Merge changes from develop (#48)

* Split out the config profiles (#43)

* Split out the config profiles

* Resolve the conflict using the upstream config

* Refactor channel identifiers and process names (#45)

**Main change**

Processes, channels and workflow names have had its case names changed in order to meet nextflow's community standards.

**Commits**
* Refactor names
* refactor names in the workflows
* Update workflows/bacannot.nf
* Update workflows/bacannot.nf
* Apply suggestions from code review
* Update workflows/bacannot.nf wrt iceberg
* Accomodate code review and fix the channel name
* fix MERGE_ANNOTATIONS process case in line 331

Co-authored-by: Felipe Marques de Almeida <felipemarques89@gmail.com>

* added small dataset test profile

* fixing name of quicktest profile

* fixing urls of testing samplesheets

* removing unnecessary files

* added new action to test the pipeline from PR and updated docs about quicktest

* fixed branch name in github action

* fixing input typo in quicktest profile

* adding more space to workflow env

* fixed action as only 2 threads are available

Co-authored-by: Abhinav Sharma <abhi18av@users.noreply.github.com>

conf/awsbatch.config

@@ -0,0 +1,6 @@
+process {
+    executor = 'awsbatch'
+    queue = 'my-batch-queue'
+    // cpu allocation
+    cpus = params.threads
+}

conf/docker.config

@@ -0,0 +1,45 @@
+// Container usage and permission
+
+docker {
+  enabled      = true
+  runOptions   = '--platform linux/amd64 -u $(id -u):root'
+  fixOwnership = true
+}
+
+
+/*
+                Configuration of Docker usage
+                DO NOT change any of those
+*/
+
+// specific images
+process {
+    withLabel: 'main' {
+        container = 'fmalmeida/bacannot:v3.0'
+    }
+
+    withLabel: 'renv' {
+        container = 'fmalmeida/bacannot:v3.0_renv'
+    }
+
+    withLabel: 'jbrowse' {
+        container = 'fmalmeida/bacannot:jbrowse'
+    }
+
+    withLabel: 'kofam' {
+        container = 'fmalmeida/bacannot:kofamscan'
+    }
+
+    withLabel: 'smash' {
+        container = 'fmalmeida/bacannot:antismash'
+    }
+
+    withLabel: 'unicycler' {
+        container = 'quay.io/biocontainers/unicycler:0.4.8--py38h8162308_3'
+    }
+
+    withLabel: 'flye' {
+        container = 'quay.io/biocontainers/flye:2.9--py39h39abbe0_0'
+    }
+}
+

conf/small_dataset_test_profile.config

@@ -0,0 +1,86 @@
+/*
+ * Configuration File to run fmalmeida/bacannot pipeline.
+ */
+
+/*
+
+                                                    Required Parameters.
+                                            This parameters must always be set
+
+*/
+params {
+
+    /*
+
+            INPUT SAMPLESHEET
+
+    */
+
+// Input data mus be given inside a well-formated samplesheet.
+// We provide a well-formated example at: https://github.com/fmalmeida/test_datasets/raw/main/bacannot_testing_samplesheets/samplesheet.yaml
+//
+// Please read the example samplesheet so you can understand how to properly fill it.
+//
+// It is also documented in the main manual: https://bacannot.readthedocs.io/en/latest/samplesheet.html
+  input = 'https://github.com/fmalmeida/test_datasets/raw/main/bacannot_testing_samplesheets/small_dataset_samplesheet.yml'
+
+    /*
+
+            GENERAL PARAMETERS
+
+     */
+
+// Main output folder name. More than one bacannot annotation can be redirected
+// to the same output parameter. It is good to keep related annotations together.
+// A subdirectory with the filename will be created inside this directory.
+  output = 'EXAMPLE_OUTPUT'
+
+// Number of threads to be used by each software
+  threads = 5
+
+          /*
+           * Resfinder species panel
+           */
+
+// Species panel to be used when annotating with Resfinder.
+// It sets a default for all samples in the samplesheet.
+// If a sample has a different value inside the samplesheet it will overwrite the value for that sample
+// If blank it will not be executed.
+// It must be identical (without the *) as written in their webservice https://cge.cbs.dtu.dk/services/ResFinder/.
+// E.g. 'Escherichia coli'; 'Klebsiella' ...
+  resfinder_species = 'Other'
+
+          /*
+           * Custom databases can be used to annotate additional genes in the genome.
+           * It runs a BLASTn alignment against the genome, therefore, the custom database
+           * MUST be a nucleotide fasta of genes. More than one custom database can be given
+           * separated by commas. Gene headers must be properly formated as described in the
+           * documentation: https://bacannot.readthedocs.io/en/latest/custom-db.html
+           */
+// Custom nucleotide fastas
+  custom_db = 'https://github.com/fmalmeida/test_datasets/raw/main/small_custom_db.fasta'
+
+}
+
+/*
+                                        Configuration of Nextflow Scopes
+ */
+
+//Trace Report
+trace {
+    enabled = true
+    file = "${params.output}" + "/annotation_pipeline_trace.txt"
+    fields = 'task_id,name,status,exit,realtime,cpus,%cpu,memory,%mem,rss'
+}
+
+//Timeline Report
+timeline {
+    enabled = true
+    file = "${params.output}" + "/annotation_pipeline_timeline.html"
+}
+
+//Complete Report
+report {
+    enabled = true
+    file = "${params.output}" + "/annotation_pipeline_nextflow_report.html"
+}

conf/standard.config

@@ -0,0 +1,15 @@
+// Executor
+process {
+    executor = "local"
+}
+
+// QueueSize limit
+if (params.parallel_jobs || params.parallel_jobs != '') {
+    qs = params.parallel_jobs
+}
+executor {
+    name = "local"
+    if (params.parallel_jobs || params.parallel_jobs != '') {
+    queueSize = qs
+    }
+}

test_data/test_profile.config → conf/test_profile.config

@@ -17,12 +17,12 @@ params {
     */
 
 // Input data mus be given inside a well-formated samplesheet.
-// We provide a well-formated example at: https://github.com/fmalmeida/bacannot/blob/master/example_samplesheet.yaml
+// We provide a well-formated example at: https://github.com/fmalmeida/test_datasets/raw/main/bacannot_testing_samplesheets/samplesheet.yaml
 //
 // Please read the example samplesheet so you can understand how to properly fill it.
 //
 // It is also documented in the main manual: https://bacannot.readthedocs.io/en/latest/samplesheet.html
-  input = 'https://github.com/fmalmeida/bacannot/raw/master/test_data/samplesheet.yaml'
+  input = 'https://github.com/fmalmeida/test_datasets/raw/main/bacannot_testing_samplesheets/samplesheet.yaml'
 
     /*
 
@@ -58,7 +58,7 @@ params {
            * documentation: https://bacannot.readthedocs.io/en/latest/custom-db.html
            */
 // Custom nucleotide fastas
-  custom_db = 'https://github.com/fmalmeida/bacannot/raw/master/test_data/small_custom_db.fasta'
+  custom_db = 'https://github.com/fmalmeida/test_datasets/raw/main/small_custom_db.fasta'
 
 }
 

docs/quickstart.rst

@@ -59,9 +59,12 @@ Moreover, we have also made available a few example datasets in the pipeline so
 
 .. code-block:: bash
 
-  # Run the pipeline using the provided test datasets
+  # Run the pipeline using the provided (bigger) test dataset
   nextflow run fmalmeida/bacannot --profile test --threads 10
 
+  # Or run the quick test
+  nextflow run fmalmeida/bacannot --profile quicktest --threads 10
+
 .. note::
 
   Unfortunately, due to file sizes, we could not provide fast5 files for users to check on the methylation step.

modules/KOs/kegg-decoder.nf

@@ -1,4 +1,4 @@
-process kegg_decoder {
+process KEGG_DECODER {
   publishDir "${params.output}/${prefix}/KOfamscan", mode: 'copy'
   tag "${prefix}"
   label 'kofam'

modules/KOs/kofamscan.nf

@@ -1,4 +1,4 @@
-process kofamscan {
+process KOFAMSCAN {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else "$filename"

modules/MGEs/digIS.nf

@@ -1,4 +1,4 @@
-process digis {
+process DIGIS {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else if (filename == "${prefix}.gff") null

modules/MGEs/draw_gis.nf

@@ -1,4 +1,4 @@
-process draw_GIs {
+process DRAW_GIS {
   publishDir "${params.output}/${prefix}/genomic_islands", mode: 'copy', saveAs: { filename ->
     if (filename == "plots") "$filename"
     else null

modules/MGEs/iceberg.nf

@@ -1,4 +1,4 @@
-process iceberg {
+process ICEBERG {
   publishDir "${params.output}/${prefix}/ICEs", mode: 'copy'
   tag "${prefix}"
   label 'main'

modules/MGEs/islandPath_DIMOB.nf

@@ -1,4 +1,4 @@
-process find_GIs {
+process FIND_GIS {
   publishDir "${params.output}/${prefix}/genomic_islands", mode: 'copy'
   errorStrategy 'retry'
   maxRetries 5

modules/MGEs/plasmidfinder.nf

@@ -1,4 +1,4 @@
-process plasmidfinder {
+process PLASMIDFINDER {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename == "plasmidfinder") "plasmids/$filename"
     else null

modules/MGEs/platon.nf

@@ -1,4 +1,4 @@
-process platon {
+process PLATON {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else if (filename == "platon") "plasmids/$filename"

modules/assembly/flye.nf

@@ -1,4 +1,4 @@
-process flye {
+process FLYE {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else if (filename == "flye_${prefix}") "assembly"

modules/assembly/unicycler.nf

@@ -1,4 +1,4 @@
-process unicycler {
+process UNICYCLER {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else if (filename == "unicycler_${prefix}") "assembly"

modules/generic/antismash.nf

@@ -1,4 +1,4 @@
-process antismash {
+process ANTISMASH {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else "$filename"

modules/generic/barrnap.nf

@@ -1,4 +1,4 @@
-process barrnap {
+process BARRNAP {
    publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
      if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
      else "rRNA/$filename"

modules/generic/compute_gc.nf

@@ -1,4 +1,4 @@
-process compute_gc {
+process COMPUTE_GC {
   tag "${prefix}"
   label 'main'
 

modules/generic/custom_blast.nf

@@ -1,4 +1,4 @@
-process custom_blast {
+process CUSTOM_BLAST {
   publishDir "${params.output}/${prefix}/custom_annotations/${customDB.baseName}", mode: 'copy'
   tag "${prefix}"
   label 'main'

modules/generic/custom_blast_report.nf

@@ -1,4 +1,4 @@
-process custom_blast_report {
+process CUSTOM_BLAST_REPORT {
   publishDir "${params.output}/${prefix}/report_files/custom_databases", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf(".html") > 0) "report_${customDB}.html"
     else "$filename"

modules/generic/genome_mask.nf

@@ -1,4 +1,4 @@
-process masking_genome {
+process MASKING_GENOME {
   publishDir "${params.output}/${prefix}", mode: 'copy',
   saveAs: {filename ->
   //This line saves the files with specific sufixes in specific folders

modules/generic/gff2gbk.nf

@@ -1,4 +1,4 @@
-process gff2gbk {
+process GFF2GBK {
   publishDir "${params.output}/${prefix}/gbk", mode: 'copy'
   label 'main'
   tag "${prefix}"

modules/generic/gff2sql.nf

@@ -1,4 +1,4 @@
-process create_sql {
+process CREATE_SQL {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf(".sqlite") > 0) "sqldb/$filename"
     else "$filename"

modules/generic/jbrowse.nf

@@ -1,4 +1,4 @@
-process jbrowse {
+process JBROWSE {
   publishDir "${params.output}/${prefix}/jbrowse", mode: 'copy'
   label 'jbrowse'
   tag "${prefix}"

modules/generic/mash.nf

@@ -1,4 +1,4 @@
-process refseq_masher {
+process REFSEQ_MASHER {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else "refseq_masher/$filename"

modules/generic/merge_annotations.nf

@@ -1,4 +1,4 @@
-process merge_annotations {
+process MERGE_ANNOTATIONS {
   publishDir "${params.output}/${prefix}/gffs", mode: 'copy'
   label 'renv'
   tag "${prefix}"

modules/generic/merge_gff.nf

@@ -1,4 +1,4 @@
-process gff_merge {
+process GFF_MERGE {
   publishDir "${params.output}/${prefix}/gffs", mode: 'copy'
   label 'main'
   tag "${prefix}"

modules/generic/methylation.nf

@@ -1,4 +1,4 @@
-process call_methylation {
+process CALL_METHYLATION {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else "methylations/$filename"

modules/generic/mlst.nf

@@ -1,4 +1,4 @@
-process mlst {
+process MLST {
    publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
      if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
      else "MLST/$filename"

modules/generic/prokka.nf

@@ -1,4 +1,4 @@
-process prokka {
+process PROKKA {
     publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
       if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
       else if (filename == "annotation") "$filename"

modules/generic/reports.nf

@@ -1,4 +1,4 @@
-process report {
+process REPORT {
   publishDir "${params.output}/${prefix}/report_files", mode: 'copy'
   label 'renv'
   tag "${prefix}"

modules/generic/sequenceserver.nf

@@ -1,4 +1,4 @@
-process sequenceserver {
+process SEQUENCESERVER {
     publishDir "${params.output}/${prefix}/SequenceServerDBs", mode: 'copy'
     tag "${prefix}"
     label 'main'
@@ -23,4 +23,4 @@ process sequenceserver {
     # proteins
     makeblastdb -in $proteins -dbtype prot -title "${prefix} proteins" -parse_seqids
     """
-}
+}

modules/prophages/phast.nf

@@ -1,4 +1,4 @@
-process phast {
+process PHAST {
   publishDir "${params.output}/${prefix}/prophages/phast_db", mode: 'copy'
   tag "${prefix}"
   label 'main'

modules/prophages/phigaro.nf

@@ -1,4 +1,4 @@
-process phigaro {
+process PHIGARO {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename == "out.phg") null
     else if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"

modules/prophages/phispy.nf

@@ -1,4 +1,4 @@
-process phispy {
+process PHISPY {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else if (filename == "PhiSpy") "prophages/$filename"

modules/resistance/amrfinder.nf

@@ -1,4 +1,4 @@
-process amrfinder {
+process AMRFINDER {
   publishDir "${params.output}/${prefix}", mode: 'copy', saveAs: { filename ->
     if (filename.indexOf("_version.txt") > 0) "tools_versioning/$filename"
     else "resistance/AMRFinderPlus/$filename"

modules/resistance/argminer.nf

@@ -1,4 +1,4 @@
-process argminer {
+process ARGMINER {
   publishDir "${params.output}/${prefix}/resistance/ARGMiner", mode: 'copy'
   tag "${prefix}"
   label 'main'

modules/resistance/resfinder.nf

@@ -1,4 +1,4 @@
-process resfinder {
+process RESFINDER {
   publishDir "${params.output}/${prefix}/resistance", mode: 'copy'
   tag "${prefix}"
   label 'main'