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 1/6] 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

From ba53e09b6416305e12b071e16e604e9a96f94d59 Mon Sep 17 00:00:00 2001
From: jasmezz <jasmin.frangenberg@hki-jena.de>
Date: Thu, 9 Jun 2022 15:37:35 +0200
Subject: [PATCH 2/6] Implement suggestions from code review

---
 modules/ampir/main.nf        | 15 ++++++++-------
 modules/ampir/meta.yml       | 14 +++++++-------
 tests/modules/ampir/main.nf  |  4 +---
 tests/modules/ampir/test.yml | 10 ++++++----
 4 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/modules/ampir/main.nf b/modules/ampir/main.nf
index e1720b83..412317b7 100644
--- a/modules/ampir/main.nf
+++ b/modules/ampir/main.nf
@@ -11,11 +11,11 @@ process AMPIR {
     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
+    tuple val(meta), path("*.faa"), emit: amps_faa
+    tuple val(meta), path("*.csv"), emit: amps_csv
+    path "versions.yml"           , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -27,10 +27,11 @@ process AMPIR {
     #!/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')
+    protein_seqs <- read_faa('${faa}')
+    prediction <- predict_amps(protein_seqs, model = '${model}')
+    prediction <- protein_seqs[which(prediction\$prob_AMP >= as.integer(${cut_off})), ]
+    df_to_faa(protein_seqs, "${prefix}.faa")
+    write.table(prediction, file = "${prefix}.csv", row.names = FALSE, quote = FALSE, dec = '.')
 
     version_file_path <- "versions.yml"
     version_ampir <- paste(unlist(packageVersion("ampir")), collapse = ".")
diff --git a/modules/ampir/meta.yml b/modules/ampir/meta.yml
index b37ace09..30e55e99 100644
--- a/modules/ampir/meta.yml
+++ b/modules/ampir/meta.yml
@@ -8,7 +8,7 @@ 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"
+      documentation: "https://cran.r-project.org/web/packages/ampir/index.html"
       tool_dev_url: "https://github.com/Legana/ampir"
       doi: "10.1093/bioinformatics/btaa653"
       licence: ["GPL v2"]
@@ -42,14 +42,14 @@ output:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  - amps:
+  - amps_faa:
       type: file
-      description: File containing AMP predictions
-      pattern: "prediction.fasta"
-  - output_name:
-      type: value
-      description: File name of the FASTA output file
+      description: File containing AMP predictions in amino acid FASTA format
       pattern: "*.{faa,fasta}"
+  - amps_csv:
+      type: file
+      description: File containing AMP predictions in CSV format
+      pattern: "*.csv"
 
 authors:
   - "@jasmezz"
diff --git a/tests/modules/ampir/main.nf b/tests/modules/ampir/main.nf
index 769ebb3f..cc7b07c8 100644
--- a/tests/modules/ampir/main.nf
+++ b/tests/modules/ampir/main.nf
@@ -14,7 +14,5 @@ workflow test_ampir {
 
     model = "precursor"
 
-    output_name = "prediction.fasta"
-
-    AMPIR ( fasta, cut_off, model, output_name )
+    AMPIR ( fasta, cut_off, model )
 }
diff --git a/tests/modules/ampir/test.yml b/tests/modules/ampir/test.yml
index 663ba675..40bedd37 100644
--- a/tests/modules/ampir/test.yml
+++ b/tests/modules/ampir/test.yml
@@ -1,9 +1,11 @@
-- name: "ampir"
-  command: nextflow run ./tests/modules/ampir -entry test_ampir -c ./tests/config/nextflow.config -c ./tests/modules/ampir/nextflow.config
+- name: ampir test_ampir
+  command: nextflow run ./tests/modules/ampir -entry test_ampir -c ./tests/config/nextflow.config  -c ./tests/modules/ampir/nextflow.config
   tags:
-    - "ampir"
+    - ampir
   files:
-    - path: output/ampir/prediction.fasta
+    - path: output/ampir/test.csv
+      md5sum: 063fd8866f6a669457d7a49404fb449f
+    - path: output/ampir/test.faa
       md5sum: e605d38752fd90261c924d51f7007189
     - path: output/ampir/versions.yml
       md5sum: 4a11d25b8a904a7ffb34ae88f6826888

From ecf1d146ab3c3a60fdc5daf0fee18a26c9105c24 Mon Sep 17 00:00:00 2001
From: jasmezz <jasmin.frangenberg@hki-jena.de>
Date: Thu, 9 Jun 2022 16:59:00 +0200
Subject: [PATCH 3/6] Add full user options for AMPir

---
 modules/ampir/main.nf        | 15 +++++++++------
 modules/ampir/meta.yml       |  8 ++++++--
 tests/modules/ampir/main.nf  |  8 +++++---
 tests/modules/ampir/test.yml |  4 ++--
 4 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/modules/ampir/main.nf b/modules/ampir/main.nf
index 412317b7..11fc88cf 100644
--- a/modules/ampir/main.nf
+++ b/modules/ampir/main.nf
@@ -9,8 +9,9 @@ process AMPIR {
 
     input:
     tuple val(meta), path(faa)
-    val cut_off
     val model
+    val min_length
+    val min_probability
 
     output:
     tuple val(meta), path("*.faa"), emit: amps_faa
@@ -23,15 +24,17 @@ process AMPIR {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    min_length = ("${min_length}" == "[]") ? "": " min_len = as.integer(${min_length})," // Fall back to AMPir default value if none specified
     """
     #!/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(${cut_off})), ]
-    df_to_faa(protein_seqs, "${prefix}.faa")
-    write.table(prediction, file = "${prefix}.csv", row.names = FALSE, quote = FALSE, dec = '.')
+    input_seqs <- read_faa('${faa}')
+    prediction <- predict_amps(input_seqs,${min_length} model = '${model}')
+    prediction <- prediction[which(prediction\$prob_AMP >= as.numeric(${min_probability})), ]
+    output_seqs <- input_seqs[row.names(prediction), ]
+    write.table(prediction, file = "${prefix}.csv", row.names = FALSE, sep = ";", quote = FALSE, dec = '.')
+    df_to_faa(output_seqs, "${prefix}.faa")
 
     version_file_path <- "versions.yml"
     version_ampir <- paste(unlist(packageVersion("ampir")), collapse = ".")
diff --git a/modules/ampir/meta.yml b/modules/ampir/meta.yml
index 30e55e99..0b3850c0 100644
--- a/modules/ampir/meta.yml
+++ b/modules/ampir/meta.yml
@@ -25,9 +25,13 @@ input:
       pattern: "*.{faa,fasta}"
   - model:
       type: value
-      description: Model for AMP prediction
+      description: Built-in model for AMP prediction
       pattern: "{precursor,mature}"
-  - cut_off:
+  - min_length:
+      type: value
+      description: Minimum protein length for which predictions will be generated
+      pattern: "[0-9]+"
+  - min_probability:
       type: value
       description: Cut-off for AMP prediction
       pattern: "[0-9][0-9]"
diff --git a/tests/modules/ampir/main.nf b/tests/modules/ampir/main.nf
index cc7b07c8..bee2ff90 100644
--- a/tests/modules/ampir/main.nf
+++ b/tests/modules/ampir/main.nf
@@ -10,9 +10,11 @@ workflow test_ampir {
               file(params.test_data['candidatus_portiera_aleyrodidarum']['genome']['proteome_fasta'], checkIfExists: true),
     ]
 
-    cut_off = "80"
-
     model = "precursor"
 
-    AMPIR ( fasta, cut_off, model )
+    min_length = []
+
+    min_probability = "0.7"
+
+    AMPIR ( fasta, model, min_length, min_probability )
 }
diff --git a/tests/modules/ampir/test.yml b/tests/modules/ampir/test.yml
index 40bedd37..4077ef14 100644
--- a/tests/modules/ampir/test.yml
+++ b/tests/modules/ampir/test.yml
@@ -4,8 +4,8 @@
     - ampir
   files:
     - path: output/ampir/test.csv
-      md5sum: 063fd8866f6a669457d7a49404fb449f
+      md5sum: a3b3152373a8add3613ace8c71073e68
     - path: output/ampir/test.faa
-      md5sum: e605d38752fd90261c924d51f7007189
+      md5sum: 0435609144022c55ac196db053f0df89
     - path: output/ampir/versions.yml
       md5sum: 4a11d25b8a904a7ffb34ae88f6826888

From 5841f11edbbae29f4904a2994e53d1e81233efc4 Mon Sep 17 00:00:00 2001
From: jasmezz <jasmin.frangenberg@hki-jena.de>
Date: Thu, 9 Jun 2022 18:15:27 +0200
Subject: [PATCH 4/6] Replace MD5 with contains check

---
 tests/modules/ampir/test.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/modules/ampir/test.yml b/tests/modules/ampir/test.yml
index 4077ef14..3c6a2f64 100644
--- a/tests/modules/ampir/test.yml
+++ b/tests/modules/ampir/test.yml
@@ -4,7 +4,7 @@
     - ampir
   files:
     - path: output/ampir/test.csv
-      md5sum: a3b3152373a8add3613ace8c71073e68
+      contains: ["seq_name;seq_aa;prob_AMP", "WP_014895017.1"]
     - path: output/ampir/test.faa
       md5sum: 0435609144022c55ac196db053f0df89
     - path: output/ampir/versions.yml

From 39388abc0473ca5c7a282ec0ea7f63ba7c439053 Mon Sep 17 00:00:00 2001
From: jasmezz <jasmin.frangenberg@hki-jena.de>
Date: Fri, 10 Jun 2022 12:54:39 +0200
Subject: [PATCH 5/6] Add file name collision check + TSV output

---
 modules/ampir/main.nf        | 5 +++--
 modules/ampir/meta.yml       | 6 +++---
 tests/modules/ampir/test.yml | 4 ++--
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/modules/ampir/main.nf b/modules/ampir/main.nf
index 11fc88cf..97ea0bbb 100644
--- a/modules/ampir/main.nf
+++ b/modules/ampir/main.nf
@@ -15,7 +15,7 @@ process AMPIR {
 
     output:
     tuple val(meta), path("*.faa"), emit: amps_faa
-    tuple val(meta), path("*.csv"), emit: amps_csv
+    tuple val(meta), path("*.tsv"), emit: amps_csv
     path "versions.yml"           , emit: versions
 
     when:
@@ -25,6 +25,7 @@ process AMPIR {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     min_length = ("${min_length}" == "[]") ? "": " min_len = as.integer(${min_length})," // Fall back to AMPir default value if none specified
+    if ("$faa" == "${prefix}.faa") error "Input and output names are the same, set prefix in module configuration to disambiguate!"
     """
     #!/usr/bin/env Rscript
     library(ampir)
@@ -33,7 +34,7 @@ process AMPIR {
     prediction <- predict_amps(input_seqs,${min_length} model = '${model}')
     prediction <- prediction[which(prediction\$prob_AMP >= as.numeric(${min_probability})), ]
     output_seqs <- input_seqs[row.names(prediction), ]
-    write.table(prediction, file = "${prefix}.csv", row.names = FALSE, sep = ";", quote = FALSE, dec = '.')
+    write.table(prediction, file = "${prefix}.tsv", row.names = FALSE, sep = "\t", quote = FALSE, dec = '.')
     df_to_faa(output_seqs, "${prefix}.faa")
 
     version_file_path <- "versions.yml"
diff --git a/modules/ampir/meta.yml b/modules/ampir/meta.yml
index 0b3850c0..33189d66 100644
--- a/modules/ampir/meta.yml
+++ b/modules/ampir/meta.yml
@@ -49,11 +49,11 @@ output:
   - amps_faa:
       type: file
       description: File containing AMP predictions in amino acid FASTA format
-      pattern: "*.{faa,fasta}"
+      pattern: "*.{faa}"
   - amps_csv:
       type: file
-      description: File containing AMP predictions in CSV format
-      pattern: "*.csv"
+      description: File containing AMP predictions in TSV format
+      pattern: "*.tsv"
 
 authors:
   - "@jasmezz"
diff --git a/tests/modules/ampir/test.yml b/tests/modules/ampir/test.yml
index 3c6a2f64..54921e9a 100644
--- a/tests/modules/ampir/test.yml
+++ b/tests/modules/ampir/test.yml
@@ -3,8 +3,8 @@
   tags:
     - ampir
   files:
-    - path: output/ampir/test.csv
-      contains: ["seq_name;seq_aa;prob_AMP", "WP_014895017.1"]
+    - path: output/ampir/test.tsv
+      contains: ["seq_name\tseq_aa\tprob_AMP", "WP_014895017.1"]
     - path: output/ampir/test.faa
       md5sum: 0435609144022c55ac196db053f0df89
     - path: output/ampir/versions.yml

From 01d4a1fa3a0f6c87b02a50f450f5e85464eaa7e4 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Fri, 10 Jun 2022 14:46:58 +0200
Subject: [PATCH 6/6] Apply suggestions from code review

---
 modules/ampir/main.nf  | 2 +-
 modules/ampir/meta.yml | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/modules/ampir/main.nf b/modules/ampir/main.nf
index 97ea0bbb..57e20902 100644
--- a/modules/ampir/main.nf
+++ b/modules/ampir/main.nf
@@ -15,7 +15,7 @@ process AMPIR {
 
     output:
     tuple val(meta), path("*.faa"), emit: amps_faa
-    tuple val(meta), path("*.tsv"), emit: amps_csv
+    tuple val(meta), path("*.tsv"), emit: amps_tsv
     path "versions.yml"           , emit: versions
 
     when:
diff --git a/modules/ampir/meta.yml b/modules/ampir/meta.yml
index 33189d66..7569ca69 100644
--- a/modules/ampir/meta.yml
+++ b/modules/ampir/meta.yml
@@ -50,7 +50,7 @@ output:
       type: file
       description: File containing AMP predictions in amino acid FASTA format
       pattern: "*.{faa}"
-  - amps_csv:
+  - amps_tsv:
       type: file
       description: File containing AMP predictions in TSV format
       pattern: "*.tsv"