feat: accept gzip-compressed fasta input

modules/local/rename/decompress_fasta.nf

@@ -0,0 +1,20 @@
+process DECOMPRESS_FASTA {
+    label 'process_tiny'
+
+    tag { name }
+
+    conda "${moduleDir}/environment.yml"
+    container "community.wave.seqera.io/library/bbmap:801715ef64484762"
+
+    input:
+    tuple val(name), path(fasta_gz)
+
+    output:
+    tuple val(name), path("DECOMPRESSED/${name}.fa"), emit: decompressed_fasta
+
+    script:
+    """
+    mkdir -p DECOMPRESSED
+    reformat.sh in=${fasta_gz} out=DECOMPRESSED/${name}.fa
+    """
+}

nextflow_schema.json

@@ -68,13 +68,13 @@
                     "format": "path",
                     "exists": true,
                     "description": "Path to FASTA directory",
-                    "help_text": "This parameter is *mandatory*.",
+                    "help_text": "This parameter is *mandatory*. Files may be uncompressed (.fa/.fna/.fasta) or gzip-compressed (.fa.gz/.fna.gz/.fasta.gz); compressed inputs are decompressed automatically before downstream stages.",
                     "fa_icon": "fas fa-folder-open"
                 },
                 "fasta_fmt": {
                     "type": "string",
                     "default": "*.f*",
-                    "description": "Input format for the FASTA file.",
+                    "description": "Input glob for the FASTA files. The default matches both plain and .gz files.",
                     "fa_icon": "fas fa-plus"
                 },
                 "input_genes": {

workflows/dram.nf

@@ -20,6 +20,7 @@ include { MERGE                  } from "../subworkflows/local/merge.nf"
 include { ANNOTATE               } from "../subworkflows/local/annotate.nf"
 include { ADD_ANNOTATIONS        } from "../modules/local/add_and_combine/add_annotations.nf"
 include { SUMMARIZE              } from "../modules/local/distill/distill.nf"
+include { DECOMPRESS_FASTA       } from "../modules/local/rename/decompress_fasta.nf"
 
 
 /*
@@ -59,14 +60,25 @@ workflow DRAM {
     }
 
     if (params.input_fasta && (params.rename || call)) {
-        ch_fasta = Channel
+        ch_fasta_raw = Channel
             .fromPath(file(params.input_fasta) / params.fasta_fmt, checkIfExists: true)
                 .ifEmpty { exit 1, "Cannot find any fasta files matching: ${params.input_fasta}\nNB: Path needs to follow pattern: path/to/directory/" }
 
-        ch_fasta = ch_fasta.map {
-            fasta_name = it.getBaseName()
-            tuple(fasta_name, it)
+        // Strip .gz (if present) and then .fa/.fna/.fasta so a sample's
+        // gz and plain inputs yield the same downstream sample name.
+        ch_fasta_named = ch_fasta_raw.map { f ->
+            def name = f.name.replaceAll(/\.gz$/, '').replaceAll(/\.(fa|fna|fasta)$/, '')
+            tuple(name, f)
         }
+
+        // Route .gz inputs through DECOMPRESS_FASTA; pass plain inputs unchanged.
+        ch_fasta_branched = ch_fasta_named.branch { entry ->
+            gz: entry[1].name.endsWith('.gz')
+            plain: true
+        }
+
+        DECOMPRESS_FASTA( ch_fasta_branched.gz )
+        ch_fasta = DECOMPRESS_FASTA.out.decompressed_fasta.mix( ch_fasta_branched.plain )
     }
     viz_rules_system = params.viz_rules_system