Wire deacon host scrubbing into preprocessing workflow

Replaces STAT-based SCRUB_HOST_READS with deacon-based HOST_DEPLETION in preprocess_reads.nf. The scrub_host_reads param continues to gate the step; deacon is used when any deacon index config is available.

The host_depletion subworkflow uses declarative channel ternaries and empty-channel gating rather than procedural if/else blocks. This ensures Nextflow constructs the same DAG structure regardless of which params are set, which matters for -resume cache consistency and makes the dataflow easier to reason about. Processes that aren't needed receive Channel.empty() inputs and simply don't execute, rather than being conditionally excluded from the DAG. Index union routing is determined at parse time from params via a def, avoiding runtime .branch/.size()/.map gymnastics that are fragile in Groovy's type system.

Author: nrminor

lib/py_nvd/_fingerprint.json

@@ -1,4 +1,4 @@
 {
   "main.nf": "d3df999c77a6754811017c07fa446c551d8334e72822a6df1c5cdcacb4715ebb",
-  "nextflow.config": "8d1bbbd14e66c6813a75fce1e3aca4307704fa1e4cd6552fb2d653dd60f78d51"
+  "nextflow.config": "555a48aea54dc2f91d1db96206784e999981c5004464270a9260f62041cb48d9"
 }

workflows/preprocess_reads.nf

@@ -1,5 +1,5 @@
 include { DEDUP_WITH_CLUMPIFY ; TRIM_ADAPTERS ; FILTER_READS ; REPAIR_PAIRS } from "../modules/bbmap"
-include { SCRUB_HOST_READS } from "../modules/stat"
+include { HOST_DEPLETION } from "../subworkflows/host_depletion"
 
 workflow PREPROCESS_READS {
     take:
@@ -29,13 +29,12 @@ workflow PREPROCESS_READS {
 
     ch_after_trim = ch_trimmed_illumina.mix(ch_branched_for_trim.other)
 
-    // 3. Host scrub (requires sra_human_db to be set)
-    ch_human_db = params.sra_human_db
-        ? Channel.fromPath(params.sra_human_db)
-        : Channel.empty()
+    // 3. Host scrub with deacon
+    // Requires at least one of: deacon_index, deacon_index_url, deacon_contaminants_fasta
+    def has_deacon_config = params.deacon_index || params.deacon_index_url || params.deacon_contaminants_fasta
 
-    ch_after_scrub = (should_scrub && params.sra_human_db)
-        ? SCRUB_HOST_READS(ch_after_trim.combine(ch_human_db))
+    ch_after_scrub = (should_scrub && has_deacon_config)
+        ? HOST_DEPLETION(ch_after_trim).reads
         : ch_after_trim
 
     // 4. Quality/length filter (with platform-specific quality threshold)
@@ -51,6 +50,7 @@ workflow PREPROCESS_READS {
         : ch_after_scrub
 
     // 5. Repair pairs (interleaved reads only) - fixes orphans from upstream steps
+    // Note: This works because deacon preserves CASAVA FASTQ headers
     ch_branched_for_repair = ch_after_filter.branch { _id, _platform, read_structure, _reads ->
         interleaved: read_structure == "interleaved"
         other: true