Updates to complete skeleton of pipeline

sanger-tol · Aug 9, 2024 · 56760f8 · 56760f8
1 parent 2470082
commit 56760f8
Show file tree

Hide file tree

Showing 5 changed files with 56 additions and 74 deletions.
diff --git a/assets/test.yaml b/assets/test.yaml
@@ -1,6 +1,6 @@
 assembly_id: Oscheius_DF5033
-reference_hap1: /nfs/users/nfs_d/dp24/sanger-tol-ear/test.fa
-reference_hap2: /nfs/users/nfs_d/dp24/sanger-tol-ear/test.fa
+reference_hap1: /nfs/treeoflife-01/teams/tola/users/dp24/ascc/asccTinyTest_V2/assembly/pyoelii_tiny_testfile_with_adapters.fa
+reference_hap2: /nfs/treeoflife-01/teams/tola/users/dp24/ascc/asccTinyTest_V2/assembly/pyoelii_tiny_testfile_with_adapters.fa
 longread:
   type: hifi
   dir: /lustre/scratch123/tol/resources/treeval/treeval-testdata/TreeValSmallData/Oscheius_DF5033/genomic_data/nxOscSpes1/pacbio/fasta/

diff --git a/conf/modules.config b/conf/modules.config
@@ -30,4 +30,12 @@ process {
         ext.prefix      = { "${meta.id}_sorted"}
     }
 
+    withName: SANGER_TOL_BTK {
+        ext.args            = "--blastx_outext 'txt'"
+        ext.executor        = "bsub -Is -tty -e test.e -o test.log -n 2 -q oversubscribed -M1400 -R'select[mem>1400] rusage[mem=1400] span[hosts=1]'"
+        ext.profiles        = "singularity,sanger"
+        ext.get_versions    = "lsid | head -n1 | cut -d ',' -f 1"
+        ext.version         = "draft_assemblies"
+    }
+
 }
diff --git a/modules/local/sanger_tol_btk.nf b/modules/local/sanger_tol_btk.nf
@@ -17,44 +17,41 @@ process SANGER_TOL_BTK {
     val gca_accession
 
     output:
-    tuple val(meta), path("${meta.id}_btk_out/blobtoolkit/draft"),  emit: dataset
-    path("${meta.id}_btk_out/blobtoolkit/plots"),                   emit: plots
-    path("${meta.id}_btk_out/blobtoolkit/draft/summary.json.gz"),   emit: summary_json
-    path("${meta.id}_btk_out/busco"),                               emit: busco_data
-    path("${meta.id}_btk_out/multiqc"),                             emit: multiqc_report
-    path("blobtoolkit_pipeline_info"),                              emit: pipeline_info
-    path "versions.yml",                                            emit: versions
+    tuple val(meta), path("${meta.id}_btk_out/blobtoolkit/REFERENCE"),      emit: dataset
+    path("${meta.id}_btk_out/blobtoolkit/plots"),                           emit: plots
+    path("${meta.id}_btk_out/blobtoolkit/REFERENCE/summary.json.gz"),     emit: summary_json
+    path("${meta.id}_btk_out/busco"),                                       emit: busco_data
+    path("${meta.id}_btk_out/multiqc"),                                     emit: multiqc_report
+    path("blobtoolkit_pipeline_info"),                                      emit: pipeline_info
+    path "versions.yml",                                                    emit: versions
 
     script:
-    def prefix              =   task.ext.prefix         ?:  "${meta.id}"
     def args                =   task.ext.args           ?:  ""
     def executor            =   task.ext.executor       ?:  ""
     def profiles            =   task.ext.profiles       ?:  ""
     def get_version         =   task.ext.version_data   ?:  "UNKNOWN - SETTING NOT SET"
     def btk_config          =   btk_config_file         ? "-c $btk_config_file"         : ""
-    def pipeline_version    =   task.ext.version        ?: "main"
+    def pipeline_version    =   task.ext.version        ?: "draft_assemblies"
     // YAML used to avoid the use of GCA accession number
     //    https://github.com/sanger-tol/blobtoolkit/issues/77
 
     // Seems to be an issue where a nested pipeline can't see the files in the same directory
     // Running realpath gets around this but the files copied into the folder are
-    // now just wasted space.
+    // now just wasted space. Should be fixed with using Mahesh's method of nesting but
+    // this is proving a bit complicated with BTK
 
     // outdir should be an arg
 
-    //        --accession draft \\
-
-    // blastx and blastp use the same database hence the StageAs
+    // blastx and blastp can use the same database hence the StageAs
 
 
     """
     $executor 'nextflow run sanger-tol/blobtoolkit \\
         -r $pipeline_version \\
         -profile  $profiles \\
         --input "\$(realpath $samplesheet_csv)" \\
-        --outdir ${prefix}_btk_out \\
-        --fasta "\$(realpath REFERENCE.fa)" \\
-        --yaml "\$(realpath BTK.yaml)" \\
+        --outdir ${meta.id}_btk_out \\
+        --fasta ./REFERENCE.fa \\
         --busco_lineages $busco_lineages \\
         --taxon $taxon \\
         --taxdump "\$(realpath $tax_dump)" \\
@@ -64,7 +61,7 @@ process SANGER_TOL_BTK {
         $btk_config \\
         $args'
 
-    mv ${prefix}_btk_out/pipeline_info blobtoolkit_pipeline_info
+    mv ${meta.id}_btk_out/pipeline_info blobtoolkit_pipeline_info
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -75,27 +72,26 @@ process SANGER_TOL_BTK {
     """
 
     stub:
-    def prefix              =   task.ext.prefix         ?:  "${meta.id}"
-    def pipeline_version    =   task.ext.version        ?: "main"
+    def pipeline_version    =   task.ext.version        ?: "draft_assemblies"
 
     """
-    mkdir -p ${prefix}_btk_out/blobtoolkit/$gca_accession
-    touch ${prefix}_btk_out/blobtoolkit/$gca_accession/test.json.gz
+    mkdir -p ${meta.id}_btk_out/blobtoolkit/${meta.id}_out
+    touch ${meta.id}_btk_out/blobtoolkit/${meta.id}_out/test.json.gz
 
-    mkdir ${prefix}_btk_out/blobtoolkit/plots
-    touch ${prefix}_btk_out/blobtoolkit/plots/test.png
+    mkdir ${meta.id}_btk_out/blobtoolkit/plots
+    touch ${meta.id}_btk_out/blobtoolkit/plots/test.png
 
-    mkdir ${prefix}_btk_out/busco
-    touch ${prefix}_btk_out/busco/test.batch_summary.txt
-    touch ${prefix}_btk_out/busco/test.fasta.txt
-    touch ${prefix}_btk_out/busco/test.json
+    mkdir ${meta.id}_btk_out/busco
+    touch ${meta.id}_btk_out/busco/test.batch_summary.txt
+    touch ${meta.id}_btk_out/busco/test.fasta.txt
+    touch ${meta.id}_btk_out/busco/test.json
 
-    mkdir ${prefix}_btk_out/multiqc
-    mkdir ${prefix}_btk_out/multiqc/multiqc_data
-    mkdir ${prefix}_btk_out/multiqc/multiqc_plots
-    touch ${prefix}_btk_out/multiqc/multiqc_report.html
+    mkdir ${meta.id}_btk_out/multiqc
+    mkdir ${meta.id}_btk_out/multiqc/multiqc_data
+    mkdir ${meta.id}_btk_out/multiqc/multiqc_plots
+    touch ${meta.id}_btk_out/multiqc/multiqc_report.html
 
-    mv ${prefix}_btk_out/pipeline_info blobtoolkit_pipeline_info
+    mv ${meta.id}_btk_out/pipeline_info blobtoolkit_pipeline_info
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/subworkflows/local/yaml_input.nf b/subworkflows/local/yaml_input.nf
@@ -86,14 +86,14 @@ workflow YAML_INPUT {
     //
     // LOGIC: Building BlobToolKit specific channels
     //
-    btk_nt_database         = Channel.of([inputs.assembly_id], inputs.btk.nt_database)
+    btk_nt_database         = Channel.of(inputs.btk.nt_database)
     btk_nt_database_prefix  = Channel.of(inputs.btk.nt_database_prefix)
-    btk_nt_diamond_database = Channel.of(inputs.btk.diamond_nt_database_path)
+    btk_nt_diamond_database = Channel.of(inputs.btk.diamond_nr_database_path)
     btk_un_diamond_database = Channel.of(inputs.btk.diamond_uniprot_database_path)
     btk_ncbi_taxonomy_path  = Channel.of(inputs.btk.ncbi_taxonomy_path)
     btk_ncbi_lineage_path   = Channel.of(inputs.btk.ncbi_rankedlineage_path)
     btk_yaml                = Channel.of(inputs.btk.btk_yaml)
-    btk_taxid               = Channel.of([inputs.assembly_id], inputs.btk.taxid)
+    btk_taxid               = Channel.of(inputs.btk.taxid)
     btk_gca_accession       = Channel.of(inputs.btk.gca_accession)
     busco_lineages          = Channel.of(inputs.btk.lineages)
 

diff --git a/workflows/ear.nf b/workflows/ear.nf
@@ -134,8 +134,6 @@ workflow EAR {
         )
         ch_versions = ch_versions.mix(SE_MAPPING.out.versions)
 
-        SE_MAPPING.out.mapped_bam.view()
-
         ch_align_bam
             .mix( SE_MAPPING.out.mapped_bam )
             .set { merged_bam }
@@ -156,8 +154,6 @@ workflow EAR {
             .set { merged_bam }
     }
 
-    merged_bam.view()
-
     //
     // MODULE: SORT MAPPED BAM
     //
@@ -172,56 +168,38 @@ workflow EAR {
     //
     YAML_INPUT.out.sample_id
         .combine(merged_bam)
-        .map{ sample_id, pacbio_path ->
+        .map{ sample_id, pacbio_meta, pacbio_path ->
             tuple(  [id: sample_id],
                     pacbio_path
             )
         }
-        .set { samplesheet_input }
+        .set { mapped_bam }
 
 
     GENERATE_SAMPLESHEET(
-        samplesheet_input
+        mapped_bam
     )
+    ch_versions = ch_versions.mix( GENERATE_SAMPLESHEET.out.versions )
 
     //
     // MODULE: Run Sanger-ToL/BlobToolKit
-    //         - This was built using: https://github.com/mahesh-panchal/nf-cascade
     //
-
-    // BLOBTOOLKIT(
-    //     "sanger-tol/blobtoolkit",
-    //     [
-    //         "-r 0.5.0",
-    //         "--input",
-    //         GENERATE_SAMPLESHEET.out.csv,
-    //         "--fasta",
-    //         reference,
-    //         "--yaml",
-    //         btk_yaml,
-    //         "-taxon",
-    //         btk_taxon,
-    //         "--taxdump",
-    //         btk_taxdump,
-    //         "--blastp",
-    //         btk_blastp,
-    //         "--blastn",
-    //         btk_blastn,
-    //         "--blastx",
-    //         btk_uniprot,
-    //         "-profile singularity,sanger"
-    //     ].join(" ").trim(),                                                                 // workflow opts
-    //     Channel.value([]),//readWithDefault( params.demo.params_file, Channel.value([]) ),  // params file
-    //     Channel.value([]),//readWithDefault( params.demo.input, Channel.value([]) ),        // samplesheet
-    //     Channel.value([])//readWithDefault( params.demo.add_config, Channel.value([]) ),    // custom config
-    // )
+    YAML_INPUT.out.reference_hap1.view{ it -> "Reference: $it"}
+    mapped_bam.view{ it -> "samplesheet: $it"}
+    GENERATE_SAMPLESHEET.out.csv.view{ it -> "samplesheetcsv: $it"}
+    YAML_INPUT.out.btk_un_diamond_database.view{ it -> "un diamond: $it"}
+    YAML_INPUT.out.btk_nt_database.view{ it -> "nt diamond: $it"}
+    YAML_INPUT.out.btk_ncbi_taxonomy_path.view{ it -> "Taxdump: $it"}
+    YAML_INPUT.out.btk_yaml.view{ it -> "btk_yaml: $it"}
+    YAML_INPUT.out.busco_lineages.view{ it -> "lineages: $it"}
+    YAML_INPUT.out.btk_taxid.view{ it -> "TAXID: $it"}
 
     SANGER_TOL_BTK (
         YAML_INPUT.out.reference_hap1,
-        samplesheet_input,
+        mapped_bam,
         GENERATE_SAMPLESHEET.out.csv,
         YAML_INPUT.out.btk_un_diamond_database,
-        YAML_INPUT.out.btk_nt_diamond_database,
+        YAML_INPUT.out.btk_nt_database,
         YAML_INPUT.out.btk_un_diamond_database,
         [],
         YAML_INPUT.out.btk_ncbi_taxonomy_path,