAssembly" \
-             --set metagenome_assembly_set \ 
+             --set metagenome_assembly_set \
              --part ${proj} \
              -p "name=Metagenome Assembly Activity for ${proj}" \
                 was_informed_by=${informed_by} \
@@ -164,7 +164,7 @@ task finish_asm {
                 version="v1.0.3-beta" \
              --url ${url_root}${proj}/assembly/ \
              --extra stats.json \
-             --inputs ${input_file} \
+             --inputs ${input_file[0]} ${input_file[1]} \
              --outputs \
              ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" \
              ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" \

From 4997dcef3c1ca88b781c93cf13bf0d29fa17c8ee Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Thu, 8 Dec 2022 08:15:21 -0800
Subject: [PATCH 09/13] add project description

---
 jgi_assembly.wdl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index d737724..7ac3636 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -166,11 +166,11 @@ task finish_asm {
              --extra stats.json \
              --inputs ${input_file[0]} ${input_file[1]} \
              --outputs \
-             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" \
-             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" \
-             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats" \
-             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP" \
-             ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM"
+             nmdc_mgasm0xxxx.1_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" "Assembly contigs for ${proj}" \
+             nmdc_mgasm0xxxx.1_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" "Assembly scaffolds for ${proj}" \
+             nmdc_mgasm0xxxx.1_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats" "Coverage Stats for ${proj}" \
+             nmdc_mgasm0xxxx.1_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP" "AGP for ${proj}" \
+             nmdc_mgasm0xxxx.1_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM" "Sorted Bam for ${proj}"
 
     >>>
     output {

From 0b97f24193fdd30836d92d98d0b8af52f2fbdb38 Mon Sep 17 00:00:00 2001
From: Shane Canon <scanon@lbl.gov>
Date: Thu, 8 Dec 2022 08:17:39 -0800
Subject: [PATCH 10/13] add prefix back

---
 jgi_assembly.wdl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 7ac3636..94d80fa 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -166,11 +166,11 @@ task finish_asm {
              --extra stats.json \
              --inputs ${input_file[0]} ${input_file[1]} \
              --outputs \
-             nmdc_mgasm0xxxx.1_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" "Assembly contigs for ${proj}" \
-             nmdc_mgasm0xxxx.1_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" "Assembly scaffolds for ${proj}" \
-             nmdc_mgasm0xxxx.1_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats" "Coverage Stats for ${proj}" \
-             nmdc_mgasm0xxxx.1_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP" "AGP for ${proj}" \
-             nmdc_mgasm0xxxx.1_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM" "Sorted Bam for ${proj}"
+             ${prefix}_contigs.fna "Final assembly contigs fasta" "Assembly Contigs" "Assembly contigs for ${proj}" \
+             ${prefix}_scaffolds.fna "Final assembly scaffolds fasta" "Assembly Scaffolds" "Assembly scaffolds for ${proj}" \
+             ${prefix}_covstats.txt "Assembled contigs coverage information" "Assembly Coverage Stats" "Coverage Stats for ${proj}" \
+             ${prefix}_assembly.agp "An AGP format file that describes the assembly" "Assembly AGP" "AGP for ${proj}" \
+             ${prefix}_pairedMapped_sorted.bam "Sorted bam file of reads mapping back to the final assembly" "Assembly Coverage BAM" "Sorted Bam for ${proj}"
 
     >>>
     output {

From 95ae1f9ce5347908c5e89ac0ad84d795642ff698 Mon Sep 17 00:00:00 2001
From: Chienchi Lo <chien-chi@pn2034281.lanl.gov>
Date: Fri, 27 Jan 2023 17:03:31 -0700
Subject: [PATCH 11/13] add make_info_file task

---
 jgi_assembly.wdl | 112 +++++++++++++++++++++++++++++++----------------
 1 file changed, 74 insertions(+), 38 deletions(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 94d80fa..0abd4b3 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -34,6 +34,9 @@ workflow jgi_metaASM {
          input: reads=stage.assembly_input, ref=create_agp.outcontigs, container=bbtools_container, memory=memory, threads=threads,  paired = paired
     }
 
+    call make_info_file {
+         input: bbcms_info= bbcms.outcounts, assy_info = assy.outlog, container=bbtools_container, proj=proj
+    }
     call finish_asm {
         input:
         proj=proj,
@@ -62,6 +65,7 @@ workflow jgi_metaASM {
         File covstats=finish_asm.outcovstats
         File asmstats=finish_asm.outasmstats
         File objects=finish_asm.objects
+        File asminfo=make_info_file.asminfo
     }
  
     meta {
@@ -105,6 +109,36 @@ task stage {
    }
 }
 
+task make_info_file {
+    File assy_info
+    File bbcms_info
+    String proj
+    String prefix=sub(proj, ":", "_")
+    String container
+
+    command<<<
+        bbtools_version=`grep BBToolsVer ${bbcms_info}| awk '{print $2}' | sed -e 's/"//g' -e 's/,//' `
+        spades_version=`grep  'SPAdes version' ${assy_info} | awk '{print $3}'`
+        echo -e "The workflow takes paired-end reads runs error correction by bbcms.sh (BBTools(1) version $bbtools_version)." > ${prefix}_metaAsm.info
+        echo -e "The clean reads are assembled by metaSpades(2) version $spades_version with parameters, --only-assembler -k 33,55,77,99,127  --meta" >> ${prefix}_metaAsm.info
+        echo -e "After assembly, Contigs and Scaffolds are consumed by the *create_agp* task to rename the FASTA header and generate an AGP format (https://www.ncbi.nlm.nih.gov/assembly/agp/AGP_Specification/) file which describes the assembly"
+        echo -e "In the end, the reads are mapped back to contigs by bbmap (BBTools(1) version $bbtools_version) for coverage information." >> ${prefix}_metaAsm.info
+
+        echo -e "\n(1) B. Bushnell: BBTools software package, http://bbtools.jgi.doe.gov/" >> ${prefix}_metaAsm.info
+        echo -e "(2) Nurk S, Meleshko D, Korobeynikov A, Pevzner PA. metaSPAdes: a new versatile metagenomic assembler. Genome Res. 2017 May;27(5):824-834."  >> ${prefix}_metaAsm.info
+    >>>
+
+    output {
+        File asminfo = "${prefix}_metaAsm.info"
+    }
+    runtime {
+        memory: "1 GiB"
+        cpu:  1
+        maxRetries: 1
+        docker: container
+    }
+}
+
 task finish_asm {
     Array[File] input_file
     File fasta
@@ -174,13 +208,13 @@ task finish_asm {
 
     >>>
     output {
-       	File outcontigs = "${prefix}_contigs.fna"
-		File outscaffolds = "${prefix}_scaffolds.fna"
+        File outcontigs = "${prefix}_contigs.fna"
+        File outscaffolds = "${prefix}_scaffolds.fna"
         File outagp = "${prefix}_assembly.agp"
-		File outbam = "${prefix}_pairedMapped_sorted.bam"
-		File outsamgz = "${prefix}_pairedMapped.sam.gz"
-		File outcovstats = "${prefix}_covstats.txt"
-		File outasmstats = "stats.json"
+        File outbam = "${prefix}_pairedMapped_sorted.bam"
+        File outsamgz = "${prefix}_pairedMapped.sam.gz"
+        File outcovstats = "${prefix}_covstats.txt"
+        File outasmstats = "stats.json"
         File objects = "objects.json"
     }
 
@@ -209,28 +243,28 @@ task make_output{
         String asmstats_name=basename(contigs)
         String container
  
- 	command{
- 		if [ ! -z ${outdir} ]; then
- 			mkdir -p ${outdir}
- 			cp ${contigs} ${scaffolds} ${agp} ${bam} \
- 			   ${samgz} ${covstats} ${asmstats} ${outdir}
- 			chmod 764 -R ${outdir}
- 		fi
- 	}
-	runtime {
+    command{
+        if [ ! -z ${outdir} ]; then
+            mkdir -p ${outdir}
+            cp ${contigs} ${scaffolds} ${agp} ${bam} \
+               ${samgz} ${covstats} ${asmstats} ${outdir}
+            chmod 764 -R ${outdir}
+        fi
+    }
+    runtime {
                 docker: container
-		memory: "1 GiB"
-		cpu:  1
-	}
-	output{
-		File? outcontigs = "${outdir}/${contigs_name}"
-		File? outscaffolds = "${outdir}/${scaffolds_name}"
-		File? outagp = "${outdir}/${agp_name}"
-		File? outbam = "${outdir}/${bam_name}"
-		File? outsamgz = "${outdir}/${samgz_name}"
-		File? outcovstats = "${outdir}/${covstats_name}"
-		File? outasmstats = "${outdir}/${asmstats_name}"
-	}
+        memory: "1 GiB"
+        cpu:  1
+    }
+    output{
+        File? outcontigs = "${outdir}/${contigs_name}"
+        File? outscaffolds = "${outdir}/${scaffolds_name}"
+        File? outagp = "${outdir}/${agp_name}"
+        File? outbam = "${outdir}/${bam_name}"
+        File? outsamgz = "${outdir}/${samgz_name}"
+        File? outcovstats = "${outdir}/${covstats_name}"
+        File? outasmstats = "${outdir}/${asmstats_name}"
+    }
 }
 
 task read_mapping_pairs{
@@ -253,8 +287,8 @@ task read_mapping_pairs{
     runtime {
             docker: container
             memory: "120 GiB"
-	    cpu:  16
-	    maxRetries: 1
+        cpu:  16
+        maxRetries: 1
      }
     command{
         set -eo pipefail
@@ -270,7 +304,7 @@ task read_mapping_pairs{
         samtools sort -m100M -@ ${jvm_threads} ${filename_unsorted} -o ${filename_sorted}
         samtools index ${filename_sorted}
         reformat.sh -Xmx${default="105G" memory} in=${filename_unsorted} out=${filename_outsam} overwrite=true
-	    ln ${filename_cov} mapping_stats.txt
+        ln ${filename_cov} mapping_stats.txt
         rm $mapping_input
   }
   output{
@@ -294,7 +328,7 @@ task create_agp {
     runtime {
             docker: container
             memory: "120 GiB"
-	    cpu:  16
+        cpu:  16
      }
     command{
         fungalrelease.sh -Xmx${default="105G" memory} in=${scaffolds_in} out=${filename_scaffolds} outc=${filename_contigs} agp=${filename_agp} legend=${filename_legend} mincontig=200 minscaf=200 sortscaffolds=t sortcontigs=t overwrite=t
@@ -305,10 +339,10 @@ task create_agp {
         sed -i 's/l_gt50k/l_gt50K/g' stats.json
     }
     output{
-	File outcontigs = filename_contigs
-	File outscaffolds = filename_scaffolds
-	File outagp = filename_agp
-	File outstats = "stats.json"
+    File outcontigs = filename_contigs
+    File outscaffolds = filename_scaffolds
+    File outagp = filename_agp
+    File outstats = "stats.json"
     File outlegend = filename_legend
     }
 }
@@ -327,7 +361,7 @@ task assy {
      runtime {
             docker: container
             memory: "120 GiB"
-	    cpu:  16
+        cpu:  16
      }
      command{
         set -eo pipefail
@@ -360,7 +394,7 @@ task bbcms {
      runtime {
             docker: container
             memory: "120 GiB"
-	    cpu:  16
+        cpu:  16
      }
 
      command {
@@ -369,7 +403,7 @@ task bbcms {
              cat ${sep=" " input_files} > infile.fastq.gz
              export bbcms_input="infile.fastq.gz"
         fi
-	    if file --mime -b ${input_files[0]} | grep plain; then
+        if file --mime -b ${input_files[0]} | grep plain; then
              cat ${sep=" " input_files} > infile.fastq
              export bbcms_input="infile.fastq"
         fi
@@ -379,6 +413,7 @@ task bbcms {
         fi
         readlength.sh -Xmx${default="105G" memory} in=${filename_outfile} out=${filename_readlen}
         rm $bbcms_input
+        
      }
      output {
             File out = filename_outfile
@@ -389,6 +424,7 @@ task bbcms {
             File stderr = filename_errlog
             File outcounts = filename_counts
             File outkmer = filename_kmerfile
+            
      }
 }
 

From 2e334d28a3ba432ec153bd4e879a45828e792ef4 Mon Sep 17 00:00:00 2001
From: Chienchi Lo <chien-chi@pn2034281.lanl.gov>
Date: Fri, 27 Jan 2023 17:19:22 -0700
Subject: [PATCH 12/13] udpate README

---
 README.md  | 23 ++++++++++-------------
 input.json |  9 +++++----
 2 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/README.md b/README.md
index 8c605a4..f575a0d 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@ Description of the files:
 
 ## The Docker image and Dockerfile can be found here
 
-[microbiomedata/bbtools:38.94](https://hub.docker.com/r/microbiomedata/bbtools)
+[microbiomedata/bbtools:38.96](https://hub.docker.com/r/microbiomedata/bbtools)
 
 [microbiomedata/spades:3.15.0](https://hub.docker.com/r/microbiomedata/spades)
 
@@ -24,26 +24,23 @@ Description of the files:
     
 2. contig prefix for fasta header
     
-3. output path
+3. project name 
 
-4. input_interleaved (boolean)
+4. resource where run the workflow
 
-5. forwards reads fastq file (required value when input_interleaved is false, otherwise use [] )
+5. informed_by 
 
-6. reverse reads fastq file (required value when input_interleaved is false, otherwise use [] )
+6. memory (optional) ex: "jgi_metaASM.memory": "105G"
 
-7. memory (optional) ex: "jgi_metaASM.memory": "105G"
-
-8. threads (optional) ex: "jgi_metaASM.threads": "16"
+7. threads (optional) ex: "jgi_metaASM.threads": "16"
 
 ```
 {
-  "jgi_metaASM.input_file":["/global/cfs/projectdirs/m3408/ficus/11809.7.220839.TCCTGAG-ACTGCAT.fastq.gz"],
+  "jgi_metaASM.input_file":"/global/cfs/projectdirs/m3408/ficus/11809.7.220839.TCCTGAG-ACTGCAT.fastq.gz",
   "jgi_metaASM.rename_contig_prefix":"503125_160870",
-  "jgi_metaASM.outdir":"/global/cfs/projectdirs/m3408/aim2/metagenome/assembly/ficus/503125_160870",
-  "jgi_metaASM.input_interleaved":true,
-  "jgi_metaASM.input_fq1":[],
-  "jgi_metaASM.input_fq2":[],
+  "jgi_metaASM.proj":"nmdc:503125_160870",
+  "jgi_metaASM.resource": "NERSC -- perlmutter",
+  "jgi_metaASM.informed_by": "nmdc:xxxxxx",
   "jgi_metaASM.memory": "105G",
   "jgi_metaASM.threads": "16"
 }
diff --git a/input.json b/input.json
index 8ea0673..f291ba3 100755
--- a/input.json
+++ b/input.json
@@ -1,8 +1,9 @@
 {
   "jgi_metaASM.input_file":["/global/cfs/projectdirs/m3408/ficus/11809.7.220839.TCCTGAG-ACTGCAT.fastq.gz"],
   "jgi_metaASM.rename_contig_prefix":"503125_160870",
-  "jgi_metaASM.input_interleaved":true,
-  "jgi_metaASM.input_fq1":[],
-  "jgi_metaASM.input_fq2":[],
-  "jgi_metaASM.outdir":"/global/cfs/projectdirs/m3408/aim2/metagenome/assembly/ficus/503125_160870"
+  "jgi_metaASM.proj":"nmdc:503125_160870",
+  "jgi_metaASM.resource": "NERSC -- perlmutter",
+  "jgi_metaASM.informed_by": "nmdc:xxxxxx",
+  "jgi_metaASM.memory": "105G",
+  "jgi_metaASM.threads": "16"
 }

From 272967486ad1ac78d496a98c9d65d20a554fa4a7 Mon Sep 17 00:00:00 2001
From: Chienchi Lo <chien-chi@pn2034281.lanl.gov>
Date: Fri, 27 Jan 2023 17:28:59 -0700
Subject: [PATCH 13/13] fix missing make_info file direct

---
 jgi_assembly.wdl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/jgi_assembly.wdl b/jgi_assembly.wdl
index 0abd4b3..ac14ce9 100755
--- a/jgi_assembly.wdl
+++ b/jgi_assembly.wdl
@@ -121,7 +121,7 @@ task make_info_file {
         spades_version=`grep  'SPAdes version' ${assy_info} | awk '{print $3}'`
         echo -e "The workflow takes paired-end reads runs error correction by bbcms.sh (BBTools(1) version $bbtools_version)." > ${prefix}_metaAsm.info
         echo -e "The clean reads are assembled by metaSpades(2) version $spades_version with parameters, --only-assembler -k 33,55,77,99,127  --meta" >> ${prefix}_metaAsm.info
-        echo -e "After assembly, Contigs and Scaffolds are consumed by the *create_agp* task to rename the FASTA header and generate an AGP format (https://www.ncbi.nlm.nih.gov/assembly/agp/AGP_Specification/) file which describes the assembly"
+        echo -e "After assembly, Contigs and Scaffolds are consumed by the *create_agp* task to rename the FASTA header and generate an AGP format (https://www.ncbi.nlm.nih.gov/assembly/agp/AGP_Specification/) file which describes the assembly"  >> ${prefix}_metaAsm.info
         echo -e "In the end, the reads are mapped back to contigs by bbmap (BBTools(1) version $bbtools_version) for coverage information." >> ${prefix}_metaAsm.info
 
         echo -e "\n(1) B. Bushnell: BBTools software package, http://bbtools.jgi.doe.gov/" >> ${prefix}_metaAsm.info