prokka2tsv

nf-core · Apr 8, 2024 · 821f2bd · 821f2bd
1 parent ae70e71
commit 821f2bd
Show file tree

Hide file tree

Showing 3 changed files with 75 additions and 0 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -63,6 +63,14 @@ process {
         ]
     }
 
+    withName: PROKKAGFF2TSV {
+        publishDir = [
+            path: { "${params.outdir}/summary_tables" },
+            mode: params.publish_dir_mode,
+            pattern: "*.prokka-annotations.tsv.gz"
+        ]
+    }
+
     withName: 'GENOMEINDEX' {
         publishDir = [
             enabled: false

diff --git a/modules/local/prokkagff2tsv.nf b/modules/local/prokkagff2tsv.nf
@@ -0,0 +1,62 @@
+process PROKKAGFF2TSV {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "conda-forge::r-tidyverse=2.0.0 conda-forge::r-dtplyr=1.3.1 conda-forge::r-data.table=1.14.8"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-b2ec1fea5791d428eebb8c8ea7409c350d31dada:a447f6b7a6afde38352b24c30ae9cd6e39df95c4-1' :
+        'biocontainers/mulled-v2-b2ec1fea5791d428eebb8c8ea7409c350d31dada:a447f6b7a6afde38352b24c30ae9cd6e39df95c4-1' }"
+
+    input:
+    tuple val(meta), path(gff)
+
+    output:
+    tuple val(meta), path("*.prokka-annotations.tsv.gz"), emit: tsv
+    path "versions.yml"                          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    #!/usr/bin/env Rscript
+
+    library(data.table)
+    library(dtplyr)
+    library(dplyr)
+    library(tidyr)
+    library(readr)
+    library(stringr)
+
+    fread(
+        cmd = "zgrep -P '\\t' $gff",
+        col.names = c('contig', 'gene_caller', 'feature', 'start', 'end', 'a', 'strand', 'b', 'c')
+    ) %>%
+        separate_rows(c, sep = ';') %>%
+        separate(c, c('k', 'v'), sep = '=') %>%
+        pivot_wider(names_from = k, values_from = v) %>%
+        select(-a, -b) %>%
+        rename(orf = ID) %>%
+        rename_all(str_to_lower) %>%
+        relocate(sort(colnames(.)[8:ncol(.)]), .after = 7) %>%
+        relocate(orf) %>%
+        as.data.table() %>%
+        write_tsv("${prefix}.prokka-annotations.tsv.gz")
+
+    writeLines(
+        c(
+            "\\"${task.process}\\":",
+            paste0("    R: ", paste0(R.Version()[c("major","minor")], collapse = ".")),
+            paste0("    data.table: ", packageVersion("data.table")),
+            paste0("    dtplyr: "    , packageVersion("dtplyr")),
+            paste0("    dplyr: "     , packageVersion("dplyr")),
+            paste0("    tidyr: "     , packageVersion("tidyr")),
+            paste0("    readr: "     , packageVersion("readr"))
+        ),
+        "versions.yml"
+    )
+    """
+}
diff --git a/subworkflows/local/concatenate_gff.nf b/subworkflows/local/concatenate_gff.nf
@@ -6,6 +6,7 @@ include { CAT_CAT as FIRST_CAT  } from '../../modules/nf-core/cat/cat'
 include { CAT_CAT as SECOND_CAT } from '../../modules/nf-core/cat/cat'
 include { GENOMEINDEX           } from '../../modules/local/genomeindex'
 include { CAT_CAT as GINDEX_CAT } from '../../modules/nf-core/cat/cat'
+include { PROKKAGFF2TSV         } from '../../modules/local/prokkagff2tsv'
 
 workflow CAT_GFFS {
     take: ch_genome_gffs
@@ -31,8 +32,12 @@ workflow CAT_GFFS {
         GINDEX_CAT(GENOMEINDEX.out.genomes2id.collect().map { [ [id: 'genomes_index'], it ] })
         ch_versions = ch_versions.mix(GINDEX_CAT.out.versions)
 
+        PROKKAGFF2TSV(SECOND_CAT.out.file_out)
+        ch_versions = ch_versions.mix(PROKKAGFF2TSV.out.versions)
+
     emit:
     gff      = SECOND_CAT.out.file_out
     gindex   = GINDEX_CAT.out.file_out
+    gfftsv   = PROKKAGFF2TSV.out.tsv
     versions = ch_versions
 }