Fixes for misspelling, formatting and such

sanger-tol · Jul 25, 2023 · 1216730 · 1216730
1 parent 3c2fdb7
commit 1216730
Show file tree

Hide file tree

Showing 5 changed files with 39 additions and 9 deletions.
diff --git a/nextflow.config b/nextflow.config
@@ -183,7 +183,7 @@ report {
 }
 trace {
     enabled = true
-    file    = "${params.tracedir}/resource_trace_${trace_timestamp}.txt"
+    file    = "${params.tracedir}/pipeline_execution_${trace_timestamp}.txt"
     fields  = 'name,status,module,cpus,memory,attempt,realtime,%cpu,%mem,peak_rss'
 }
 dag {

diff --git a/subworkflows/local/hic_mapping.nf b/subworkflows/local/hic_mapping.nf
@@ -131,7 +131,10 @@ workflow HIC_MAPPING {
     SAMTOOLS_MERGE.out.bam
         .combine( reference_tuple )
         .multiMap { bam_meta, bam, ref_meta, ref_fa ->
-            input_bam:  tuple(bam_meta, bam)
+            input_bam:  tuple( [    id: bam_meta.id,
+                                    sz: file( bam ).size() ],
+                                bam
+                        )
             reference:  ref_fa
         }
         .set { pretext_input }
@@ -264,5 +267,6 @@ workflow HIC_MAPPING {
     //highres_snpshot     = SNAPSHOT_HRES.out.image
     mcool               = COOLER_ZOOMIFY.out.mcool
     hic                 = JUICER_TOOLS_PRE.out.hic
+    ch_reporting        = pretext_input.input_bam
     versions            = ch_versions.ifEmpty(null)
 }
diff --git a/subworkflows/local/longread_coverage.nf b/subworkflows/local/longread_coverage.nf
@@ -183,13 +183,15 @@ workflow LONGREAD_COVERAGE {
     //
     // LOGIC: PREPARING MERGE INPUT WITH REFERENCE GENOME AND REFERENCE INDEX
     //
+    SAMTOOLS_SORT.out.bam.view()
     SAMTOOLS_SORT.out.bam
         .combine( reference_tuple )
-        .multiMap { meta, file, ref_meta, ref ->
+        .multiMap { meta, bam, ref_meta, ref ->
                 bam_input       :   tuple(
                                         [   id          : meta.id,
+                                            sz          : bam.size(),
                                             single_end  : true  ],
-                                        file,
+                                        bam,
                                         []   // As we aren't using an index file here
                                     )
                 ref_input       :   tuple(
@@ -198,7 +200,7 @@ workflow LONGREAD_COVERAGE {
                                     )
         }
         .set { view_input }
-
+    view_input.bam_input.view()
     //
     // MODULE: EXTRACT READS FOR PRIMARY ASSEMBLY
     //
@@ -333,6 +335,7 @@ workflow LONGREAD_COVERAGE {
     ch_halfbed      = FINDHALFCOVERAGE.out.bed
     ch_maxbed       = BEDTOOLS_MERGE_MAX.out.bed
     ch_bigwig       = UCSC_BEDGRAPHTOBIGWIG.out.bigwig
+    ch_reporting    = view_input.bam_input
     versions        = ch_versions
 }
 

diff --git a/subworkflows/local/yaml_input.nf b/subworkflows/local/yaml_input.nf
@@ -113,7 +113,7 @@ workflow YAML_INPUT {
     assembly_level                   = assembly_data.level
     assembly_asmVer                  = assembly_data.asmVersion
     assembly_dbVer                   = assembly_data.dbVersion
-    assembly_gtype                   = assembly_data.gevalType
+    assembly_ttype                   = assembly_data.gevalType
 
     pacbio_reads                     = assem_reads.pacbio
     hic_reads                        = assem_reads.hic

diff --git a/workflows/treeval.nf b/workflows/treeval.nf
@@ -102,7 +102,7 @@ workflow TREEVAL {
         YAML_INPUT.out.reference
     )
 
-    ch_versions     = ch_versions.mix(GENERATE_GENOME.out.versions)
+    ch_versions     = ch_versions.mix( GENERATE_GENOME.out.versions )
 
     //
     // SUBWORKFLOW: Takes reference, channel of enzymes, my.genome, assembly_id and as file to generate
@@ -118,7 +118,7 @@ workflow TREEVAL {
         ch_enzyme,
         digest_asfile
     )
-    ch_versions     = ch_versions.mix(INSILICO_DIGEST.out.versions)
+    ch_versions     = ch_versions.mix( INSILICO_DIGEST.out.versions )
 
     //
     // SUBWORKFLOW: FOR SPLITTING THE REF GENOME INTO SCAFFOLD CHUNKS AND RUNNING SOME SUBWORKFLOWS
@@ -240,6 +240,28 @@ workflow TREEVAL {
         ch_versions.unique().collectFile(name: 'collated_versions.yml')
     )
 
+    //
+    // LOGIC: GENERATE SOME CHANNELS FOR REPORTING
+    //
+    GENERATE_GENOME.out.reference_tuple
+        .combine( YAML_INPUT.out.assembly_classT )
+        .combine( YAML_INPUT.out.assembly_ttype )
+        .map { meta, reference, lineage, ticket ->
+            tuple( [id: meta.id,
+                    sz: file(reference).size(),
+                    ln: lineage,
+                    tk: ticket ],
+                    reference
+            )
+        }
+        .set { rf_data }
+
+    pb_data = LONGREAD_COVERAGE.out.ch_reporting    // merged pacbio.bam data tuple( [ id, size ], file )
+    cm_data = HIC_MAPPING.out.ch_reporting          // merged cram.bam data tuple ( [ id, size ], file ) | Should really be a collected list of the raw cram
+    rf_data.view()
+    pb_data.view()
+    cm_data.view()
+
     emit:
     software_ch     = CUSTOM_DUMPSOFTWAREVERSIONS.out.yml
     versions_ch     = CUSTOM_DUMPSOFTWAREVERSIONS.out.versions
@@ -259,7 +281,8 @@ workflow.onComplete {
     if (params.hook_url) {
         NfcoreTemplate.IM_notification(workflow, params, summary_params, projectDir, log)
     }
-    // TreeValProject.summary(workflow, reference_tuple, summary_params, projectDir)
+
+    TreeValProject.summary(workflow, rf_data, pb_data, cm_data, summary_params, projectDir, params)
 
 }