Biobakery 4

aws-params.yaml

@@ -1,8 +1,8 @@
 readsdir: "s3://vkc-nextflow/rawfastq/"
 outdir: "s3://vkc-nextflow/output/"
 human_genome: "s3://biobakery-databases/kneaddata_databases/"
-metaphlan_db: "s3://biobakery-databases/metaphlan_databases/"
+metaphlan_db: "s3://biobakery-databases/metaphlan_v4_databases/"
 humann_bowtie_db: "s3://biobakery-databases/humann_databases/chocophlan"
 humann_protein_db: "s3://biobakery-databases/humann_databases/uniref"
 humann_utility_db: "s3://biobakery-databases/humann_databases/utility_mapping"
-filepattern: "*_L00{1,2,3,4}_R{1,2}_001.fastq.gz"
+filepattern: "*_L00{1,2,3,4}_R{1,2}_001.fastq.gz"

main.nf

@@ -14,14 +14,8 @@ workflow {
 
     human_genome      = params.human_genome
     metaphlan_db      = params.metaphlan_db
-    humann_bowtie_db  = params.humann_bowtie_db
-    humann_protein_db = params.humann_protein_db
-    humann_utility_db = params.humann_utility_db
 
     knead_out     = kneaddata(read_pairs_ch, human_genome)
     metaphlan_out = metaphlan(knead_out[0], knead_out[1], metaphlan_db)
     metaphlan_bzip = metaphlan_bzip(metaphlan_out[0], metaphlan_out[4])
-    humann_out    = humann(metaphlan_out[0], metaphlan_out[1], metaphlan_out[2], humann_bowtie_db, humann_protein_db)
-    regroup_out   = humann_regroup(humann_out[0], humann_out[1], humann_utility_db)
-    humann_rename(regroup_out, humann_utility_db)
 }

metaphlan_only.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+nextflow.enable.dsl=2
+
+include { metaphlan; metaphlan_bzip } from './processes/metaphlan.nf'
+
+workflow {
+
+    read_pairs_ch = Channel
+        .fromFilePairs(
+            [ "$params.readsdir/$params.filepattern",
+              "$params.readsdir/*_kneaddata.fastq.gz" ],
+            size:-1)
+
+    metaphlan_db      = params.metaphlan_db
+
+    metaphlan_out = metaphlan(read_pairs_ch, metaphlan_db)
+    metaphlan_bzip = metaphlan_bzip(metaphlan_out[0], metaphlan_out[4])
+}

processes/metaphlan.nf

@@ -3,9 +3,9 @@ process metaphlan {
     publishDir "$params.outdir/metaphlan", pattern: "{*.tsv}"
 
     input:
-    tuple val(sample), path(kneads)
-    path unmatched
-    path metaphlan_db
+        tuple val(sample), path(kneads)
+        path unmatched
+        path metaphlan_db
 
     output:
     val  sample                  , emit: sample
@@ -15,13 +15,9 @@ process metaphlan {
     path "${sample}.sam"
 
     script:
-    def forward = kneads[0]
-    def reverse = kneads[1]
-    def unf = unmatched[0]
-    def unr = unmatched[1]
-
+
     """
-    cat $forward $reverse $unf $unr > ${sample}_grouped.fastq.gz
+    cat $kneads > ${sample}_grouped.fastq.gz
 
     metaphlan ${sample}_grouped.fastq.gz ${sample}_profile.tsv \
         --bowtie2out ${sample}_bowtie2.tsv \
@@ -49,4 +45,4 @@ process metaphlan {
     """
     bzip2 -v $sam
     """
-}
+}