Dev

conf/base.config

@@ -169,8 +169,8 @@ process {
         time   = { 1.h  * ( reference.size() < 1e9 ? 10 : reference.size() < 10e9 ? 30 : 48) }
     }
 
-    withName: '.*:.*:READ_COVERAGE:BEDTOOLS_GENOMECOV' {
-        memory = { 6.GB * (task.attempt * task.attempt) }
+    withName: BEDTOOLS_GENOMECOV {
+        memory = { 8.GB * (task.attempt * task.attempt) }
         time   = { 12.h * task.attempt }
     }
 
@@ -247,8 +247,8 @@ process {
             // If 100-150GB -> 50GB + (BAM/4GB)
             // If >150GB -> BAM/4GB
                 (bam.size() <= 150e9 ?
-                    50.GB + (1.GB * Math.ceil(bam.size() / 4e9)) :
-                    1.GB * Math.ceil(bam.size() / 4e9)
+                    50.GB + (1.GB * Math.ceil(bam.size() / 3e9)) :
+                    1.GB * Math.ceil(bam.size() / 3e9)
                 )
             ) * Math.ceil(task.attempt * 1)
         }
@@ -257,7 +257,7 @@ process {
 
     withName: SAMTOOLS_MARKDUP {
         cpus    = { 12   * 1 }
-        memory  = { 1.GB * Math.ceil( ( (input.size() / 1e9) / 4 ) ) * task.attempt }
+        memory  = { 1.GB * Math.ceil( ( (input.size() / 1e9) / 3 ) ) * task.attempt }
     }
 
     withName: COOLER_CLOAD {
@@ -347,7 +347,7 @@ process {
     }
 
     withName: BEDTOOLS_INTERSECT {
-        memory  = { 6.GB * (task.attempt * task.attempt) }
+        memory  = { 8.GB * (task.attempt * task.attempt) }
     }
 
     withName: GENERATE_CRAM_CSV {

docs/usage.md

@@ -445,7 +445,7 @@ work                # Directory containing the nextflow working files
 
 The TreeVal pipeline now contains a command line option for `--mode` which replaces the now depreciated `-entry` parameter.
 
-This enum param expects only one of ["FULL", "RAPID", "RAPID-TOL", "JBROWSE"].
+This enum param expects only one of ["FULL", "RAPID", "RAPID-TOL", "JBROWSE", "FULL_COMBINED"].
 
 FULL will run all subworkflows shows in all_steps_list.
 
@@ -459,10 +459,13 @@ This qualifies as: if (false && false) { run juicer } or if workflow is RAPID_TO
 
 JBROWSE, generates the data which can be ingested by JBROWSE. Useful when RAPID has been used in a previous run and you now need "the rest" of the data. This runs all subworkflows notes in jbrowse_include_list.
 
+FULL_COMBINED runs all subworkflows in combined_include_list, which includes all steps except selfcomp and gene_alignment.
+
 ```
 all_steps_list          = ["insilico_digest", "gene_alignment", "repeat_density", "gap_finder", "selfcomp", "synteny", "read_coverage", "telo_finder", "busco", "kmer", "hic_mapping", "NONE"]
 
 jbrowse_include_list    = ["insilico_digest", "gene_alignment", "selfcomp", "synteny", "busco", "kmer"]
+combined_include_list   = ["insilico_digest", "repeat_density", "gap_finder", "synteny", "read_coverage", "telo_finder", "busco", "kmer", "hic_mapping"]
 rapid_include_list      = ["repeat_density", "gap_finder", "read_coverage", "telo_finder", "hic_mapping", "kmer"]
 ```
 

nextflow_schema.json

@@ -57,8 +57,8 @@
                 },
                 "mode": {
                     "type": "string",
-                    "description": "Run mode specified (FULL, RAPID, RAPID_TOL, JBROWSE)",
-                    "enum": ["FULL", "RAPID", "RAPID_TOL", "JBROWSE"],
+                    "description": "Run mode specified (FULL, RAPID, RAPID_TOL, JBROWSE, FULL_COMBINED)",
+                    "enum": ["FULL", "RAPID", "RAPID_TOL", "JBROWSE", "FULL_COMBINED"],
                     "fa_icon": "fas fa-folder-open"
                 },
                 "run_hires": {

subworkflows/local/hic_mapping/main.nf

@@ -140,7 +140,7 @@ workflow HIC_MAPPING {
             //
             // LOGIC: MAKE YAHS INPUT
             //
-            ref_yahs.map { meta, ref -> ref }.set{ch_ref}
+            reference_tuple.map { meta, ref -> ref }.set{ch_ref}
             reference_index.map { meta, fai -> fai }.set{ch_fai}
 
             //

subworkflows/local/utils_nfcore_treeval_pipeline/main.nf

@@ -33,7 +33,7 @@ workflow PIPELINE_INITIALISATION {
     nextflow_cli_args //   array: List of positional nextflow CLI args
     outdir            //  string: The output directory where the results will be saved
     input             //  string: Path to input YAML
-    mode              //  string: Run mode, default FULL, alternatives: JBROWSE, RAPID, RAPID_TOL
+    mode              //  string: Run mode, default FULL, alternatives: JBROWSE, RAPID, RAPID_TOL, FULL_COMBINED
 
     main:
 

workflows/treeval.nf

@@ -66,36 +66,53 @@ workflow TREEVAL {
     //
     ch_versions             = Channel.empty()
 
-    exclude_steps_list      = params.steps.length() > 1 ? params.steps.tokenize(',').collect { it.trim() } : params.steps
+    exclude_steps_list      = params.steps == "NONE" ? [] : params.steps.tokenize(',').collect { it.trim() }
 
     all_steps_list          = ["insilico_digest", "gene_alignment", "repeat_density", "gap_finder", "selfcomp", "synteny", "read_coverage", "telo_finder", "busco", "kmer", "hic_mapping", "NONE"]
 
     jbrowse_include_list    = ["insilico_digest", "gene_alignment", "selfcomp", "synteny", "busco", "kmer"]
+
+    combined_include_list   = ["insilico_digest", "repeat_density", "gap_finder", "synteny", "read_coverage", "telo_finder", "busco", "kmer", "hic_mapping"]
+
     rapid_include_list      = ["repeat_density", "gap_finder", "read_coverage", "telo_finder", "hic_mapping", "kmer"]
 
+    // Map of mode to corresponding include list for cleaner logic
+    mode_include_map = [
+        "JBROWSE"       : jbrowse_include_list,
+        "RAPID"         : rapid_include_list,
+        "RAPID_TOL"     : rapid_include_list,
+        "FULL_COMBINED" : combined_include_list
+    ]
 
     //
-    // Add exclude determined by run mode (JBROWSE, RAPID, RAPID_TOL)
-    // take all processes, remove those in the mode include list and add on cli added exclude steps.
+    // Determine workflow steps based on run mode
+    // Take processes from the mode's include list, remove any CLI excluded steps
     //
-    if (params.mode == "JBROWSE") {
-        include_workflow_steps = (jbrowse_include_list - exclude_steps_list).unique()
-    } else if (params.mode == "RAPID") {
-        include_workflow_steps = (rapid_include_list - exclude_steps_list).unique()
-    } else if (params.mode == "RAPID_TOL") {
-        include_workflow_steps = (rapid_include_list - exclude_steps_list).unique()
-    } else {
-        include_workflow_steps = (all_steps_list - exclude_steps_list).unique()
-    }
+    include_workflow_steps = mode_include_map.containsKey(params.mode) ?
+        (mode_include_map[params.mode] - exclude_steps_list).unique() :
+        (all_steps_list - exclude_steps_list).unique()
 
     // This acts as a "double check" for the user
     log.info "[Treeval: Info] PROCESSES TO RUN INCLUDE: $include_workflow_steps"
 
-    if (!all_steps_list.containsAll(include_workflow_steps)) {
-        log.error "[Treeval: Error] There is an extra argument given on Command Line (--steps): ${exclude_steps_list - all_steps_list}"
+    // Validate that all requested steps are valid
+    invalid_steps = exclude_steps_list - all_steps_list
+    if (invalid_steps) {
+        log.error "[Treeval: Error] Invalid step(s) specified in --steps: ${invalid_steps.join(", ")}"
         log.error "[Treeval: Error] Valid options are: ${all_steps_list.join(", ")}"
+        System.exit(1)
+    }
+
+    // Validate that include_workflow_steps contains only valid steps (safety check)
+    invalid_include_steps = include_workflow_steps - all_steps_list
+    if (invalid_include_steps) {
+        log.error "[Treeval: Error] Internal error - invalid workflow steps detected: ${invalid_include_steps.join(", ")}"
+        System.exit(1)
     }
 
+    //
+    // ASSET CHANNELS: Set up channels for required asset files
+    //
     Channel
         .fromPath( "${projectDir}/assets/gene_alignment/assm_*.as", checkIfExists: true)
         .map { as_file ->
@@ -186,10 +203,9 @@ workflow TREEVAL {
             GENERATE_GENOME.out.dot_genome
         )
         ch_versions         = ch_versions.mix( REPEAT_DENSITY.out.versions )
-
         ch_repeat_density   = REPEAT_DENSITY.out.repeat_density
     } else {
-        ch_repeat_density   = [[],[]]
+        ch_repeat_density   = Channel.of([[],[]])
     }
 
 
@@ -201,7 +217,6 @@ workflow TREEVAL {
             reference
         )
         ch_versions         = ch_versions.mix( GAP_FINDER.out.versions )
-
         ch_gap_file         = GAP_FINDER.out.gap_file
     } else {
         ch_gap_file         = Channel.of([[],[]])
@@ -210,7 +225,7 @@ workflow TREEVAL {
 
     //
     // SUBWORKFLOW: Takes reference file, .genome file, mummer variables, motif length variable and as
-    //              file to generate a file containing sites of self-complementary sequnce.
+    //              file to generate a file containing sites of self-complementary sequence.
     //
     if ( include_workflow_steps.contains("selfcomp")) {
         SELFCOMP (
@@ -224,7 +239,7 @@ workflow TREEVAL {
 
     //
     // SUBWORKFLOW: Takes reference, the directory of syntenic genomes and order/clade of sequence
-    //              and generated a file of syntenic blocks.
+    //              and generates a file of syntenic blocks.
     //
     if ( include_workflow_steps.contains("synteny")) {
         SYNTENY (