fixed parameters

nextflow.config

@@ -64,13 +64,6 @@ params {
   cleanCache = false // Default to false
 }
 
-beforeCleanup {
-    if (params.cleanCache) {
-        // Clean cache directories
-        exec "rm -rf ${cacheDir}/*"
-    }
-}
-
 env {
   ENSCODE = "${params.enscode}"
   PERL5LIB = "${params.enscode}/ensembl/modules:${params.enscode}/ensembl-analysis/modules:" +

pipelines/nextflow/modules/fetch_genome.nf

@@ -23,7 +23,6 @@ process FETCH_GENOME {
   afterScript "sleep $params.files_latency"  // Needed because of file system latency
   input:
   val gca
-  val cache_dir
 
   output:
   //tuple val(db), val(busco_dataset), path("*.fna")

pipelines/nextflow/modules/fetch_protein.nf

@@ -23,7 +23,6 @@ process FETCH_PROTEINS {
 
     input:
     val(db)
-    val cache_dir
 
     output:
     //tuple val(db), val(busco_dataset), path("*_translations.fa")

pipelines/nextflow/modules/species_metadata.nf

@@ -22,8 +22,6 @@ process SPECIES_METADATA {
 
   input:
   val dbname
-  val output_dir
-  val project
 
   output:
   stdout
@@ -60,11 +58,11 @@ process SPECIES_METADATA {
   if [ "\$BRC_ORGANISM" = "" ]; then BRC_ORGANISM=""; fi
   HAS_GENES=\$(has_any "gene")
 
-  PUBLISH_DIR=$output_dir
-  if [ $project == 'ensembl' ]; then
-    PUBLISH_DIR="$output_dir/\$SPECIES/\$GCA/\$SOURCE/"
+  PUBLISH_DIR=${params.outDir}
+  if [ ${params.project} == 'ensembl' ]; then
+    PUBLISH_DIR="${params.outDir}/\$SPECIES/\$GCA/\$SOURCE/"
   fi
-  if [ $project == 'brc' ]; then
+  if [ ${params.project} == 'brc' ]; then
     PUBLISH_DIR="$output_dir/\$BRC_COMPONENT/\$BRC_ORGANISM"
   fi
 

pipelines/nextflow/subworkflows/run_busco.nf

@@ -57,7 +57,7 @@ workflow RUN_BUSCO{
 
     // Run Busco in genome mode
     if (busco_mode.contains('genome')) {
-        genomeFile = FETCH_GENOME(db_meta.gca, params.cacheDir)
+        genomeFile = FETCH_GENOME(db_meta.gca)
         buscoGenomeOutput = BUSCO_GENOME_LINEAGE(buscoDataset, genomeFile)
         buscoGenomeSummaryFile = BUSCO_GENOME_OUTPUT(db_meta, buscoGenomeOutput, "genome", params.project)
         if (params.copyToFtp) {
@@ -70,7 +70,7 @@ workflow RUN_BUSCO{
         if (params.project == 'brc') {
             buscoDataset = buscoDataset.filter{ it[0].has_genes == "1" }   ????
         }
-        proteinFile = FETCH_PROTEINS (db_meta.name, params.cacheDir)
+        proteinFile = FETCH_PROTEINS (db_meta.name)
         buscoProteinOutput = BUSCO_PROTEIN_LINEAGE(buscoDataset, proteinFile)
         buscoProteinSummaryFile = BUSCO_PROTEIN_OUTPUT(db_meta, buscoProteinOutput, "protein", params.project)
         if (copyToFtp) {

pipelines/nextflow/subworkflows/run_ensembl_stats.nf

@@ -43,11 +43,11 @@ include { CLEANING } from '../modules/cleaning.nf'
 
 workflow RUN_ENSEMBL_STATS{
     take:                 
-    tuple val(dbname),val(db_meta), bool(apply_stats)
+    tuple val(dbname),val(db_meta)
 
     main:
 
-        statisticsFile = RUN_STATISTICS (dbname, params.cacheDir)
+        statisticsFile = RUN_STATISTICS (dbname)
         if(params.apply_stats){
         UPLOAD_STATISTICS_ON_CORE(statisticsFile, db_meta)
         }

pipelines/nextflow/subworkflows/run_omark.nf

@@ -47,13 +47,13 @@ include { CLEANING } from '../modules/cleaning.nf'
 
 workflow RUN_OMARK{
     take:                 
-    tuple val(dbname),val(db_meta), bool(copyToFtp)
+    tuple val(dbname),val(db_meta)
 
     main:
         //
         // MODULE: Get canonical protein from db
         // 
-        proteinFile = FETCH_PROTEINS (dbname, params.cacheDir)
+        proteinFile = FETCH_PROTEINS (dbname)
         //
         // MODULE: Get orthologous groups from Omamer db 
         //
@@ -64,7 +64,7 @@ workflow RUN_OMARK{
         omarkOutput = OMARK (omamerOutput)
 
         omarkSummaryFile = OMARK_OUTPUT(db_meta, omarkOutput, params.project)
-        if (copyToFtp) {
+        if (params.copyToFtp) {
             COPY_OMARK_OUTPUT(db_meta, omarkSummaryFile)
         }
 

pipelines/nextflow/workflows/main.nf

@@ -98,7 +98,7 @@ if (params.help) {
 include { RUN_BUSCO } from '../subworkflows/run_busco.nf'
 include { RUN_OMARK } from '../subworkflows/run_omark.nf'
 include { RUN_ENSEMBL_STATS } from '../subworkflows/run_ensembl_stats.nf'
-
+include { BUILD_METADATA } from '../modules/build_metadata.nf'
 include { SPECIES_METADATA } from '../modules/species_metadata.nf'
 
 /*
@@ -117,34 +117,34 @@ workflow STATISTICS{
             def gca = row[0]
             def taxon = row[1]
             def busco_mode = 'genome'
-            def copyToFtp = False
-
+            def copyToFtp = false
+            db_meta = BUILD_METADATA(gca,taxon_id)
             RUN_BUSCO(db_meta, busco_mode, copyToFtp)
             }
     }
-
-    if (params.run_busco_core) {
+    if (params.run_busco_core || params.run_omark || params.run_ensembl_stats) {
         csvData = Channel.fromPath(params.csvFile).splitCsv()
         // Get db name and its metadata
         db = csvData.flatten()
-        db_meta = SPECIES_METADATA(db, params.outDir, params.project)
+        db_meta = SPECIES_METADATA(db)
+
+        if (params.run_busco_core) {
         RUN_BUSCO(db_meta, busco_mode, params.copyToFtp)
+        }
+
+        if (params.run_omark) {
+        RUN_OMARK(db, db_meta)
+        }
+
+        if (params.run_ensembl_stats) {
+        RUN_ENSEMBL_STATS(db, db_meta)
+        }
+    }    
+    afterScript:
+    """
+    if (params.cleanCache) {
+        // Clean cache directories
+        exec "rm -rf ${params.cacheDir}/*"
     }
-
-    if (params.run_omark) {
-        csvData = Channel.fromPath(params.csvFile).splitCsv()
-        // Get db name and its metadata
-        db = csvData.flatten()
-        db_meta = SPECIES_METADATA(db, params.outDir, params.project)
-        RUN_OMARK(db, db_meta, params.copyToFtp)
-    }
-
-    if (params.run_ensembl_stats) {
-        csvData = Channel.fromPath(params.csvFile).splitCsv()
-        // Get db name and its metadata
-        db = csvData.flatten()
-        db_meta = SPECIES_METADATA(db, params.outDir, params.project)
-        RUN_ENSEMBL_STATS(db, db_meta, params.apply_stats)
-    }
-
+    """
 }