preparing for main report

assets/main_report.Rmd

@@ -0,0 +1,53 @@
+---
+title: "Test report for core genome phylogeny"
+output: html_document
+date: "`r format(Sys.time(), '%d %B, %Y')`"
+params:
+  ref_meta: "/home/fosterz/files/projects/work/current/nf-core-plantpathsurveil/test/output_full/iqtree2/input_alignments.treefile"
+  core_phylo: "/media/fosterz/external_primary/files/projects/work/current/nf-core-plantpathsurveil/test/data/metadata_medium.csv"
+---
+
+```{r include=FALSE, eval=FALSE}
+params = list(
+  ref_meta = "/home/fosterz/files/projects/work/current/nf-core-plantpathsurveil/test/output_full/iqtree2/input_alignments.treefile",
+  ref_meta = "/media/fosterz/external_primary/files/projects/work/current/nf-core-plantpathsurveil/test/data/metadata_medium.csv"
+)
+```
+
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Prepare
+
+Load required libraries.
+
+```{r}
+library(ggtree)
+library(treeio)
+```
+
+
+Load metadata.
+
+```{r}
+metadata <- read.csv(params$metadata)
+metadata$sample <- paste0(metadata$sample, "_T1")
+```
+
+Load treefile.
+
+```{r}
+tree <- read.newick(params$treefile)
+```
+
+plot tree
+
+```{r}
+ggplot(tree, aes(x, y)) +
+  geom_tree() + 
+  theme_tree() +
+  geom_tiplab(as_ylab = FALSE, color = '#555555')
+```
+

modules/local/mainreport.nf

@@ -0,0 +1,41 @@
+process MAIN_REPORT {
+    tag "$group_meta.id"
+    label 'process_low'
+
+    conda "conda-forge::r-base conda-forge::r-rmarkdown conda-forge::r-yaml conda-forge::r-poppr conda-forge::r-adegenet conda-forge::r-ape conda-forge::r-readr conda-forge::r-igraph"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-31ad840d814d356e5f98030a4ee308a16db64ec5:0e852a1e4063fdcbe3f254ac2c7469747a60e361-0' :
+        'quay.io/biocontainers/mulled-v2-31ad840d814d356e5f98030a4ee308a16db64ec5:0e852a1e4063fdcbe3f254ac2c7469747a60e361-0' }"
+
+    input:
+    tuple val(group_meta), val(ref_metas), file(snp_phylos), file(ani_matrix), file(core_phylo)
+    path samp_stats
+    path ref_stats
+
+    output:
+    tuple val(ref_meta), path("*.html"), emit: html
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${group_meta.id}"
+    """
+    Rscript -e "workdir<-getwd()
+        rmarkdown::render('${projectDir}/assets/main_report.Rmd',
+        params = list(
+        ref_meta = \\\"$ref_meta\\\",
+        core_phylo = \\\"$core_phylo\\\"
+        ),
+        output_file = \\\"${prefix}_report.html\\\",
+        knit_root_dir=workdir,
+        output_dir=workdir)"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        rmarkdown: \$(Rscript -e "cat(paste(packageVersion('rmarkdown'), collapse='.'))")
+    END_VERSIONS
+    """
+}

subworkflows/local/assign_references.nf

@@ -122,5 +122,6 @@ workflow ASSIGN_REFERENCES {
 
     emit:
     sample_data     = new_sample_data   // [val(meta), [file(fastq)], val(ref_meta), file(reference), val(group_meta)]
+    ani_matrix      = SOURMASH_COMPARE.out.csv // [val(group_meta), val(csv)]
     versions        = ch_versions       // channel: [ versions.yml ]
 }

subworkflows/local/call_variants.nf

@@ -67,7 +67,7 @@ workflow CALL_VARIANTS {
     ch_versions = ch_versions.mix(VCFLIB_VCFFILTER.out.versions.toSortedList().map{it[0]}) 
 
     emit:
-    vcf      = VCFLIB_VCFFILTER.out.vcf        // channel: [ ref_meta, vcf ]
+    vcf      = VCFLIB_VCFFILTER.out.vcf        // channel: [ val(ref+group_meta), fil(vcf) ]
     versions = ch_versions                     // channel: [ versions.yml ]
 }
 

subworkflows/local/core_genome_phylogeny.nf

@@ -52,6 +52,7 @@ workflow CORE_GENOME_PHYLOGENY {
 
     emit:
     pirate_aln      = PIRATE.out.aln        // channel: [ ref_meta, align_fasta ]
+    phylogeny       = IQTREE2.out.phylogeny // channel: [ group_meta, tree ]
 
     versions = ch_versions                     // channel: [ versions.yml ]
 }

subworkflows/local/download_references.nf

@@ -66,8 +66,9 @@ workflow DOWNLOAD_REFERENCES {
 
     emit:
     assem_samp_combos = genome_ids                            // [ val(genome_id), val(meta) ] for each assembly/sample combination
-    sequence          = DOWNLOAD_ASSEMBLIES.out.sequence      // [ val(genome_id), file(fna) ] for each assembly
-    gff               = MAKEGFFWITHFASTA.out.gff              // [ val(genome_id), file(gff) ] for each assembly
-    signatures        = SOURMASH_SKETCH_GENOME.out.signatures // [ val(genome_id), file(signature) ] for each assembly
-    versions          = ch_versions                           // [ versions.yml ]
+    sequence   = DOWNLOAD_ASSEMBLIES.out.sequence      // [ val(genome_id), file(fna) ] for each assembly
+    gff        = MAKEGFFWITHFASTA.out.gff              // [ val(genome_id), file(gff) ] for each assembly
+    signatures = SOURMASH_SKETCH_GENOME.out.signatures // [ val(genome_id), file(signature) ] for each assembly
+    stats      = MERGE_ASSEMBLIES.out.merged_stats.map { it[1] }     // [ file(stats) ]
+    versions   = ch_versions                           // [ versions.yml ]
 }

subworkflows/local/variant_calling_analysis.nf

@@ -57,6 +57,9 @@ workflow VARIANT_CALLING_ANALYSIS {
     samtools_fai = MAKE_REFERENCE_INDEX.out.samtools_fai
     samtools_gzi = MAKE_REFERENCE_INDEX.out.samtools_gzi
     bwa_index    = MAKE_REFERENCE_INDEX.out.bwa_index 
+    phylogeny    = IQTREE2_SNP.out.phylogeny                                        
+                       .map { [it[0].group, it[0].ref, it[1]] }        // channel: [ group_meta, ref_meta, tree ]
+
     versions = ch_versions                           // channel: [ versions.yml ]
 
 }

workflows/plantpathsurveil.nf

@@ -47,6 +47,7 @@ include { DOWNLOAD_REFERENCES      } from '../subworkflows/local/download_refere
 include { ASSIGN_REFERENCES        } from '../subworkflows/local/assign_references'
 include { GENOME_ASSEMBLY          } from '../subworkflows/local/genome_assembly'
 
+include { MAIN_REPORT              } from '../modules/local/mainreport'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -142,29 +143,19 @@ workflow PLANTPATHSURVEIL {
     //READ2TREE_ANALYSIS (
     //)
 
+    // Create main summary report
+    report_in = VARIANT_CALLING_ANALYSIS.out.phylogeny // [ group_meta, ref_meta, tree ]
+        .groupTuple() // [ group_meta, [ref_meta], [tree] ]
+        .join(ASSIGN_REFERENCES.out.ani_matrix) // [ group_meta, [ref_meta], [tree], ani_matrix ]
+        .join(CORE_GENOME_PHYLOGENY.out.phylogeny, remainder: true) // [ group_meta, [ref_meta], [snp_tree], ani_matrix, core_tree ]
+        .map { it + [ch_input, ASSIGN_REFERENCES.out.stats] }.view()
+
+    MAIN_REPORT ( 
+        report_in,
+        ch_input,
+        DOWNLOAD_REFERENCES.out.stats.first()
+    )  
 
-
-    //COARSE_SAMPLE_TAXONOMY.out.kingdom
-    //.join(COARSE_SAMPLE_TAXONOMY.out.hits)
-    //.join(INPUT_CHECK.out.reads_and_ref)
-    //.branch {
-    //    bacteria: it[1] == "Bacteria"
-    //    eukaryote: it[1] == "Eukaryota"
-    //    unknown: true 
-    //}
-    //.set { subpipeline_input }
-    //
-    //BACTERIAPIPELINE (
-    //    subpipeline_input.bacteria,
-    //    ch_input
-    //)
-    //ch_versions = ch_versions.mix(BACTERIAPIPELINE.out.versions)
-    //EUKARYOTEPIPELINE (
-    //    subpipeline_input.eukaryote,
-    //    ch_input
-    //)
-    //ch_versions = ch_versions.mix(EUKARYOTEPIPELINE.out.versions)
-
     // Save version info
     CUSTOM_DUMPSOFTWAREVERSIONS (                                               
         ch_versions.unique().collect(sort:true)