Merge branch 'main' into dev

README.md

@@ -12,7 +12,7 @@
 Mikrokondo is a tidy workflow for performing routine bioinformatic tasks like, read pre-processing, assessing contamination, assembly and quality assessment of assemblies. It is easily configurable, provides dynamic dispatch of species specific workflows and produces common outputs.
 
 ## Is mikrokondo right for me?
-Mikrokondo takes in either, Illumina, Nanopore or Pacbio data (Pacbio data only partially tested). You can also use mikrokondo for hybrid assemblies or even pass it pre-assembled assembled genomes. Additionally, mikrokondo required minimal upfront knowledge of your sample.
+Mikrokondo takes in either, Illumina, Nanopore or Pacbio data (Pacbio data only partially tested). You can also use mikrokondo for hybrid assemblies or even pass it pre-assembled genomes to handle annotation for you. Additionally, mikrokondo required minimal upfront knowledge of your sample.
 
 # Installation
 
@@ -51,8 +51,8 @@ Under the usage section you can find example commands, instructions for configur
 - [GTDB Mash Sketch](https://zenodo.org/record/8408361): required for speciation and determination if sample is metagenomic
 - [Decontamination Index](https://zenodo.org/record/8408557): Required for decontamination of reads (it is simply a minimap2 index)
 - [Kraken2 nt database](https://benlangmead.github.io/aws-indexes/k2): Required for binning of metagenommic data and is an alternative to using Mash for speciation
-- [Bakta database](https://zenodo.org/record/7669534): Running Bakta is optional and there is a light database option, however the full one is recommended. You will have to unzip and un-tar the database for usage.
-- [StarAMR database](https://github.com/phac-nml/staramr#database-build): Running StarAMR is optional and requires downloading the StarAMR databases. Also if you wish to avoid downloading the database, the container for StarAMR has a database included which mikrokondo will default to using if one is not specified.
+- [Bakta database](https://zenodo.org/record/7669534): Running Bakta is optional and there is a light database option, however the full one is recommended. You will have to unzip and un-tar the database for usage. You can skip running Bakta however making the requirement of downloading this database **optional**.
+- [StarAMR database](https://github.com/phac-nml/staramr#database-build): Running StarAMR is optional and requires downloading the StarAMR databases. Also if you wish to avoid downloading the database, the container for StarAMR has a database included which mikrokondo will default to using if one is not specified making this requirement **optional**.
 
 ### Fields to update with resources
 The above downloadable resources must be updated in the following places in your `nextflow.config`. The spots to update in the params section of the `nextflow.config` are listed below:
@@ -108,6 +108,7 @@ Three test profile with example data are provided and can be run like so:
 
 - Swap Seqtk with Rasusa for down sampling
 - Integrate nf-validate
+- Trim pilon prefix added to contigs by pilon
 
 ## Citations
 

conf/modules.config

@@ -737,9 +737,9 @@ process {
 
     }
 
-    withName: ABRICATE_RUN {
+    withName: ABRICATE {
         errorStrategy = 'ignore'
-
+        ext.containers = params.abricate
         stageInMode = params.stage_in_mode
         publishDir = [
             [

docs/usage/configuration.md

@@ -224,9 +224,11 @@ If as an example if, the `--quast.min_contig_lenth` parameter would be written a
 Note: Parameters that are bolded are ones that can be freely changed. Sensible defaults are provided however
 
 ### Abricate
-Screens contigs for antimicrobial and virulence genes.
+Screens contigs for antimicrobial and virulence genes. If you wish to use a different Abricate database you may need to update the container you use.
 
 - abricate
+    - singularity: Abricate singularity container
+    - docker: Abricate docker container
     - **args**: Can be a string of additional command line arguments to pass to abricate
     - report_tag: This field determines the name of the Abricate output in the final summary file. Do no touch this unless doing pipeline development.
     - header_p: This field tells the report module that the Abricate output contains headers. Do no touch this unless doing pipeline development.

modules.json

@@ -5,11 +5,6 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
-                    "abricate/run": {
-                        "branch": "master",
-                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
-                        "installed_by": ["modules"]
-                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "c8e35eb2055c099720a75538d1b8adb3fb5a464c",

modules/local/abricate.nf

@@ -0,0 +1,27 @@
+/// Abricate module
+
+
+process ABRICATE {
+    tag "$meta.id"
+    label 'process_medium'
+    container "${workflow.containerEngine == 'singularity' || workflow.containerEngine == 'apptainer' ? task.ext.containers.get('singularity') : task.ext.containers.get('docker')}"
+
+
+    input:
+    tuple val(meta), path(assembly)
+
+    output:
+    tuple val(meta), path("*.txt"), emit: report
+    path "versions.yml", emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    abricate $assembly $args --threads $task.cpus > ${prefix}.txt
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        abricate: \$(echo \$(abricate --version 2>&1) | sed 's/^.*abricate //' )
+    END_VERSIONS
+    """
+}

nextflow.config

@@ -123,7 +123,9 @@ params {
     max_cpus                   = 16
     max_time                   = '240.h'
 
-    abricate_params {
+    abricate {
+        singularity = "https://depot.galaxyproject.org/singularity/abricate%3A1.0.1--ha8f3691_1"
+        docker = "quay.io/biocontainers/abricate:1.0.1--ha8f3691_1"
         args = ""
         report_tag = "Abricate"
         header_p = true

nextflow_schema.json

@@ -1414,20 +1414,6 @@
             "type": "integer",
             "default": 100
         },
-        "abricate_params.args": {
-            "type": "string",
-            "hidden": true
-        },
-        "abricate_params.report_tag": {
-            "type": "string",
-            "default": "Abricate",
-            "hidden": true
-        },
-        "abricate_params.header_p": {
-            "type": "boolean",
-            "default": true,
-            "hidden": true
-        },
         "raw_reads.high_precision": {
             "type": "boolean",
             "hidden": true
@@ -1731,26 +1717,6 @@
             "default": true,
             "hidden": true
         },
-        "shigatyper.docker": {
-            "type": "string",
-            "default": "quay.io/biocontainers/shigatyper:2.0.1--pyhdfd78af_0",
-            "hidden": true
-        },
-        "shigatyper.tsv_ext": {
-            "type": "string",
-            "default": ".tsv",
-            "hidden": true
-        },
-        "shigatyper.report_tag": {
-            "type": "string",
-            "default": "Subtyping",
-            "hidden": true
-        },
-        "shigatyper.header_p": {
-            "type": "boolean",
-            "default": true,
-            "hidden": true
-        },
         "kraken_bin.fasta_ext": {
             "type": "string",
             "default": "_binned.fasta.gz",
@@ -2569,11 +2535,6 @@
             "default": "https://depot.galaxyproject.org/singularity/shigeifinder:1.3.2--pyhdfd78af_0",
             "hidden": true
         },
-        "shigatyper.singularity": {
-            "type": "string",
-            "default": "https://depot.galaxyproject.org/singularity/shigatyper%3A2.0.1--pyhdfd78af_0",
-            "hidden": true
-        },
         "flye_read_type": {
             "type": "string",
             "default": "hq",
@@ -2597,6 +2558,38 @@
             "type": "string",
             "default": "docker://python/python:3.10.4-alpine3.16",
             "hidden": true
+        },
+        "abricate.singularity": {
+            "type": "string",
+            "default": "https://depot.galaxyproject.org/singularity/abricate%3A1.0.1--ha8f3691_1",
+            "hidden": true
+        },
+        "abricate.docker": {
+            "type": "string",
+            "default": "quay.io/biocontainers/abricate:1.0.1--ha8f3691_1",
+            "hidden": true
+        },
+        "abricate.args": {
+            "type": "string",
+            "hidden": true
+        },
+        "abricate.report_tag": {
+            "type": "string",
+            "default": "Abricate",
+            "hidden": true
+        },
+        "abricate.header_p": {
+            "type": "string",
+            "default": "true",
+            "hidden": true
+        },
+        "shigeifinder.container_version": {
+            "type": "string",
+            "default": "1.3.2"
+        },
+        "shigeifinder.report_tag": {
+            "type": "string",
+            "default": "ShigeifinderSubtyping"
         }
     }
 }

subworkflows/local/annotate_genomes.nf

@@ -1,6 +1,6 @@
 // annotate genomes
 include { BAKTA_ANNOTATE } from '../../modules/local/bakta_annotate.nf'
-include { ABRICATE_RUN } from "../../modules/nf-core/abricate/run/main.nf"
+include { ABRICATE } from "../../modules/local/abricate.nf"
 include { MOBSUITE_RECON } from "../../modules/local/mob_recon.nf"
 include { STARAMR } from "../../modules/local/staramr.nf"
 include { STARAMR_DUMP_DB_VERSIONS } from "../../modules/local/staramr_version.nf"
@@ -46,11 +46,11 @@ workflow ANNOTATE_GENOMES {
     }
 
     if(!params.skip_abricate){
-        abricated = ABRICATE_RUN(contig_data)
+        abricated = ABRICATE(contig_data)
         abricate_report = abricated.report
         versions = versions.mix(abricated.versions)
         reports = reports.mix(abricated.report.map{
-            meta, report -> tuple(meta, params.abricate_params, report);
+            meta, report -> tuple(meta, params.abricate, report);
         })
     }