merge

modules/cd_hit.nf

-
-
 process INDIVIDUAL_CD_HIT {
-  tag "${replicateId}"
+  tag "${sampleId}"
   publishDir "${params.outdir}/06_func_annot/06_1_clustering", mode: 'copy'
   label 'CD_HIT'
 
   input:
-  tuple val(replicateId), file(assembly_ffn_file)
+  tuple val(sampleId), file(assembly_ffn_file)
   val percentage_identity_cdhit
 
   output:
-  path("${replicateId}.cd-hit-est.${percentage_identity_cdhit}.fasta"), emit: clstr_fasta
-  path("${replicateId}.cd-hit-est.${percentage_identity_cdhit}.table_cluster_contigs.txt"), emit: individual_clstr_table
-  path("${replicateId}.cd-hit-est.${percentage_identity_cdhit}.fasta.clstr")
+  path("${sampleId}.cd-hit-est.${percentage_identity_cdhit}.fasta"), emit: clstr_fasta
+  path("${sampleId}.cd-hit-est.${percentage_identity_cdhit}.table_cluster_contigs.txt"), emit: individual_clstr_table
+  path("${sampleId}.cd-hit-est.${percentage_identity_cdhit}.fasta.clstr")
 
   // when: ('06_func_annot' in step)
 
   script:
   """
-  cd-hit-est -c ${percentage_identity_cdhit} -i ${assembly_ffn_file} -o ${replicateId}.cd-hit-est.${percentage_identity_cdhit}.fasta -T ${task.cpus} -M ${task.mem} -d 150
-  cat ${replicateId}.cd-hit-est.${percentage_identity_cdhit}.fasta.clstr | cd_hit_produce_table_clstr.py > ${replicateId}.cd-hit-est.${percentage_identity_cdhit}.table_cluster_contigs.txt
+  cd-hit-est -c ${percentage_identity_cdhit} -i ${assembly_ffn_file} -o ${sampleId}.cd-hit-est.${percentage_identity_cdhit}.fasta -T ${task.cpus} -M ${task.mem} -d 150
+  cat ${sampleId}.cd-hit-est.${percentage_identity_cdhit}.fasta.clstr | cd_hit_produce_table_clstr.py > ${sampleId}.cd-hit-est.${percentage_identity_cdhit}.table_cluster_contigs.txt
   """
 }
 

modules/feature_counts.nf

 
 // Quantification of reads on each gene in each sample.
-process quantification {
-   tag "${replicateId}"
+process QUANTIFICATION {
+   tag "${sampleId}"
    publishDir "${params.outdir}/06_func_annot/06_2_quantification", mode: 'copy'
 
    input:
-   tuple val(replicateId), file(gff_prokka), file(bam), file(bam_index)
+   tuple val(sampleId), file(gff_prokka), file(bam), file(bam_index)
 
    output:
-   path "${replicateId}.featureCounts.tsv", emit: count_table
-   path "${replicateId}.featureCounts.tsv.summary", emit: summary
-   path "${replicateId}.featureCounts.stdout"
-
-   // when: ('06_func_annot' in step)
+   path "${sampleId}.featureCounts.tsv", emit: count_table
+   path "${sampleId}.featureCounts.tsv.summary", emit: summary
+   path "${sampleId}.featureCounts.stdout"
 
    script:
    """
-   featureCounts -T ${task.cpus} -p -O -t gene -g ID -a ${gff_prokka} -o ${replicateId}.featureCounts.tsv ${bam} &> ${replicateId}.featureCounts.stdout
+   featureCounts -T ${task.cpus} -p -O -t gene -g ID -a ${gff_prokka} -o ${sampleId}.featureCounts.tsv ${bam} &> ${sampleId}.featureCounts.stdout
    """
 }
 
@@ -43,8 +41,6 @@ process quantification {
    """
  }
  
- 
- 
  workflow FEATURE_COUNTS {
    
  take:

nextflow.config

@@ -18,7 +18,8 @@ params {
     metaspades_mem = 440
     min_contigs_cpm = 1000
     diamond_bank = ""
-    
+    percentage_identity = 0.95
+
     // Skip step or sub-step.
     skip_clean = false
     skip_sickle = false

subworkflows/06_functionnal_annot.nf

+include { CD_HIT } from '../modules/cd_hit'
+//include {FEATURE_COUNTS} from './modules/feature_counts'
+// cd_hit + quantification + quantification_table + eggnog_mapper_db + eggnog_mapper 
+// + best_hit_diamond + mergeçquandtif and functionnal annot + make_functionnal_annotation_tables
+
+workflow STEP_06_FUNC_ANNOT {
+    take:
+        assembly_ch // channel: [ val(sampleid), path(assemblyfasta) ]
+	main:
+        CD_HIT(assembly_ch, params.percentage_identity)
+    }

subworkflows/shared.nf

@@ -2,7 +2,7 @@
 include { FILTERED_QUAST } from '../modules/metaquast'
 include { STEP_04_STRUCTURAL_ANNOT } from './04_structural_annot'
 include { STEP_05_ALIGNMENT } from './05_alignment'
-
+include { STEP_06_FUNC_ANNOT } from './06_functionnal_annot'
 
 workflow SHARED {
 	take:
@@ -10,25 +10,24 @@ workflow SHARED {
         ch_assembly
         
 	main:
-        FILTERED_QUAST (
-    		ch_assembly
-    	)
-
-        ch_prokka_and_reads = Channel.empty()
-        ch_faa = Channel.empty()
-        if ( ! params.skip_structural_annot ) {
-            STEP_04_STRUCTURAL_ANNOT ( ch_assembly )
-            ch_gff = STEP_04_STRUCTURAL_ANNOT.out.gff
-            ch_fna = STEP_04_STRUCTURAL_ANNOT.out.fna
-            ch_faa = STEP_04_STRUCTURAL_ANNOT.out.faa
-
-            ch_prokka_and_reads = ch_gff.join(ch_fna, remainder: true).join(ch_reads, remainder: true)
-        }
-        
-        if ( ! params.skip_alignment) {
-            STEP_05_ALIGNMENT( ch_prokka_and_reads, ch_faa )
-        }
 
+    FILTERED_QUAST (
+		ch_assembly
+	)
+    ch_prokka_reads = Channel.empty()
+    ch_prokka_faa = Channel.empty()
+    if ( ! params.skip_structural_annot ) {
+        PROKKA_AND_RENAME (ch_assembly)
+        ch_prokka_reads = PROKKA_AND_RENAME.out.gff.join(PROKKA_AND_RENAME.out.fna, remainder: true).join(ch_reads, remainder: true)
+        ch_prokka_faa = PROKKA_AND_RENAME.out.faa
+    }
+    if ( ! params.skip_alignment) {
+        STEP_05_ALIGNMENT(ch_prokka_reads, ch_prokka_faa)
+    }
+    if ( ! params.skip_func_annot) {
+        STEP_06_FUNC_ANNOT(PROKKA_AND_RENAME.out.fna)
+    }
+    
 	emit:
         report_prokka = STEP_04_STRUCTURAL_ANNOT.out.report
     	report_quast = FILTERED_QUAST.out.report