Add singlem

.gitattributes

@@ -1,3 +1,4 @@
+* text=auto eol=lf
 *.config linguist-language=nextflow
 *.nf.test linguist-language=nextflow
 modules/nf-core/** linguist-generated

assets/samplesheet.csv

@@ -1,6 +1,8 @@
 sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
-2611,ERR5766174,ILLUMINA,,,/<path>/<to>/fasta/ERX5474930_ERR5766174_1.fa.gz
-2612,ERR5766176,ILLUMINA,/<path>/<to>/fastq/ERX5474932_ERR5766176_1.fastq.gz,/<path>/<to>/fastq/ERX5474932_ERR5766176_2.fastq.gz,
-2612,ERR5766180,ILLUMINA,/<path>/<to>/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
-2613,ERR5766181,ILLUMINA,/<path>/<to>/fastq/ERX5474937_ERR5766181_1.fastq.gz,/<path>/<to>/fastq/ERX5474937_ERR5766181_2.fastq.gz,
-ERR3201952,ERR3201952,OXFORD_NANOPORE,/<path>/<to>/fastq/ERR3201952.fastq.gz,,
+2611,ERR5766174,ILLUMINA,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERX5474930_ERR5766174_1.fa.gz
+2612,ERR5766176,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_2.fastq.gz,
+2612,ERR5766176_B,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_2.fastq.gz,
+2612,ERR5766180,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
+2613,ERR5766181,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_2.fastq.gz,
+ERR3201952,ERR3201952,OXFORD_NANOPORE,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERR3201952.fastq.gz,,
+2614,ERR3201952,OXFORD_NANOPORE,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERR3201952_dup.fa.gz

assets/schema_database.json

@@ -23,9 +23,10 @@
                     "motus",
                     "sylph",
                     "melon",
+                    "singlem",
                     "metacache"
                 ],
-                "errorMessage": "Invalid tool name. Please see documentation for all supported profilers. Currently these classifers are included: bracken, centrifuge, diamond, ganon, kaiju, kmcp, kraken2, krakenuniq, malt, metaphlan, motus, sylph, melon, metacache.",
+                "errorMessage": "Invalid tool name. Please see documentation for all supported profilers. Currently these classifers are included: bracken, centrifuge, diamond, ganon, kaiju, kmcp, kraken2, krakenuniq, malt, metaphlan, motus, sylph, melon, singlem, metacache.",
                 "meta": ["tool"]
             },
             "db_name": {

databases_empty.csv

@@ -0,0 +1,2 @@
+tool,db_name,db_params,db_path
+singlem,GTDB_r226,,/projectnb/bf528/students/dennig2/singlem_db/S5.4.0.GTDB_r226.metapackage_20250331.smpkg.zb

nextflow.config

@@ -48,7 +48,7 @@ params {
     validate_params                                      = true
 
     // Databases
-    databases                                            = null
+    databases                                            = 'databases_empty.csv'
     save_untarred_databases                              = false
 
     // FASTQ preprocessing
@@ -192,6 +192,12 @@ params {
     run_melon                                            = false
     melon_k2_db                                          = null
 
+    // singlem
+    run_singlem                                          = true
+    singlem_save_reads                                   = false
+    singlem_save_log                                     = false
+    singlem_metapackage                                  = null
+
     // metacache
     run_metacache                                        = false
 
@@ -399,6 +405,7 @@ env {
     R_PROFILE_USER   = "/.Rprofile"
     R_ENVIRON_USER   = "/.Renviron"
     JULIA_DEPOT_PATH = "/usr/local/share/julia"
+// SINGLEM_METAPACKAGE_PATH = params.singlem_metapackage
 }
 
 // Set bash options

samplesheet.csv

@@ -0,0 +1,8 @@
+sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
+2611,ERR5766174,ILLUMINA,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERX5474930_ERR5766174_1.fa.gz
+2612,ERR5766176,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_2.fastq.gz,
+2612,ERR5766176_B,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_2.fastq.gz,
+2612,ERR5766180,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
+2613,ERR5766181,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_2.fastq.gz,
+ERR3201952,ERR3201952,OXFORD_NANOPORE,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERR3201952.fastq.gz,,
+2614,ERR3201952,OXFORD_NANOPORE,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERR3201952_dup.fa.gz

subworkflows/local/profiling.nf

@@ -23,6 +23,7 @@ include { GANON_REPORT                                  } from '../../modules/nf
 include { SYLPH_PROFILE                                 } from '../../modules/nf-core/sylph/profile/main'
 include { SYLPHTAX_TAXPROF                              } from '../../modules/nf-core/sylphtax/taxprof/main'
 include { MELON                                         } from '../../modules/nf-core/melon/main'
+include { SINGLEM_PIPE                                  } from '../../modules/nf-core/singlem/singlem/main'
 
 workflow PROFILING {
     take:
@@ -78,6 +79,7 @@ workflow PROFILING {
             ganon: db_meta.tool == 'ganon'
             sylph: db_meta.tool == 'sylph'
             melon: db_meta.tool == 'melon'
+            singlem: db_meta.tool == 'singlem'
             unknown: true
         }
 
@@ -612,6 +614,24 @@ workflow PROFILING {
         ch_raw_profiles = ch_raw_profiles.mix(MELON.out.tsv_output)
     }
 
+if (params.run_singlem) {
+
+    ch_input_for_singlem = ch_input_for_profiling.singlem
+        .map { sample_meta, input_reads, db_meta, db ->
+            def meta = sample_meta + [
+                tool    : 'singlem',           // profiler name expected by Taxpasta
+                db_name : db_meta.db_name,     // for grouping/ID
+                db_type : db_meta.type ?: null // optional, if you use it elsewhere
+            ]
+            tuple(meta, input_reads, db)
+        }
+
+    SINGLEM_PIPE(ch_input_for_singlem)
+
+    ch_raw_profiles = ch_raw_profiles.mix(SINGLEM_PIPE.out.results)
+    ch_versions     = ch_versions.mix(SINGLEM_PIPE.out.versions)
+    }
+
     emit:
     classifications = ch_raw_classifications
     profiles        = ch_raw_profiles // channel: [ val(meta), [ reads ] ] - should be text files or biom