WIP: enable in epi2me

Dockerfile

@@ -0,0 +1,9 @@
+FROM condaforge/mambaforge:latest AS conda
+
+COPY environment.yml .
+
+RUN /opt/conda/bin/mamba env create -f /environment.yml
+
+ENV PATH=/opt/conda/envs/artic_rsv/bin:$PATH
+
+CMD ["/bin/bash"]

environment.yml

@@ -0,0 +1,15 @@
+name: artic_rsv
+channels:
+  - bioconda
+  - conda-forge
+  - defaults
+dependencies:
+  - python<=3.10
+  - biopython
+  - pysam
+  - nextflow
+  - bedtools
+  - artic
+  - pip:
+      - git+https://github.com/Desperate-Dan/ampli_clean.git
+

clean_cons.nf → main.nf

@@ -1,12 +1,5 @@
-// Declare syntax version
-nextflow.enable.dsl=2
-
-// Script parameters
-params.refs = "/home/dmmalone/RSV_analysis/testing_ground/RSV_refs.fasta"
-params.bed = "/home/dmmalone/RSV_analysis/testing_ground/RSVA.primer.bed"
-params.fastqIn = "/home/dmmalone/RSV_analysis/RSVLO_A_Run2/fastq_pass/*/*"
-
 process ampliClean {
+  container "${params.wf.container}@${params.wf.container_sha}"
   input:
     tuple val(key), file(samples)
     path refs
@@ -26,6 +19,7 @@ process ampliClean {
 }
 
 process articMinion {
+  container "${params.wf.container}@${params.wf.container_sha}"
   input:
     path input_reads
     val base
@@ -39,9 +33,9 @@ process articMinion {
 }
 
 workflow {
-  def ref_ch = Channel.value(params.refs)
-  def bed_ch = Channel.value(params.bed)
-  def fastqIn_ch = Channel.fromPath(params.fastqIn, checkIfExists:true) 
+  ref_ch = file(params.refs)
+  bed_ch = file(params.bed)
+  fastqIn_ch = Channel.fromPath(params.fastq, checkIfExists:true)
     | map { file -> 
       def key = file.parent.toString().tokenize('/').last()
       return tuple(key, file)

nextflow.config

@@ -0,0 +1,208 @@
+//
+// Notes to End Users.
+//
+// The workflow should run without editing this configuration file,
+// however there may be instances in which you wish to edit this
+// file for compute performance or other reasons. Please see:
+//
+//   https://nextflow.io/docs/latest/config.html#configuration
+//
+// for further help editing this file.
+
+params {
+    help = false
+    version = false
+
+    refs = null
+    bed = null
+    fastq = null
+
+    wf {
+          example_cmd = [
+              "--fastq test_data/barcode01/reads.fastq.gz",
+          ]
+          agent = null
+          container = "rmcolq/artic_rsv"
+          container_sha = "sha256:68100b5e1d4dc995d707ee716bda9373e827879904c381b59a71105476c36f58"
+        }
+}
+
+
+manifest {
+    name            = 'Desperate-Dan/RSV_nextflow'
+    author          = 'Daniel Maloney'
+    homePage        = 'https://github.com/Desperate-Dan/RSV_nextflow/'
+    description     = 'Generate assemblies from RSV sequence data generated using the ARTIC primer scheme.'
+    mainScript      = 'main.nf'
+    nextflowVersion = '>=20.10.0'
+    version         = 'v0.0.1'
+}
+
+profiles {
+    standard {
+        docker {
+            enabled = true
+            // this ensures container is run as host user and group, but
+            //    also adds host user to the within-container group
+            runOptions = "--user \$(id -u):\$(id -g) --group-add 100"
+        }
+    }
+    debug {
+        dumpHashes             = true
+        process.beforeScript   = 'echo $HOSTNAME'
+        cleanup = false
+    }
+    conda {
+        conda.enabled          = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    mamba {
+        conda.enabled          = true
+        conda.useMamba         = true
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    docker {
+        docker.enabled         = true
+        docker.registry        = 'docker.io'
+        docker.userEmulation   = true
+        conda.enabled          = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    arm {
+        docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
+    }
+    singularity {
+        singularity.enabled    = true
+        singularity.autoMounts = true
+        conda.enabled          = false
+        docker.enabled         = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    podman {
+        podman.enabled         = true
+        podman.registry        = 'quay.io'
+        conda.enabled          = false
+        docker.enabled         = false
+        singularity.enabled    = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    shifter {
+        shifter.enabled        = true
+        conda.enabled          = false
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        charliecloud.enabled   = false
+        apptainer.enabled      = false
+    }
+    charliecloud {
+        charliecloud.enabled   = true
+        conda.enabled          = false
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        apptainer.enabled      = false
+    }
+    apptainer {
+        apptainer.enabled      = true
+        conda.enabled          = false
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
+    gitpod {
+        executor.name          = 'local'
+        executor.cpus          = 16
+        executor.memory        = 60.GB
+    }
+    test      { includeConfig 'conf/test.config'      }
+    test_full { includeConfig 'conf/test_full.config' }
+}
+
+
+// Export these variables to prevent local Python/R libraries from conflicting with those in the container
+// The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
+// See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.
+
+env {
+    PYTHONNOUSERSITE = 1
+    R_PROFILE_USER   = "/.Rprofile"
+    R_ENVIRON_USER   = "/.Renviron"
+    JULIA_DEPOT_PATH = "/usr/local/share/julia"
+}
+
+// Capture exit codes from upstream processes when piping
+process.shell = ['/bin/bash', '-euo', 'pipefail']
+
+timeline {
+    enabled = true
+    file    = "${params.tracedir}/execution_timeline_${params.unique_id}.html"
+}
+report {
+    enabled = true
+    file    = "${params.tracedir}/execution_report_${params.unique_id}.html"
+}
+trace {
+    enabled = true
+    file    = "${params.tracedir}/execution_trace_${params.unique_id}.txt"
+}
+dag {
+    enabled = true
+    file    = "${params.tracedir}/pipeline_dag_${params.unique_id}.html"
+}
+
+
+// Function to ensure that resource requirements don't go beyond
+// a maximum limit
+def check_max(obj, type) {
+    if (type == 'memory') {
+        try {
+            if (obj.compareTo(params.max_memory as nextflow.util.MemoryUnit) == 1)
+                return params.max_memory as nextflow.util.MemoryUnit
+            else
+                return obj
+        } catch (all) {
+            println "   ### ERROR ###   Max memory '${params.max_memory}' is not valid! Using default value: $obj"
+            return obj
+        }
+    } else if (type == 'time') {
+        try {
+            if (obj.compareTo(params.max_time as nextflow.util.Duration) == 1)
+                return params.max_time as nextflow.util.Duration
+            else
+                return obj
+        } catch (all) {
+            println "   ### ERROR ###   Max time '${params.max_time}' is not valid! Using default value: $obj"
+            return obj
+        }
+    } else if (type == 'cpus') {
+        try {
+            return Math.min( obj, params.max_cpus as int )
+        } catch (all) {
+            println "   ### ERROR ###   Max cpus '${params.max_cpus}' is not valid! Using default value: $obj"
+            return obj
+        }
+    }
+}