Merge pull request #421 from microbiomedata/398-genomad-output-directory-error

398 genomad output directory error

Author: mflynn-lanl

data/workflow/WDL/metaG/viral-plasmid_tasks.wdl

@@ -3,6 +3,7 @@ version 1.0
 task geNomad_full {
     input {
         File ASM_FASTA
+        String proj_name
         String GENOMAD_DB
         String OUTDIR
         String DOCKER
@@ -25,18 +26,24 @@ task geNomad_full {
     command <<<
 
         set -eo pipefail
+        cp  ~{ASM_FASTA} ~{proj_name}
+        mkdir -p ~{OUTDIR}
         if [ ~{OPTION["default"]} == true ]; then 
-            genomad end-to-end --cleanup --splits 4 ~{ASM_FASTA} ~{OUTDIR} ~{GENOMAD_DB} \
-            && mv ~{OUTDIR}/~{prefix}_summary/ ~{GeNomad_Summary} 
+            genomad end-to-end --cleanup --splits 4 ~{proj_name} ~{OUTDIR} ~{GENOMAD_DB} \
+            && mv  ~{OUTDIR}/~{proj_name}_summary ~{GeNomad_Summary}
+
         fi
         if [ ~{OPTION["relaxed"]} == true ]; then
-            genomad end-to-end --relaxed --splits 4 ~{ASM_FASTA} ~{OUTDIR} ~{GENOMAD_DB} \
-            && mv ~{OUTDIR}/~{prefix}_summary/ ~{GeNomad_Summary} 
+            genomad end-to-end --relaxed --splits 4 ~{proj_name} ~{OUTDIR} ~{GENOMAD_DB} \
+            && mv OUTDIR/~{proj_name}_summary ~{GeNomad_Summary}
+
         fi
         if [ ~{OPTION["conservative"]} == true ]; then
-            genomad end-to-end --conservative --splits 4 ~{ASM_FASTA} ~{OUTDIR} ~{GENOMAD_DB} \
-            && mv ~{OUTDIR}/~{prefix}_summary/ ~{GeNomad_Summary} 
+            genomad end-to-end --conservative --splits 4 ~{proj_name} ~{OUTDIR} ~{GENOMAD_DB} \
+            && mv  ~{OUTDIR}/~{proj_name}_summary ~{GeNomad_Summary}
+ 
         fi
+ 
         if [ ~{OPTION["custom"]} == true ]; then
             if [ ~{calibration} == true ]; then
                 genomad end-to-end --cleanup --splits 4 --min-score ~{min_score} \
@@ -48,8 +55,8 @@ task geNomad_full {
                 --min-virus-marker-enrichment ~{min_virus_marker_enrichment} \
                 --max-uscg ~{max_uscg} \
                 --enable-score-calibration --max-fdr ~{fdr} \
-                ~{ASM_FASTA} ~{OUTDIR} ~{GENOMAD_DB} \
-                && mv ~{OUTDIR}/~{prefix}_summary/ ~{GeNomad_Summary} 
+                ~{proj_name} ~{OUTDIR} ~{GENOMAD_DB} \
+                && mv  ~{OUTDIR}/~{proj_name}_summary ~{GeNomad_Summary}
             else
                 genomad end-to-end --cleanup --splits 4 --min-score ~{min_score} \
                 --min-virus-hallmarks ~{min_virus_hallmark} \
@@ -59,28 +66,29 @@ task geNomad_full {
                 --min-plasmid-marker-enrichment ~{min_plasmid_marker_enrichment} \
                 --min-virus-marker-enrichment ~{min_virus_marker_enrichment} \
                 --max-uscg ~{max_uscg} \
-                ~{ASM_FASTA} ~{OUTDIR} ~{GENOMAD_DB} \
-                && mv ~{OUTDIR}/~{prefix}_summary/ ~{GeNomad_Summary} 
+                ~{proj_name} ~{OUTDIR} ~{GENOMAD_DB} \
+                && mv ~{OUTDIR}/~{proj_name}_summary ~{GeNomad_Summary}
             fi
         fi
-
+        
+        
     >>>
 
     output {
-    File plasmids_fasta = "~{GeNomad_Summary}/~{prefix}_plasmid.fna"
-    File plasmid_genes = "~{GeNomad_Summary}/~{prefix}_plasmid_genes.tsv"
-    File plasmid_protiens = "~{GeNomad_Summary}/~{prefix}_plasmid_proteins.faa"
-    File plasmid_summary = "~{GeNomad_Summary}/~{prefix}_plasmid_summary.tsv"
-    File virus_fasta = "~{GeNomad_Summary}//~{prefix}_virus.fna"
-    File virus_genes = "~{GeNomad_Summary}/~{prefix}_virus_genes.tsv"
-    File virus_proteins = "~{GeNomad_Summary}/~{prefix}_virus_proteins.faa"
-    File virus_summary = "~{GeNomad_Summary}/~{prefix}_virus_summary.tsv"
-    File summary_log = "~{OUTDIR}/~{prefix}_summary.log"
-    File aggregated_log = "~{OUTDIR}/~{prefix}_aggregated_classification.log" 
-    File annotate_log = "~{OUTDIR}/~{prefix}_annotate.log"
-    File provirus_log = "~{OUTDIR}/~{prefix}_find_proviruses.log"
-    File marker_log = "~{OUTDIR}/~{prefix}_marker_classification.log"
-    File nn_log = "~{OUTDIR}/~{prefix}_nn_classification.log"
+    File plasmids_fasta = "~{GeNomad_Summary}/~{proj_name}_plasmid.fna"
+    File plasmid_genes = "~{GeNomad_Summary}/~{proj_name}_plasmid_genes.tsv"
+    File plasmid_protiens = "~{GeNomad_Summary}/~{proj_name}_plasmid_proteins.faa"
+    File plasmid_summary = "~{GeNomad_Summary}/~{proj_name}_plasmid_summary.tsv"
+    File virus_fasta = "~{GeNomad_Summary}/~{proj_name}_virus.fna"
+    File virus_genes = "~{GeNomad_Summary}/~{proj_name}_virus_genes.tsv"
+    File virus_proteins = "~{GeNomad_Summary}/~{proj_name}_virus_proteins.faa"
+    File virus_summary = "~{GeNomad_Summary}/~{proj_name}_virus_summary.tsv"
+    File summary_log = "~{OUTDIR}/~{proj_name}_summary.log"
+    File aggregated_log = "~{OUTDIR}/~{proj_name}_aggregated_classification.log" 
+    File annotate_log = "~{OUTDIR}/~{proj_name}_annotate.log"
+    File provirus_log = "~{OUTDIR}/~{proj_name}_find_proviruses.log"
+    File marker_log = "~{OUTDIR}/~{proj_name}_marker_classification.log"
+    File nn_log = "~{OUTDIR}/~{proj_name}_nn_classification.log"
     }
     runtime {
         docker: DOCKER

data/workflow/WDL/metaG/viral-plasmid_wf.wdl

@@ -8,6 +8,7 @@ workflow viral {
         String genomad_db = database + '/genomad_db-v1.6'
         String checkv_db = database + '/checkv-db-v1.4'
         File fasta
+        String proj_name
         Map[String, Boolean] option
         Float? min_score
         Int? min_virus_hallmark
@@ -28,6 +29,7 @@ workflow viral {
     call tasks.geNomad_full as gn {
         input: 
             ASM_FASTA = fasta,
+            proj_name = proj_name,
             GENOMAD_DB = genomad_db,
             OPTION = option,
             min_score = min_score,

data/workflow/templates/virus_plasmid_inputs.tmpl

@@ -3,6 +3,7 @@
 "main_workflow.<WORKFLOW>_min_plasmid_hallmark": <MIN_PLASMID_HALLMARK>,
 "main_workflow.<WORKFLOW>_database": "/refdata",
 "main_workflow.<WORKFLOW>_fasta": <FASTA>,
+"main_workflow.<WORKFLOW>_proj_name": <PROJ_NAME>,
 "main_workflow.<WORKFLOW>_option": <OPTION>,
 "main_workflow.<WORKFLOW>_min_plasmid_hallmarks_short_seqs": <MIN_PLASMID_HALLMARK_SHORT_SEQS>,
 "main_workflow.<WORKFLOW>_min_virus_hallmarks_short_seqs": <MIN_VIRUS_HALLMARK_SHORT_SEQS>,

data/workflow/templates/virus_plasmid_wdl.tmpl

@@ -4,6 +4,7 @@ import "<WDL_IMPORT>" as <WORKFLOW>
 workflow main_workflow {
     input {
         String <WORKFLOW>_database
+        String <WORKFLOW>_proj_name
         File <WORKFLOW>_fasta
         Float? <WORKFLOW>_min_score
         Int? <WORKFLOW>_min_virus_hallmark
@@ -24,6 +25,7 @@ workflow main_workflow {
             input:
             database=<WORKFLOW>_database,
             fasta=<WORKFLOW>_fasta,
+            proj_name=<WORKFLOW>_proj_name,
             min_score=<WORKFLOW>_min_score,
             min_virus_hallmark=<WORKFLOW>_min_virus_hallmark,
             min_plasmid_hallmark=<WORKFLOW>_min_plasmid_hallmark,

webapp/server/crons/workflowMonitor.js

@@ -401,6 +401,7 @@ async function generateInputs(proj_home, workflow, proj) {
     } else if (workflow.name === 'virus_plasmid') {
         templInputs = templInputs.replace(/<OUTDIR>/, '"' + proj_home + "/" + workflowSettings['outdir'] + '"');
         templInputs = templInputs.replace(/<FASTA>/, JSON.stringify(workflow['input_fasta']));
+        templInputs = templInputs.replace(/<PROJ_NAME>/, '"' + proj.name + '"');
         // templInputs = templInputs.replace(/<ENABLED_MODULES>/, JSON.stringify(workflow['enabled_modules']));
         templInputs = templInputs.replace(/<MIN_SCORE>/, JSON.stringify(workflow['min_score']));
         templInputs = templInputs.replace(/<MIN_VIRUS_HALLMARK>/, JSON.stringify(workflow['min_virus_hallmark']));