From 96ac5961f39f5368603e5c40659c8c36a9c61097 Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Mon, 2 Dec 2024 21:40:19 +0100
Subject: [PATCH 1/9] update ampcombi to 2.0.1

---
 .../ampcombi2/parsetables/environment.yml     |   2 +-
 modules/nf-core/ampcombi2/parsetables/main.nf |  60 ++--
 .../nf-core/ampcombi2/parsetables/meta.yml    | 132 +++++++--
 .../ampcombi2/parsetables/tests/main.nf.test  |  32 ++-
 .../parsetables/tests/main.nf.test.snap       | 263 +++++++++++++++---
 5 files changed, 385 insertions(+), 104 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/environment.yml b/modules/nf-core/ampcombi2/parsetables/environment.yml
index 420c955bfd2..f9c25b04a1d 100644
--- a/modules/nf-core/ampcombi2/parsetables/environment.yml
+++ b/modules/nf-core/ampcombi2/parsetables/environment.yml
@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::ampcombi=0.2.2"
+  - "bioconda::ampcombi=2.0.1"
diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index d779440bea2..511b3b8ec39 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -4,28 +4,36 @@ process AMPCOMBI2_PARSETABLES {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ampcombi:0.2.2--pyhdfd78af_0':
-        'biocontainers/ampcombi:0.2.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/ampcombi:2.0.1--pyhdfd78af_0':
+        'biocontainers/ampcombi:2.0.1--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(amp_input)
     path(faa_input)
     path(gbk_input)
-    path(opt_amp_db)
+    val(opt_amp_db)
 
     output:
-    tuple val(meta), path("${meta.id}/")                              , emit: sample_dir
-    tuple val(meta), path("${meta.id}/contig_gbks/")                  , emit: contig_gbks
-    tuple val(meta), path("${meta.id}/${meta.id}_diamond_matches.txt"), emit: txt
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")       , emit: tsv
-    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")            , emit: faa
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")       , emit: sample_log, optional:true
-    tuple val(meta), path("Ampcombi_parse_tables.log")                , emit: full_log, optional:true
-    tuple val(meta), path("amp_ref_database/")                        , emit: results_db, optional:true
-    tuple val(meta), path("amp_ref_database/*.dmnd")                  , emit: results_db_dmnd, optional:true
-    tuple val(meta), path("amp_ref_database/*.clean.fasta")           , emit: results_db_fasta, optional:true
-    tuple val(meta), path("amp_ref_database/*.tsv")                   , emit: results_db_tsv, optional:true
-    path "versions.yml"                                               , emit: versions
+    tuple val(meta), path("${meta.id}/")                                        , emit: sample_dir
+    tuple val(meta), path("${meta.id}/contig_gbks/")                            , emit: contig_gbks
+    tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")           , emit: db_tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")                 , emit: tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")                      , emit: faa
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                 , emit: sample_log, optional:true
+    tuple val(meta), path("Ampcombi_parse_tables.log")                          , emit: full_log, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/")                        , emit: db, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                   , emit: db_txt, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                 , emit: db_fasta, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")                , emit: db_mmseqs, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")          , emit: db_mmseqs_binary, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")   , emit: db_mmseqs_dbtype, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")        , emit: db_mmseqs_h, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype") , emit: db_mmseqs_hdbtype, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index")  , emit: db_mmseqs_hindex, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")    , emit: db_mmseqs_index, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")   , emit: db_mmseqs_lookup, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")   , emit: db_mmseqs_source, optional:true
+    path "versions.yml"                                                         , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -33,14 +41,13 @@ process AMPCOMBI2_PARSETABLES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db = opt_amp_db? "--amp_database $opt_amp_db": ""
     """
     ampcombi parse_tables \\
     --path_list '${amp_input.collect{"$it"}.join("' '")}' \\
     --faa ${faa_input} \\
     --gbk ${gbk_input} \\
     --sample_list ${prefix} \\
-    ${db} \\
+    --amp_database ${opt_amp_db} \\
     $args \\
     --threads ${task.cpus}
 
@@ -53,20 +60,27 @@ process AMPCOMBI2_PARSETABLES {
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db = opt_amp_db? "--amp_database $opt_amp_db": ""
     """
     mkdir -p ${prefix}
     mkdir -p ${prefix}/contig_gbks
-    touch ${prefix}/${meta.id}_diamond_matches.txt
+    touch ${prefix}/${meta.id}_mmseqs_matches.tsv
     touch ${prefix}/${meta.id}_ampcombi.tsv
     touch ${prefix}/${meta.id}_amp.faa
     touch ${prefix}/${meta.id}_ampcombi.log
     touch Ampcombi_parse_tables.log
 
-    mkdir -p amp_ref_database
-    touch amp_ref_database/*.dmnd
-    touch amp_ref_database/*.clean.fasta
-    touch amp_ref_database/*.tsv
+    mkdir -p amp_${opt_amp_db}_database
+    mkdir -p amp_${opt_amp_db}_database/mmseqs2
+    touch amp_${opt_amp_db}_database/*.fasta
+    touch amp_${opt_amp_db}_database/*.txt
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB_h
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB.index
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup
+    touch amp_${opt_amp_db}_database/mmseqs2/ref_DB.source
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/modules/nf-core/ampcombi2/parsetables/meta.yml b/modules/nf-core/ampcombi2/parsetables/meta.yml
index 7159b117739..aabe239d041 100644
--- a/modules/nf-core/ampcombi2/parsetables/meta.yml
+++ b/modules/nf-core/ampcombi2/parsetables/meta.yml
@@ -16,12 +16,13 @@ keywords:
   - ampgram
   - amptransformer
   - DRAMP
+  - MMseqs2
 tools:
   - ampcombi2/parsetables:
       description: "A parsing tool to convert and summarise the outputs from multiple
         AMP detection tools in a standardized format."
       homepage: "https://github.com/Darcy220606/AMPcombi"
-      documentation: "https://github.com/Darcy220606/AMPcombi"
+      documentation: "https://ampcombi.readthedocs.io/en/main/"
       tool_dev_url: "https://github.com/Darcy220606/AMPcombi/tree/dev"
       licence: ["MIT"]
       identifier: ""
@@ -52,9 +53,9 @@ input:
           name.
         pattern: "*.gbk"
   - - opt_amp_db:
-        type: directory
-        description: The path to the folder containing the fasta and tsv database files.
-        pattern: "*/"
+        type: string
+        description: The name of the database to download and set up. This can either be 'DRAMP', 'APD' or 'UniRef100'.
+        pattern: "'*'"
 output:
   - sample_dir:
       - meta:
@@ -78,17 +79,17 @@ output:
           description: The output subdirectory that contains the gbk files containing
             the AMP hits for each sample.
           pattern: "/*/contig_gbks"
-  - txt:
+  - db_tsv:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - ${meta.id}/${meta.id}_diamond_matches.txt:
+      - ${meta.id}/${meta.id}_mmseqs_matches.tsv:
           type: file
-          description: An alignment file containing the results from the DIAMOND alignment
+          description: An alignment file containing the results from the MMseqs2 alignment
             step done on all AMP hits.
-          pattern: "/*/*_diamond_matches.txt"
+          pattern: "/*/*_mmseqs_matches.tsv"
   - tsv:
       - meta:
           type: map
@@ -134,50 +135,131 @@ output:
           description: A log file that captures the standard output for the entire process
             in a log file. Can be activated by `--log`.
           pattern: "Ampcombi_parse_tables.log"
-  - results_db:
+  - db:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - amp_ref_database/:
+      - amp_${opt_amp_db}_database/:
           type: directory
-          description: If the AMP reference database is not provided by the user using
+          description: If the AMP reference database ID is not provided by the user using
             the flag `--amp_database', by default the DRAMP database will be downloaded,
             filtered and stored in this folder.
-          pattern: "/amp_ref_database"
-  - results_db_dmnd:
+          pattern: "/amp_*_database"
+  - db_txt:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - amp_ref_database/*.dmnd:
+      - amp_${opt_amp_db}_database/*.txt:
           type: file
-          description: AMP reference database converted to DIAMOND database format.
-          pattern: "/amp_ref_database/*.dmnd"
-  - results_db_fasta:
+          description: AMP reference database in tsv-format with two columns containing
+            header and sequence.
+          pattern: "/amp_*_database/*.txt"
+  - db_fasta:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - amp_ref_database/*.clean.fasta:
+      - amp_${opt_amp_db}_database/*.fasta:
           type: file
-          description: AMP reference database fasta file, cleaned of diamond-uncompatible
+          description: AMP reference database fasta file in clean format.
             characters.
-          pattern: "/amp_ref_database/*.clean.fasta"
-  - results_db_tsv:
+          pattern: "/amp_*_database/*.fasta"
+  - db_mmseqs:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - amp_ref_database/*.tsv:
+      - amp_${opt_amp_db}_database/mmseqs2/:
+          type: directory
+          description: As alignment to the reference database is carried out by MMseqs2, this directory
+            contains all the files generated by MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2"
+  - db_mmseqs_binary:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB:
           type: file
-          description: AMP reference database in tsv-format with two columns containing
-            header and sequence.
-          pattern: "/amp_ref_database/*.tsv"
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB"
+  - db_mmseqs_dbtype:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB.dbtype"
+  - db_mmseqs_h:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB_h"
+  - db_mmseqs_hdbtype:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB_h.dbtype"
+  - db_mmseqs_hindex:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB_h.index"
+  - db_mmseqs_index:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.index:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB.index"
+  - db_mmseqs_lookup:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB.lookup"
+  - db_mmseqs_source:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.source:
+          type: file
+          description: Binary file generated by running MMseqs2 on the fasta file of the database.
+          pattern: "/amp_*_database/mmseqs2/ref_DB.source"
   - versions:
       - versions.yml:
           type: file
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
index 2d775179b2a..93ecf10e031 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
@@ -28,7 +28,7 @@ nextflow_process {
                 input[0] = amp_input
                 input[1] = faa_input
                 input[2] = gbk_input
-                input[3] = []
+                input[3] = 'DRAMP'
                 """
             }
         }
@@ -37,15 +37,25 @@ nextflow_process {
             assertAll(
                 { assert process.success },
                 { assert snapshot(process.out.sample_dir.collect { file(it[1]).getName() } +
-                                  process.out.results_db.collect { file(it[1]).getName() } +
-                                  process.out.contig_gbks.collect { file(it[1]).getName() } +
-                                  process.out.full_log.collect { file(it[1]).readLines().contains("<--AMP_database>") } +
-                                  process.out.sample_log.collect { file(it[1]).readLines().contains("found ampir file") } +
-                                  process.out.txt.collect { file(it[1]).readLines()[0] } +
-                                  process.out.tsv.collect { file(it[1]).readLines()[0] } +
-                                  process.out.faa.collect { file(it[1]).readLines()[0] } +
-                                  process.out.summary_csv.collect { file(it[1]).readLines().contains("Structure_Description") } +
-                                  process.out.versions ).match() }
+                                    process.out.contig_gbks.collect { file(it[1]).getName() } +
+                                    process.out.db_tsv.collect { file(it[1]).readLines()[0] } +
+                                    process.out.tsv.collect { file(it[1]).readLines()[0] } +
+                                    process.out.faa.collect { file(it[1]).readLines()[0] } +
+                                    process.out.full_log.collect { file(it[1]).readLines().contains("File downloaded successfully") } +
+                                    process.out.sample_log.collect { file(it[1]).readLines().contains("found ampir file") } +
+                                    process.out.db.collect { file(it[1]).getName() } +
+                                    process.out.db_txt.collect { file(it[1]).readLines()[0] } +
+                                    process.out.db_fasta.collect { file(it[1]).readLines()[0] } +
+                                    process.out.db_mmseqs.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_binary.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_dbtype.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_h.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_hdbtype.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_hindex.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_index.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_lookup.collect { file(it[1]).getName() } +
+                                    process.out.db_mmseqs_source.collect { file(it[1]).getName() } +
+                                    process.out.versions ).match() }
             )
         }
     }
@@ -67,7 +77,7 @@ nextflow_process {
                 input[0] = amp_input
                 input[1] = faa_input
                 input[2] = gbk_input
-                input[3] = []
+                input[3] = 'DRAMP'
                 """
             }
         }
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
index 54faf69f4fc..b9ad8f64516 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
@@ -3,21 +3,32 @@
         "content": [
             [
                 "sample_1",
-                "amp_ref_database",
                 "contig_gbks",
+                null,
+                "sample_id\tCDS_id\tprob_ampir\tprob_amplify\taa_sequence\tmolecular_weight\thelix_fraction\tturn_fraction\tsheet_fraction\tisoelectric_point\thydrophobicity\ttransporter_protein\tcontig_id\tCDS_start\tCDS_end\tCDS_dir\tCDS_stop_codon_found",
+                ">BAONEE_00005",
                 false,
                 true,
-                "contig_id\ttarget_id\tpident\tevalue\tnident\tfull_qseq\tfull_sseq\tqseq\tsseq\tqcovhsp\tscovhsp",
-                "sample_id\tCDS_id\tprob_ampir\tprob_amplify\taa_sequence\ttarget_id\tpident\tevalue\tSequence\tFamily\tSource\tPDB_ID\tLinear/Cyclic/Branched\tOther_Modifications\tPubmed_ID\tReference\tmolecular_weight\thelix_fraction\tturn_fraction\tsheet_fraction\tisoelectric_point\thydrophobicity\ttransporter_protein\tcontig_id\tCDS_start\tCDS_end\tCDS_dir\tCDS_stop_codon_found",
-                ">BAONEE_00005",
-                "versions.yml:md5,f32ab4ba79e66feba755b78d7d7a1f36"
+                "amp_DRAMP_database",
+                "DRAMP_ID\tSequence\tSequence_Length\tName\tSwiss_Prot_Entry\tFamily\tGene\tSource\tActivity\tProtein_existence\tStructure\tStructure_Description\tPDB_ID\tComments\tTarget_Organism\tHemolytic_activity\tLinear/Cyclic/Branched\tN-terminal_Modification\tC-terminal_Modification\tOther_Modifications\tStereochemistry\tCytotoxicity\tBinding_Traget\tPubmed_ID\tReference\tAuthor\tTitle",
+                ">DRAMP00005",
+                "mmseqs2",
+                "ref_DB",
+                "ref_DB.dbtype",
+                "ref_DB_h",
+                "ref_DB_h.dbtype",
+                "ref_DB_h.index",
+                "ref_DB.index",
+                "ref_DB.lookup",
+                "ref_DB.source",
+                "versions.yml:md5,09f086e07825d96816d792d73eee90ca"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-24T12:05:11.848363584"
+        "timestamp": "2024-12-02T21:32:24.514271276"
     },
     "ampcombi2_parsetables - metagenome - stub": {
         "content": [
@@ -34,7 +45,7 @@
                             "sample_1_amp.faa:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "sample_1_ampcombi.log:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "sample_1_ampcombi.tsv:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "sample_1_diamond_matches.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            "sample_1_mmseqs_matches.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                         ]
                     ]
                 ],
@@ -53,18 +64,91 @@
                         {
                             "id": "sample_1"
                         },
-                        "*.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
                     ]
                 ],
                 "11": [
-                    "versions.yml:md5,f32ab4ba79e66feba755b78d7d7a1f36"
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "12": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "13": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "14": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "15": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "16": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "17": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "18": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "19": [
+                    "versions.yml:md5,09f086e07825d96816d792d73eee90ca"
                 ],
                 "2": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "sample_1_diamond_matches.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "sample_1_mmseqs_matches.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "3": [
@@ -105,9 +189,18 @@
                             "id": "sample_1"
                         },
                         [
-                            "*.clean.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "*.dmnd:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "*.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            "*.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "*.txt:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            [
+                                "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            ]
                         ]
                     ]
                 ],
@@ -116,7 +209,7 @@
                         {
                             "id": "sample_1"
                         },
-                        "*.dmnd:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "*.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "9": [
@@ -124,7 +217,7 @@
                         {
                             "id": "sample_1"
                         },
-                        "*.clean.fasta:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "*.fasta:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "contig_gbks": [
@@ -137,56 +230,146 @@
                         ]
                     ]
                 ],
-                "faa": [
+                "db": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "sample_1_amp.faa:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "*.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "*.txt:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            [
+                                "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            ]
+                        ]
                     ]
                 ],
-                "full_log": [
+                "db_fasta": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "Ampcombi_parse_tables.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "*.fasta:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "results_db": [
+                "db_mmseqs": [
                     [
                         {
                             "id": "sample_1"
                         },
                         [
-                            "*.clean.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "*.dmnd:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "*.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
                         ]
                     ]
                 ],
-                "results_db_dmnd": [
+                "db_mmseqs_binary": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_dbtype": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_h": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_hdbtype": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_hindex": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_index": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_lookup": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "db_mmseqs_source": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "*.dmnd:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "results_db_fasta": [
+                "db_tsv": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "*.clean.fasta:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "sample_1_mmseqs_matches.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "results_db_tsv": [
+                "db_txt": [
                     [
                         {
                             "id": "sample_1"
                         },
-                        "*.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "*.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "faa": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "sample_1_amp.faa:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "full_log": [
+                    [
+                        {
+                            "id": "sample_1"
+                        },
+                        "Ampcombi_parse_tables.log:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "sample_dir": [
@@ -201,7 +384,7 @@
                             "sample_1_amp.faa:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "sample_1_ampcombi.log:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "sample_1_ampcombi.tsv:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "sample_1_diamond_matches.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
+                            "sample_1_mmseqs_matches.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                         ]
                     ]
                 ],
@@ -221,23 +404,15 @@
                         "sample_1_ampcombi.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "txt": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "sample_1_diamond_matches.txt:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
                 "versions": [
-                    "versions.yml:md5,f32ab4ba79e66feba755b78d7d7a1f36"
+                    "versions.yml:md5,09f086e07825d96816d792d73eee90ca"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-24T12:05:34.675308615"
+        "timestamp": "2024-12-02T21:14:19.671622923"
     }
 }
\ No newline at end of file

From df8cdc7fc19849e8ea3d58993fdf183fc021449b Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Tue, 3 Dec 2024 08:18:58 +0100
Subject: [PATCH 2/9] update the rest of the submodules to 2.0.1

---
 .../nf-core/ampcombi2/cluster/environment.yml |  2 +-
 modules/nf-core/ampcombi2/cluster/main.nf     |  4 ++--
 .../ampcombi2/cluster/tests/main.nf.test.snap | 18 +++++++-------
 .../ampcombi2/complete/environment.yml        |  2 +-
 modules/nf-core/ampcombi2/complete/main.nf    |  4 ++--
 .../complete/tests/main.nf.test.snap          | 24 +++++++++----------
 6 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/modules/nf-core/ampcombi2/cluster/environment.yml b/modules/nf-core/ampcombi2/cluster/environment.yml
index 420c955bfd2..f9c25b04a1d 100644
--- a/modules/nf-core/ampcombi2/cluster/environment.yml
+++ b/modules/nf-core/ampcombi2/cluster/environment.yml
@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::ampcombi=0.2.2"
+  - "bioconda::ampcombi=2.0.1"
diff --git a/modules/nf-core/ampcombi2/cluster/main.nf b/modules/nf-core/ampcombi2/cluster/main.nf
index 90495dba4b6..98a19a966c7 100644
--- a/modules/nf-core/ampcombi2/cluster/main.nf
+++ b/modules/nf-core/ampcombi2/cluster/main.nf
@@ -4,8 +4,8 @@ process AMPCOMBI2_CLUSTER {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ampcombi:0.2.2--pyhdfd78af_0':
-        'biocontainers/ampcombi:0.2.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/ampcombi:2.0.1--pyhdfd78af_0':
+        'biocontainers/ampcombi:2.0.1--pyhdfd78af_0' }"
 
     input:
     path(summary_file)
diff --git a/modules/nf-core/ampcombi2/cluster/tests/main.nf.test.snap b/modules/nf-core/ampcombi2/cluster/tests/main.nf.test.snap
index f4123c76322..fd79a83b92a 100644
--- a/modules/nf-core/ampcombi2/cluster/tests/main.nf.test.snap
+++ b/modules/nf-core/ampcombi2/cluster/tests/main.nf.test.snap
@@ -4,14 +4,14 @@
             true,
             true,
             [
-                "versions.yml:md5,4e9aa3812bfee6ec22a1b6ccb62de2ca"
+                "versions.yml:md5,b629089d44775078dce5e664a455422b"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-24T12:11:40.928513749"
+        "timestamp": "2024-12-03T07:57:01.869983435"
     },
     "ampcombi2_cluster - metagenome - stub": {
         "content": [
@@ -26,7 +26,7 @@
                     "Ampcombi_cluster.log:md5,d41d8cd98f00b204e9800998ecf8427e"
                 ],
                 "3": [
-                    "versions.yml:md5,4e9aa3812bfee6ec22a1b6ccb62de2ca"
+                    "versions.yml:md5,b629089d44775078dce5e664a455422b"
                 ],
                 "cluster_tsv": [
                     "Ampcombi_summary_cluster.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
@@ -38,14 +38,14 @@
                     "Ampcombi_summary_cluster_representative_seq.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                 ],
                 "versions": [
-                    "versions.yml:md5,4e9aa3812bfee6ec22a1b6ccb62de2ca"
+                    "versions.yml:md5,b629089d44775078dce5e664a455422b"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-24T12:12:08.780718892"
+        "timestamp": "2024-12-03T07:57:23.939137628"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/ampcombi2/complete/environment.yml b/modules/nf-core/ampcombi2/complete/environment.yml
index 420c955bfd2..f9c25b04a1d 100644
--- a/modules/nf-core/ampcombi2/complete/environment.yml
+++ b/modules/nf-core/ampcombi2/complete/environment.yml
@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::ampcombi=0.2.2"
+  - "bioconda::ampcombi=2.0.1"
diff --git a/modules/nf-core/ampcombi2/complete/main.nf b/modules/nf-core/ampcombi2/complete/main.nf
index 0e4d5d53738..98f62347ba2 100644
--- a/modules/nf-core/ampcombi2/complete/main.nf
+++ b/modules/nf-core/ampcombi2/complete/main.nf
@@ -4,8 +4,8 @@ process AMPCOMBI2_COMPLETE {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ampcombi:0.2.2--pyhdfd78af_0':
-        'biocontainers/ampcombi:0.2.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/ampcombi:2.0.1--pyhdfd78af_0':
+        'biocontainers/ampcombi:2.0.1--pyhdfd78af_0' }"
 
     input:
     path(summaries)
diff --git a/modules/nf-core/ampcombi2/complete/tests/main.nf.test.snap b/modules/nf-core/ampcombi2/complete/tests/main.nf.test.snap
index cd8fa18f919..87435e5b931 100644
--- a/modules/nf-core/ampcombi2/complete/tests/main.nf.test.snap
+++ b/modules/nf-core/ampcombi2/complete/tests/main.nf.test.snap
@@ -6,39 +6,39 @@
                     "Ampcombi_summary.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                 ],
                 "1": [
-                    
+
                 ],
                 "2": [
-                    "versions.yml:md5,0aa35e86761a6c160482b8b8dbfc5440"
+                    "versions.yml:md5,bfba0046e0cfa7b0b6d79663823f94c0"
                 ],
                 "log": [
-                    
+
                 ],
                 "tsv": [
                     "Ampcombi_summary.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                 ],
                 "versions": [
-                    "versions.yml:md5,0aa35e86761a6c160482b8b8dbfc5440"
+                    "versions.yml:md5,bfba0046e0cfa7b0b6d79663823f94c0"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-29T11:55:16.030399422"
+        "timestamp": "2024-12-03T07:57:53.385349848"
     },
     "ampcombi2_complete - contigs": {
         "content": [
             true,
             [
-                "versions.yml:md5,0aa35e86761a6c160482b8b8dbfc5440"
+                "versions.yml:md5,bfba0046e0cfa7b0b6d79663823f94c0"
             ]
         ],
         "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.2"
         },
-        "timestamp": "2024-04-29T11:54:54.334224301"
+        "timestamp": "2024-12-03T07:57:40.263912946"
     }
-}
\ No newline at end of file
+}

From 7a3c105d0e7a31a51187a0a288d86063c298dc2b Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Tue, 3 Dec 2024 11:09:06 +0100
Subject: [PATCH 3/9] add dir_path as input in parsetables

---
 modules/nf-core/ampcombi2/parsetables/main.nf            | 2 ++
 modules/nf-core/ampcombi2/parsetables/meta.yml           | 4 ++++
 modules/nf-core/ampcombi2/parsetables/tests/main.nf.test | 2 ++
 3 files changed, 8 insertions(+)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index 511b3b8ec39..367652dc54b 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -12,6 +12,7 @@ process AMPCOMBI2_PARSETABLES {
     path(faa_input)
     path(gbk_input)
     val(opt_amp_db)
+    path(opt_amp_db_dir)
 
     output:
     tuple val(meta), path("${meta.id}/")                                        , emit: sample_dir
@@ -48,6 +49,7 @@ process AMPCOMBI2_PARSETABLES {
     --gbk ${gbk_input} \\
     --sample_list ${prefix} \\
     --amp_database ${opt_amp_db} \\
+    --amp_database_dir ${opt_amp_db_dir} \\
     $args \\
     --threads ${task.cpus}
 
diff --git a/modules/nf-core/ampcombi2/parsetables/meta.yml b/modules/nf-core/ampcombi2/parsetables/meta.yml
index aabe239d041..ea0e0a3c41a 100644
--- a/modules/nf-core/ampcombi2/parsetables/meta.yml
+++ b/modules/nf-core/ampcombi2/parsetables/meta.yml
@@ -56,6 +56,10 @@ input:
         type: string
         description: The name of the database to download and set up. This can either be 'DRAMP', 'APD' or 'UniRef100'.
         pattern: "'*'"
+  - - opt_amp_db_dir:
+        type: directory
+        description: The path to the folder containing the fasta and tsv database files.
+        pattern: "path/to/amp_*_database"
 output:
   - sample_dir:
       - meta:
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
index 93ecf10e031..703fd5d3b11 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
@@ -29,6 +29,7 @@ nextflow_process {
                 input[1] = faa_input
                 input[2] = gbk_input
                 input[3] = 'DRAMP'
+                input[4] = []
                 """
             }
         }
@@ -78,6 +79,7 @@ nextflow_process {
                 input[1] = faa_input
                 input[2] = gbk_input
                 input[3] = 'DRAMP'
+                input[4] = []
                 """
             }
         }

From 90523c2ff49b5ce92225aa6426acadeeced2325f Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Wed, 4 Dec 2024 16:54:43 +0100
Subject: [PATCH 4/9] Nextflow format document

---
 modules/nf-core/ampcombi2/parsetables/main.nf | 60 +++++++++----------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index 367652dc54b..21b4bc6b2c1 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -1,40 +1,40 @@
 process AMPCOMBI2_PARSETABLES {
-    tag "$meta.id"
+    tag "${meta.id}"
     label 'process_medium'
 
     conda "${moduleDir}/environment.yml"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ampcombi:2.0.1--pyhdfd78af_0':
-        'biocontainers/ampcombi:2.0.1--pyhdfd78af_0' }"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/ampcombi:2.0.1--pyhdfd78af_0'
+        : 'biocontainers/ampcombi:2.0.1--pyhdfd78af_0'}"
 
     input:
     tuple val(meta), path(amp_input)
-    path(faa_input)
-    path(gbk_input)
-    val(opt_amp_db)
-    path(opt_amp_db_dir)
+    path faa_input
+    path gbk_input
+    val opt_amp_db
+    path opt_amp_db_dir
 
     output:
-    tuple val(meta), path("${meta.id}/")                                        , emit: sample_dir
-    tuple val(meta), path("${meta.id}/contig_gbks/")                            , emit: contig_gbks
-    tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")           , emit: db_tsv
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")                 , emit: tsv
-    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")                      , emit: faa
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                 , emit: sample_log, optional:true
-    tuple val(meta), path("Ampcombi_parse_tables.log")                          , emit: full_log, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/")                        , emit: db, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                   , emit: db_txt, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                 , emit: db_fasta, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")                , emit: db_mmseqs, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")          , emit: db_mmseqs_binary, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")   , emit: db_mmseqs_dbtype, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")        , emit: db_mmseqs_h, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype") , emit: db_mmseqs_hdbtype, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index")  , emit: db_mmseqs_hindex, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")    , emit: db_mmseqs_index, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")   , emit: db_mmseqs_lookup, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")   , emit: db_mmseqs_source, optional:true
-    path "versions.yml"                                                         , emit: versions
+    tuple val(meta), path("${meta.id}/")                                       , emit: sample_dir
+    tuple val(meta), path("${meta.id}/contig_gbks/")                           , emit: contig_gbks
+    tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")          , emit: db_tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")                , emit: tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")                     , emit: faa
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                , emit: sample_log,        optional:true
+    tuple val(meta), path("Ampcombi_parse_tables.log")                         , emit: full_log,          optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/")                       , emit: db,                optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                  , emit: db_txt,            optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                , emit: db_fasta,          optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")               , emit: db_mmseqs,         optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")         , emit: db_mmseqs_binary,  optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")  , emit: db_mmseqs_dbtype,  optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")       , emit: db_mmseqs_h,       optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype"), emit: db_mmseqs_hdbtype, optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index") , emit: db_mmseqs_hindex,  optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")   , emit: db_mmseqs_index,   optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")  , emit: db_mmseqs_lookup,  optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")  , emit: db_mmseqs_source,  optional:true
+    path "versions.yml"                                                        , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -44,13 +44,13 @@ process AMPCOMBI2_PARSETABLES {
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     ampcombi parse_tables \\
-    --path_list '${amp_input.collect{"$it"}.join("' '")}' \\
+    --path_list '${amp_input.collect { "${it}" }.join("' '")}' \\
     --faa ${faa_input} \\
     --gbk ${gbk_input} \\
     --sample_list ${prefix} \\
     --amp_database ${opt_amp_db} \\
     --amp_database_dir ${opt_amp_db_dir} \\
-    $args \\
+    ${args} \\
     --threads ${task.cpus}
 
     cat <<-END_VERSIONS > versions.yml

From b965c7ca1305f8bde6cf48e03477cac71dafe2b5 Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Wed, 4 Dec 2024 16:57:56 +0100
Subject: [PATCH 5/9] add code review

---
 modules/nf-core/ampcombi2/parsetables/meta.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/meta.yml b/modules/nf-core/ampcombi2/parsetables/meta.yml
index ea0e0a3c41a..30a68a39861 100644
--- a/modules/nf-core/ampcombi2/parsetables/meta.yml
+++ b/modules/nf-core/ampcombi2/parsetables/meta.yml
@@ -55,7 +55,7 @@ input:
   - - opt_amp_db:
         type: string
         description: The name of the database to download and set up. This can either be 'DRAMP', 'APD' or 'UniRef100'.
-        pattern: "'*'"
+        pattern: "DRAMP|APD|UniRef100"
   - - opt_amp_db_dir:
         type: directory
         description: The path to the folder containing the fasta and tsv database files.

From ae1dab88dfc2bc5aaf74180304088b8acc6efef1 Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Wed, 4 Dec 2024 17:04:21 +0100
Subject: [PATCH 6/9] fix harshil alignment

---
 modules/nf-core/ampcombi2/parsetables/main.nf | 28 +++++++++----------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index 21b4bc6b2c1..f6dd0419b07 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -20,20 +20,20 @@ process AMPCOMBI2_PARSETABLES {
     tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")          , emit: db_tsv
     tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")                , emit: tsv
     tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")                     , emit: faa
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                , emit: sample_log,        optional:true
-    tuple val(meta), path("Ampcombi_parse_tables.log")                         , emit: full_log,          optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/")                       , emit: db,                optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                  , emit: db_txt,            optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                , emit: db_fasta,          optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")               , emit: db_mmseqs,         optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")         , emit: db_mmseqs_binary,  optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")  , emit: db_mmseqs_dbtype,  optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")       , emit: db_mmseqs_h,       optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype"), emit: db_mmseqs_hdbtype, optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index") , emit: db_mmseqs_hindex,  optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")   , emit: db_mmseqs_index,   optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")  , emit: db_mmseqs_lookup,  optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")  , emit: db_mmseqs_source,  optional:true
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                , emit: sample_log        , optional:true
+    tuple val(meta), path("Ampcombi_parse_tables.log")                         , emit: full_log          , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/")                       , emit: db                , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                  , emit: db_txt            , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                , emit: db_fasta          , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")               , emit: db_mmseqs         , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")         , emit: db_mmseqs_binary  , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")  , emit: db_mmseqs_dbtype  , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")       , emit: db_mmseqs_h       , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype"), emit: db_mmseqs_hdbtype , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index") , emit: db_mmseqs_hindex  , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")   , emit: db_mmseqs_index   , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")  , emit: db_mmseqs_lookup  , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")  , emit: db_mmseqs_source  , optional:true
     path "versions.yml"                                                        , emit: versions
 
     when:

From 1658e5833619a06ed6967967933a9777a050a2bb Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Thu, 5 Dec 2024 13:23:44 +0100
Subject: [PATCH 7/9] remove binary files emmition

---
 modules/nf-core/ampcombi2/parsetables/main.nf |  32 ++--
 .../nf-core/ampcombi2/parsetables/meta.yml    |  80 ----------
 .../ampcombi2/parsetables/tests/main.nf.test  |   8 -
 .../parsetables/tests/main.nf.test.snap       | 140 +-----------------
 4 files changed, 14 insertions(+), 246 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index f6dd0419b07..a1ff3aa34f0 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -15,26 +15,18 @@ process AMPCOMBI2_PARSETABLES {
     path opt_amp_db_dir
 
     output:
-    tuple val(meta), path("${meta.id}/")                                       , emit: sample_dir
-    tuple val(meta), path("${meta.id}/contig_gbks/")                           , emit: contig_gbks
-    tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")          , emit: db_tsv
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")                , emit: tsv
-    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")                     , emit: faa
-    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")                , emit: sample_log        , optional:true
-    tuple val(meta), path("Ampcombi_parse_tables.log")                         , emit: full_log          , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/")                       , emit: db                , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")                  , emit: db_txt            , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")                , emit: db_fasta          , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")               , emit: db_mmseqs         , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB")         , emit: db_mmseqs_binary  , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype")  , emit: db_mmseqs_dbtype  , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h")       , emit: db_mmseqs_h       , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype"), emit: db_mmseqs_hdbtype , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index") , emit: db_mmseqs_hindex  , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.index")   , emit: db_mmseqs_index   , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup")  , emit: db_mmseqs_lookup  , optional:true
-    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/ref_DB.source")  , emit: db_mmseqs_source  , optional:true
-    path "versions.yml"                                                        , emit: versions
+    tuple val(meta), path("${meta.id}/")                                , emit: sample_dir
+    tuple val(meta), path("${meta.id}/contig_gbks/")                    , emit: contig_gbks
+    tuple val(meta), path("${meta.id}/${meta.id}_mmseqs_matches.tsv")   , emit: db_tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.tsv")         , emit: tsv
+    tuple val(meta), path("${meta.id}/${meta.id}_amp.faa")              , emit: faa
+    tuple val(meta), path("${meta.id}/${meta.id}_ampcombi.log")         , emit: sample_log   , optional:true
+    tuple val(meta), path("Ampcombi_parse_tables.log")                  , emit: full_log     , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/")                , emit: db           , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.txt")           , emit: db_txt       , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/*.fasta")         , emit: db_fasta     , optional:true
+    tuple val(meta), path("amp_${opt_amp_db}_database/mmseqs2/")        , emit: db_mmseqs    , optional:true
+    path "versions.yml"                                                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/nf-core/ampcombi2/parsetables/meta.yml b/modules/nf-core/ampcombi2/parsetables/meta.yml
index 30a68a39861..10a19f2ec35 100644
--- a/modules/nf-core/ampcombi2/parsetables/meta.yml
+++ b/modules/nf-core/ampcombi2/parsetables/meta.yml
@@ -184,86 +184,6 @@ output:
           description: As alignment to the reference database is carried out by MMseqs2, this directory
             contains all the files generated by MMseqs2 on the fasta file of the database.
           pattern: "/amp_*_database/mmseqs2"
-  - db_mmseqs_binary:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB"
-  - db_mmseqs_dbtype:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.dbtype:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB.dbtype"
-  - db_mmseqs_h:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB_h"
-  - db_mmseqs_hdbtype:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.dbtype:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB_h.dbtype"
-  - db_mmseqs_hindex:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB_h.index:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB_h.index"
-  - db_mmseqs_index:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.index:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB.index"
-  - db_mmseqs_lookup:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.lookup:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB.lookup"
-  - db_mmseqs_source:
-      - meta:
-          type: map
-          description: |
-            Groovy Map containing sample information
-            e.g. `[ id:'sample1', single_end:false ]`
-      - amp_${opt_amp_db}_database/mmseqs2/ref_DB.source:
-          type: file
-          description: Binary file generated by running MMseqs2 on the fasta file of the database.
-          pattern: "/amp_*_database/mmseqs2/ref_DB.source"
   - versions:
       - versions.yml:
           type: file
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
index 703fd5d3b11..3cf759273dd 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
@@ -48,14 +48,6 @@ nextflow_process {
                                     process.out.db_txt.collect { file(it[1]).readLines()[0] } +
                                     process.out.db_fasta.collect { file(it[1]).readLines()[0] } +
                                     process.out.db_mmseqs.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_binary.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_dbtype.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_h.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_hdbtype.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_hindex.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_index.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_lookup.collect { file(it[1]).getName() } +
-                                    process.out.db_mmseqs_source.collect { file(it[1]).getName() } +
                                     process.out.versions ).match() }
             )
         }
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
index b9ad8f64516..43a327cfb9b 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
@@ -13,14 +13,6 @@
                 "DRAMP_ID\tSequence\tSequence_Length\tName\tSwiss_Prot_Entry\tFamily\tGene\tSource\tActivity\tProtein_existence\tStructure\tStructure_Description\tPDB_ID\tComments\tTarget_Organism\tHemolytic_activity\tLinear/Cyclic/Branched\tN-terminal_Modification\tC-terminal_Modification\tOther_Modifications\tStereochemistry\tCytotoxicity\tBinding_Traget\tPubmed_ID\tReference\tAuthor\tTitle",
                 ">DRAMP00005",
                 "mmseqs2",
-                "ref_DB",
-                "ref_DB.dbtype",
-                "ref_DB_h",
-                "ref_DB_h.dbtype",
-                "ref_DB_h.index",
-                "ref_DB.index",
-                "ref_DB.lookup",
-                "ref_DB.source",
                 "versions.yml:md5,09f086e07825d96816d792d73eee90ca"
             ]
         ],
@@ -28,7 +20,7 @@
             "nf-test": "0.9.2",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-02T21:32:24.514271276"
+        "timestamp": "2024-12-05T13:02:52.664971407"
     },
     "ampcombi2_parsetables - metagenome - stub": {
         "content": [
@@ -77,70 +69,6 @@
                     ]
                 ],
                 "11": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "12": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "13": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "14": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "15": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "16": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "17": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "18": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "19": [
                     "versions.yml:md5,09f086e07825d96816d792d73eee90ca"
                 ],
                 "2": [
@@ -276,70 +204,6 @@
                         ]
                     ]
                 ],
-                "db_mmseqs_binary": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_dbtype": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_h": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_hdbtype": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h.dbtype:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_hindex": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB_h.index:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_index": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.index:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_lookup": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.lookup:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
-                "db_mmseqs_source": [
-                    [
-                        {
-                            "id": "sample_1"
-                        },
-                        "ref_DB.source:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
                 "db_tsv": [
                     [
                         {
@@ -413,6 +277,6 @@
             "nf-test": "0.9.2",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-02T21:14:19.671622923"
+        "timestamp": "2024-12-05T13:03:22.741430379"
     }
 }
\ No newline at end of file

From fb21d921cf19e5b0690070277f23114eff4d6f21 Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Wed, 11 Dec 2024 15:07:03 +0100
Subject: [PATCH 8/9] add interpro optional input

---
 modules/nf-core/ampcombi2/parsetables/main.nf          | 10 +++++++++-
 modules/nf-core/ampcombi2/parsetables/meta.yml         |  5 +++++
 .../nf-core/ampcombi2/parsetables/tests/main.nf.test   |  2 ++
 .../ampcombi2/parsetables/tests/main.nf.test.snap      |  2 +-
 .../ampcombi2/parsetables/tests/nextflow.config        |  3 ++-
 5 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index a1ff3aa34f0..05e7ec8ae10 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -13,6 +13,7 @@ process AMPCOMBI2_PARSETABLES {
     path gbk_input
     val opt_amp_db
     path opt_amp_db_dir
+    path opt_interproscan
 
     output:
     tuple val(meta), path("${meta.id}/")                                , emit: sample_dir
@@ -34,6 +35,9 @@ process AMPCOMBI2_PARSETABLES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def db_dir = opt_amp_db_dir? "--amp_database_dir $opt_amp_db_dir": ""
+    def interpro = opt_interproscan? "--interproscan_output $opt_interproscan": ""
+
     """
     ampcombi parse_tables \\
     --path_list '${amp_input.collect { "${it}" }.join("' '")}' \\
@@ -41,7 +45,8 @@ process AMPCOMBI2_PARSETABLES {
     --gbk ${gbk_input} \\
     --sample_list ${prefix} \\
     --amp_database ${opt_amp_db} \\
-    --amp_database_dir ${opt_amp_db_dir} \\
+    ${db_dir} \\
+    ${interpro} \\
     ${args} \\
     --threads ${task.cpus}
 
@@ -54,6 +59,9 @@ process AMPCOMBI2_PARSETABLES {
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def db_dir = opt_amp_db_dir? "--amp_database_dir $opt_amp_db_dir": ""
+    def interpro = opt_interproscan? "--interproscan_output $opt_interproscan": ""
+
     """
     mkdir -p ${prefix}
     mkdir -p ${prefix}/contig_gbks
diff --git a/modules/nf-core/ampcombi2/parsetables/meta.yml b/modules/nf-core/ampcombi2/parsetables/meta.yml
index 10a19f2ec35..6a7a7162715 100644
--- a/modules/nf-core/ampcombi2/parsetables/meta.yml
+++ b/modules/nf-core/ampcombi2/parsetables/meta.yml
@@ -17,6 +17,7 @@ keywords:
   - amptransformer
   - DRAMP
   - MMseqs2
+  - InterProScan
 tools:
   - ampcombi2/parsetables:
       description: "A parsing tool to convert and summarise the outputs from multiple
@@ -60,6 +61,10 @@ input:
         type: directory
         description: The path to the folder containing the fasta and tsv database files.
         pattern: "path/to/amp_*_database"
+  - - opt_interproscan:
+        type: directory
+        description:  The path to the file corresponding to the respective tsv files containing the protein classifications of the annotated CDSs. The file must be the raw output from InterProScan and have an extension of '.tsv'.
+        pattern: "*.faa.tsv"
 output:
   - sample_dir:
       - meta:
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
index 3cf759273dd..272d31e6b5f 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test
@@ -30,6 +30,7 @@ nextflow_process {
                 input[2] = gbk_input
                 input[3] = 'DRAMP'
                 input[4] = []
+                input[5] = []
                 """
             }
         }
@@ -72,6 +73,7 @@ nextflow_process {
                 input[2] = gbk_input
                 input[3] = 'DRAMP'
                 input[4] = []
+                input[5] = []
                 """
             }
         }
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
index 43a327cfb9b..47102283a39 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
+++ b/modules/nf-core/ampcombi2/parsetables/tests/main.nf.test.snap
@@ -20,7 +20,7 @@
             "nf-test": "0.9.2",
             "nextflow": "24.10.2"
         },
-        "timestamp": "2024-12-05T13:02:52.664971407"
+        "timestamp": "2024-12-11T13:58:57.988191067"
     },
     "ampcombi2_parsetables - metagenome - stub": {
         "content": [
diff --git a/modules/nf-core/ampcombi2/parsetables/tests/nextflow.config b/modules/nf-core/ampcombi2/parsetables/tests/nextflow.config
index d39b05094c3..75396b7df59 100644
--- a/modules/nf-core/ampcombi2/parsetables/tests/nextflow.config
+++ b/modules/nf-core/ampcombi2/parsetables/tests/nextflow.config
@@ -12,7 +12,8 @@ process {
         "--hmmsearch_file 'candidates.txt'",
         "--ampgram_file '.tsv'",
         "--amptransformer_file '.txt'",
-        "--log true"
+        "--log true",
+        "--interproscan_filter 'nonsense'"
     ].join(' ')
 
     ext.prefix = "sample_1"

From 62a8c7d0d49e0ea39680480384ea75656b026ea1 Mon Sep 17 00:00:00 2001
From: darcy220606 <ananhamido@hotmail.com>
Date: Wed, 11 Dec 2024 15:28:17 +0100
Subject: [PATCH 9/9] format document

---
 modules/nf-core/ampcombi2/parsetables/main.nf | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/modules/nf-core/ampcombi2/parsetables/main.nf b/modules/nf-core/ampcombi2/parsetables/main.nf
index 05e7ec8ae10..b4289d24b48 100644
--- a/modules/nf-core/ampcombi2/parsetables/main.nf
+++ b/modules/nf-core/ampcombi2/parsetables/main.nf
@@ -35,8 +35,8 @@ process AMPCOMBI2_PARSETABLES {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db_dir = opt_amp_db_dir? "--amp_database_dir $opt_amp_db_dir": ""
-    def interpro = opt_interproscan? "--interproscan_output $opt_interproscan": ""
+    def db_dir = opt_amp_db_dir ? "--amp_database_dir ${opt_amp_db_dir}" : ""
+    def interpro = opt_interproscan ? "--interproscan_output ${opt_interproscan}" : ""
 
     """
     ampcombi parse_tables \\
@@ -59,8 +59,8 @@ process AMPCOMBI2_PARSETABLES {
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db_dir = opt_amp_db_dir? "--amp_database_dir $opt_amp_db_dir": ""
-    def interpro = opt_interproscan? "--interproscan_output $opt_interproscan": ""
+    def db_dir = opt_amp_db_dir ? "--amp_database_dir ${opt_amp_db_dir}" : ""
+    def interpro = opt_interproscan ? "--interproscan_output ${opt_interproscan}" : ""
 
     """
     mkdir -p ${prefix}