From 77b5986463042de584c823976299d4b498212988 Mon Sep 17 00:00:00 2001
From: jasmezz <jasmin.frangenberg@hki-jena.de>
Date: Wed, 25 May 2022 13:27:10 +0200
Subject: [PATCH] Create ampir module

---
 modules/ampir/main.nf               | 43 ++++++++++++++++++++++
 modules/ampir/meta.yml              | 55 +++++++++++++++++++++++++++++
 tests/config/pytest_modules.yml     |  4 +++
 tests/modules/ampir/main.nf         | 20 +++++++++++
 tests/modules/ampir/nextflow.config |  5 +++
 tests/modules/ampir/test.yml        |  9 +++++
 6 files changed, 136 insertions(+)
 create mode 100644 modules/ampir/main.nf
 create mode 100644 modules/ampir/meta.yml
 create mode 100644 tests/modules/ampir/main.nf
 create mode 100644 tests/modules/ampir/nextflow.config
 create mode 100644 tests/modules/ampir/test.yml

diff --git a/modules/ampir/main.nf b/modules/ampir/main.nf
new file mode 100644
index 00000000..e1720b83
--- /dev/null
+++ b/modules/ampir/main.nf
@@ -0,0 +1,43 @@
+process AMPIR {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "conda-forge::r-ampir=1.1.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/r-ampir:1.1.0':
+        'quay.io/biocontainers/r-ampir:1.1.0' }"
+
+    input:
+    tuple val(meta), path(faa)
+    val cut_off
+    val model
+    val output_name
+
+    output:
+    tuple val(meta), path(output_name)  , emit: amps
+    path "versions.yml"                 , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    #!/usr/bin/env Rscript
+    library(ampir)
+
+    protein_seqs <- read_faa("${faa}")
+    prediction <- predict_amps(protein_seqs, model = '$model')
+    prediction <- protein_seqs[which(prediction\$prob_AMP >= as.integer($cut_off)), ]
+    df_to_faa(protein_seqs, '$output_name')
+
+    version_file_path <- "versions.yml"
+    version_ampir <- paste(unlist(packageVersion("ampir")), collapse = ".")
+    f <- file(version_file_path, "w")
+    writeLines('"${task.process}":', f)
+    writeLines("    ampir: ", f, sep = "")
+    writeLines(version_ampir, f)
+    close(f)
+    """
+}
diff --git a/modules/ampir/meta.yml b/modules/ampir/meta.yml
new file mode 100644
index 00000000..b37ace09
--- /dev/null
+++ b/modules/ampir/meta.yml
@@ -0,0 +1,55 @@
+name: "ampir"
+description: A fast and user-friendly method to predict antimicrobial peptides (AMPs) from any given size protein dataset. ampir uses a supervised statistical machine learning approach to predict AMPs.
+keywords:
+  - ampir
+  - amp
+  - antimicrobial peptide prediction
+tools:
+  - "ampir":
+      description: "A toolkit to predict antimicrobial peptides from protein sequences on a genome-wide scale."
+      homepage: "https://github.com/Legana/ampir"
+      documentation: "https://github.com/Legana/ampir"
+      tool_dev_url: "https://github.com/Legana/ampir"
+      doi: "10.1093/bioinformatics/btaa653"
+      licence: ["GPL v2"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - faa:
+      type: file
+      description: FASTA file containing amino acid sequences
+      pattern: "*.{faa,fasta}"
+  - model:
+      type: value
+      description: Model for AMP prediction
+      pattern: "{precursor,mature}"
+  - cut_off:
+      type: value
+      description: Cut-off for AMP prediction
+      pattern: "[0-9][0-9]"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - amps:
+      type: file
+      description: File containing AMP predictions
+      pattern: "prediction.fasta"
+  - output_name:
+      type: value
+      description: File name of the FASTA output file
+      pattern: "*.{faa,fasta}"
+
+authors:
+  - "@jasmezz"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 57f1a8a8..442a3cd4 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -26,6 +26,10 @@ allelecounter:
   - modules/allelecounter/**
   - tests/modules/allelecounter/**
 
+ampir:
+  - modules/ampir/**
+  - tests/modules/ampir/**
+
 amplify/predict:
   - modules/amplify/predict/**
   - tests/modules/amplify/predict/**
diff --git a/tests/modules/ampir/main.nf b/tests/modules/ampir/main.nf
new file mode 100644
index 00000000..769ebb3f
--- /dev/null
+++ b/tests/modules/ampir/main.nf
@@ -0,0 +1,20 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { AMPIR } from '../../../modules/ampir/main.nf'
+
+workflow test_ampir {
+
+    fasta = [ [ id:'test', single_end:false ], // meta map
+              file(params.test_data['candidatus_portiera_aleyrodidarum']['genome']['proteome_fasta'], checkIfExists: true),
+    ]
+
+    cut_off = "80"
+
+    model = "precursor"
+
+    output_name = "prediction.fasta"
+
+    AMPIR ( fasta, cut_off, model, output_name )
+}
diff --git a/tests/modules/ampir/nextflow.config b/tests/modules/ampir/nextflow.config
new file mode 100644
index 00000000..50f50a7a
--- /dev/null
+++ b/tests/modules/ampir/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file
diff --git a/tests/modules/ampir/test.yml b/tests/modules/ampir/test.yml
new file mode 100644
index 00000000..663ba675
--- /dev/null
+++ b/tests/modules/ampir/test.yml
@@ -0,0 +1,9 @@
+- name: "ampir"
+  command: nextflow run ./tests/modules/ampir -entry test_ampir -c ./tests/config/nextflow.config -c ./tests/modules/ampir/nextflow.config
+  tags:
+    - "ampir"
+  files:
+    - path: output/ampir/prediction.fasta
+      md5sum: e605d38752fd90261c924d51f7007189
+    - path: output/ampir/versions.yml
+      md5sum: 4a11d25b8a904a7ffb34ae88f6826888