Merge pull request #102 from nf-core/genome_ideogram

Aded BUSCO ideogram for ``GENOME`` mode

bin/plot_markers1.R

@@ -0,0 +1,52 @@
+#!/usr/bin/env Rscript
+
+# Modified from https://gitlab.com/ezlab/busco_protocol/-/blob/main/support_protocol2/plot_markers/scripts/plot_markers1.R?ref_type=heads
+
+# load libraries
+require(RIdeogram)
+
+args <- commandArgs(trailingOnly = TRUE)
+file_name_for_karyotype <- args[1]
+out_name <- args[2] # how to name the karyotype
+
+##### karyotype-------
+karyotype1 <- read.csv(file=file_name_for_karyotype, sep="\t", header = FALSE, stringsAsFactors = F)
+karyotype1$start <- 1
+karyotype1$genome <- out_name
+karyotype1$size <- 12
+karyotype1$color <- "25252"
+
+# fix columns names
+colnames(karyotype1) <- c("Chr", "End", "Start", "species", "size", "color")
+# reorder columns
+karyotype <- karyotype1[, c(1,3,2,4,5,6)]
+
+# debugging code
+print("Karyotype table\n")
+head(karyotype)
+
+write.table(karyotype, file = paste0(out_name, "_karyotype.txt"), quote = FALSE, row.names = FALSE, col.names = TRUE, sep = "\t")
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

conf/modules.config

@@ -151,9 +151,17 @@ process {
         ]
     }
 
-    withName: 'PLOT_BUSCO_IDEOGRAM' {
+    withName: 'GENOME_ANNOTATION_BUSCO_IDEOGRAM' {
         publishDir = [
-            path: { "${params.outdir}/busco_ideogram" },
+            path: { "${params.outdir}/genome_annotation_busco_ideogram" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'GENOME_ONLY_BUSCO_IDEOGRAM' {
+        publishDir = [
+            path: { "${params.outdir}/genome_busco_ideogram" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]

modules/local/plot_busco_ideogram.nf → modules/local/genome_annotation_busco_ideogram.nf

@@ -1,4 +1,4 @@
-process PLOT_BUSCO_IDEOGRAM {
+process GENOME_ANNOTATION_BUSCO_IDEOGRAM {
     tag "${genusspeci}_${lineage}"
     label 'process_single'
 

modules/local/genome_only_busco_ideogram.nf

@@ -0,0 +1,41 @@
+process GENOME_ONLY_BUSCO_IDEOGRAM {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::r-rideogram=0.2.2 bioconda::r-svglite=2.1.1"
+    container "community.wave.seqera.io/library/seqkit_r-dplyr_r-optparse_r-readr_pruned:92b750716d244919"
+
+    input:
+    tuple val(meta), path(genome), path(busco_full_table)
+
+    output:
+    tuple val(meta), path("*.svg"), emit: svg
+    tuple val(meta), path("*.png"), emit: png
+    path "versions.yml"           , emit: versions
+
+    script:
+    def args   = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    grep -v "#" ${busco_full_table} | cut -f 2,3,4,5  | grep -v "Missing" > ${prefix}_busco_coordinates.txt
+
+    # Get chromosome lengths:
+    seqkit fx2tab -i -n -l ${genome} > ${prefix}_for_karyotype.txt
+
+    # Call script for table wrangling
+    plot_markers1.R ${prefix}_for_karyotype.txt ${prefix}
+
+    # Call script for plotting
+    plot_busco_ideogram.R \\
+        --busco_output ${prefix}_busco_coordinates.txt \\
+        --karyotype ${prefix}_karyotype.txt \\
+        --prefix ${prefix} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        r-base: \$(Rscript -e "cat(as.character(getRversion()))")
+        r-rideogram: \$(Rscript -e "cat(as.character(packageVersion('RIdeogram')))")
+    END_VERSIONS
+    """
+}

modules/nf-core/busco/busco/main.nf

@@ -4,8 +4,8 @@ process BUSCO_BUSCO {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/busco:5.7.1--pyhdfd78af_0':
-        'biocontainers/busco:5.7.1--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/busco:5.8.0--pyhdfd78af_0':
+        'biocontainers/busco:5.8.0--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(fasta, stageAs:'tmp_input/*')

subworkflows/local/genome_and_annotation.nf

@@ -4,7 +4,7 @@ include { LONGEST                             } from '../../modules/local/longes
 include { BUSCO_BUSCO                         } from '../../modules/nf-core/busco/busco/main'
 include { QUAST                               } from '../../modules/nf-core/quast/main'
 include { AGAT_SPSTATISTICS                   } from '../../modules/nf-core/agat/spstatistics/main'
-include { PLOT_BUSCO_IDEOGRAM                 } from '../../modules/local/plot_busco_ideogram'
+include { GENOME_ANNOTATION_BUSCO_IDEOGRAM    } from '../../modules/local/genome_annotation_busco_ideogram'
 include { GFFREAD                             } from '../../modules/nf-core/gffread/main'
 include { ORTHOFINDER                         } from '../../modules/nf-core/orthofinder/main'
 include { FASTAVALIDATOR                      } from '../../modules/nf-core/fastavalidator/main'
@@ -52,7 +52,7 @@ workflow GENOME_AND_ANNOTATION {
                  | combine(ch_gff_agat, by:0) // by:0 | Only combine when both channels share the same id
                  | combine(ch_gff_long, by:0)
                  | multiMap {
-                     meta, fasta, gff_unfilt, gff_filt ->
+                     meta, fasta, gff_unfilt, gff_filt -> // null is is probably not necessary
                          fasta      : fasta      ? tuple( meta, file(fasta)      ) : null // channel: [ val(meta), [ fasta ] ]
                          gff_unfilt : gff_unfilt ? tuple( meta, file(gff_unfilt) ) : null // channel: [ val(meta), [ gff ] ], unfiltered
                          gff_filt   : gff_filt   ? tuple( meta, file(gff_filt)   ) : null // channel: [ val(meta), [ gff ] ], filtered for longest isoform
@@ -134,8 +134,6 @@ workflow GENOME_AND_ANNOTATION {
     // MODULE: Run BUSCO
     //
 
-    //GFFREAD.out.gffread_fasta.collect().view()
-
     BUSCO_BUSCO (
         GFFREAD.out.gffread_fasta,
         "proteins", // hardcoded
@@ -182,7 +180,7 @@ workflow GENOME_AND_ANNOTATION {
                             }
                         }
 
-    PLOT_BUSCO_IDEOGRAM ( ch_plot_input )//removed this temporarily:, ch_karyotype
+    GENOME_ANNOTATION_BUSCO_IDEOGRAM ( ch_plot_input )
 
     ch_tree_data        = ch_tree_data.mix(BUSCO_BUSCO.out.batch_summary.collect { meta, file -> file })
 

subworkflows/local/genome.nf → subworkflows/local/genome_only.nf

@@ -1,22 +1,23 @@
 
 include { QUAST                               } from '../../modules/nf-core/quast/main'
 include { BUSCO_BUSCO                         } from '../../modules/nf-core/busco/busco/main'
+include { GENOME_ONLY_BUSCO_IDEOGRAM          } from '../../modules/local/genome_only_busco_ideogram'
 
-workflow GENOME {
+workflow GENOME_ONLY {
 
     take:
     ch_fasta // channel: [ val(meta), [ fasta ] ]
 
     main:
 
-    ch_versions = Channel.empty()
+    ch_versions   = Channel.empty()
 
     QUAST ( 
         ch_fasta,
         [[],[]],
         [[],[]]
     )
-    ch_versions = ch_versions.mix(QUAST.out.versions.first())
+    ch_versions   = ch_versions.mix(QUAST.out.versions.first())
 
     BUSCO_BUSCO (
         ch_fasta,
@@ -25,7 +26,17 @@ workflow GENOME {
         params.busco_lineages_path ?: [],
         params.busco_config ?: []
     )
-    ch_versions = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
+    ch_versions   = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
+    ch_full_table = BUSCO_BUSCO.out.full_table
+
+    // Combined ch_fasta and BUSCO output channel into a single channel for ideogram
+    ch_input_ideo = ch_fasta
+                  | combine(ch_full_table, by:0)
+
+
+    GENOME_ONLY_BUSCO_IDEOGRAM (
+        ch_input_ideo
+    )
 
     emit:
     quast_results         = QUAST.out.results                   // channel: [ val(meta), [tsv] ]

workflows/genomeqc.nf

@@ -10,7 +10,7 @@ include { CREATE_PATH                         } from '../modules/local/create_pa
 include { NCBIGENOMEDOWNLOAD                  } from '../modules/nf-core/ncbigenomedownload/main'
 include { PIGZ_UNCOMPRESS as UNCOMPRESS_FASTA } from '../modules/nf-core/pigz/uncompress/main'
 include { PIGZ_UNCOMPRESS as UNCOMPRESS_GFF   } from '../modules/nf-core/pigz/uncompress/main'
-include { GENOME                              } from '../subworkflows/local/genome'
+include { GENOME_ONLY                         } from '../subworkflows/local/genome_only'
 include { GENOME_AND_ANNOTATION               } from '../subworkflows/local/genome_and_annotation'
 include { MULTIQC                             } from '../modules/nf-core/multiqc/main'
 include { TREE_SUMMARY                        } from '../modules/local/tree_summary'
@@ -201,13 +201,13 @@ workflow GENOMEQC {
 
     // Run genome only or genome + gff
     if (params.genome_only) {
-        GENOME (
+        GENOME_ONLY (
             ch_input.fasta
         )
         ch_multiqc_files = ch_multiqc_files
-                         | mix(GENOME.out.quast_results.map { meta, results -> results })
-                         | mix(GENOME.out.busco_short_summaries.map { meta, txt -> txt })
-        ch_versions      = ch_versions.mix(GENOME.out.versions.first())
+                         | mix(GENOME_ONLY.out.quast_results.map { meta, results -> results })
+                         | mix(GENOME_ONLY.out.busco_short_summaries.map { meta, txt -> txt })
+        ch_versions      = ch_versions.mix(GENOME_ONLY.out.versions.first())
     } else {
         GENOME_AND_ANNOTATION (
             ch_input.fasta,