Update ampcombi 2.0.1 (#7142)

* update ampcombi to 2.0.1 * update the rest of the submodules to 2.0.1 * add dir_path as input in parsetables * Nextflow format document * add code review * fix harshil alignment * remove binary files emmition * add interpro optional input * format document * fix container versions * add minor code review * add more code reviews :)
nf-core · Dec 11, 2024 · 993865f · 993865f
1 parent 784b3a3
commit 993865f
Show file tree

Hide file tree

Showing 12 changed files with 213 additions and 140 deletions.
diff --git 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
@@ -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
@@ -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"
     }
 }
diff --git 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
@@ -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
@@ -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"
     }
-}
+}
diff --git 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
@@ -1,48 +1,54 @@
 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: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)
+    path faa_input
+    path gbk_input
+    val opt_amp_db
+    path opt_amp_db_dir
+    path opt_interproscan
 
     output:
-    tuple val(meta), path("${meta.id}/")                              , emit: sample_dir
-    tuple val(meta), path("${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
+    path "versions.yml"                                                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db = opt_amp_db? "--amp_database $opt_amp_db": ""
+    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("' '")}' \\
-    --faa ${faa_input} \\
-    --gbk ${gbk_input} \\
-    --sample_list ${prefix} \\
-    ${db} \\
-    $args \\
-    --threads ${task.cpus}
+        --path_list '${amp_input.collect { "${it}" }.join("' '")}' \\
+        --faa ${faa_input} \\
+        --gbk ${gbk_input} \\
+        --sample_list ${prefix} \\
+        --amp_database ${opt_amp_db} \\
+        ${db_dir} \\
+        ${interpro} \\
+        ${args} \\
+        --threads ${task.cpus}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -53,20 +59,30 @@ process AMPCOMBI2_PARSETABLES {
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def db = opt_amp_db? "--amp_database $opt_amp_db": ""
+    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
-    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
@@ -16,12 +16,14 @@ keywords:
   - ampgram
   - amptransformer
   - DRAMP
+  - MMseqs2
+  - InterProScan
 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 +54,17 @@ input:
           name.
         pattern: "*.gbk"
   - - 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: "DRAMP|APD|UniRef100"
+  - - opt_amp_db_dir:
         type: directory
         description: The path to the folder containing the fasta and tsv database files.
-        pattern: "*/"
+        pattern: "path/to/amp_*_database"
+  - - opt_interproscan:
+        type: directory
+        description: A path to a file corresponding to the respective tsv files containing protein classifications of the annotated CDSs. The file must be the raw output from InterProScan.
+        pattern: "*.tsv"
 output:
   - sample_dir:
       - meta:
@@ -78,17 +88,17 @@ 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 +144,51 @@ 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_${opt_amp_db}_database/*.fasta:
           type: file
-          description: AMP reference database fasta file, cleaned of diamond-uncompatible
+          description: AMP reference database fasta file in clean format.
             characters.
-          pattern: "/amp_ref_database/*.clean.fasta"
-  - results_db_tsv:
+          pattern: "/amp_*_database/*.fasta"
+  - db_mmseqs:
       - meta:
           type: map
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'sample1', single_end:false ]`
-      - amp_ref_database/*.tsv:
-          type: file
-          description: AMP reference database in tsv-format with two columns containing
-            header and sequence.
-          pattern: "/amp_ref_database/*.tsv"
+      - amp_${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"
   - versions:
       - versions.yml:
           type: file