refactor: Switch to SRA direct download for samples

In order to use nf-validation infrastructure, we have to have pre-commit
hooks installed, so add some basic hooks

.pre-commit-config.yaml

@@ -0,0 +1,5 @@
+repos:
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v2.7.1"
+    hooks:
+      - id: prettier

assets/schema_input.json

@@ -0,0 +1,23 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema",
+  "$id": "https://raw.githubusercontent.com/nf-core/taxprofiler/master/assets/schema_input.json",
+  "title": "haplotyper battle royale pipeline - params.input schema",
+  "description": "Schema for the file provided with params.input",
+  "type": "array",
+  "items": {
+    "type": "object",
+    "properties": {
+      "sample": {
+        "type": "string",
+        "pattern": "^\\S+$",
+        "errorMessage": "Sample name must be provided and cannot contain spaces"
+      },
+      "sra": {
+        "type": "string",
+        "pattern": "^(((SR|ER|DR)[APRSX])|(SAM(N|EA|D))|(PRJ(NA|EB|DB))|(GS[EM])|(syn))(\\d+)$",
+        "errorMessage": "Please provide a valid SRA, ENA, DDBJ or GEO identifier"
+      }
+    },
+    "required": ["sample", "sra"]
+  }
+}

main.nf

@@ -1,7 +1,10 @@
 #!/usr/bin/env nextflow
 
+include { validateParameters; fromSamplesheet } from 'plugin/nf-validation'
+
 include { CLIQUESNV } from './modules/cliquesnv'
 include { EFETCH } from './modules/efetch'
+include { FASTERQ_DUMP } from './modules/fasterq_dump'
 include { HAPLINK_HAPLOTYPES as HAPLINK_ML_HAPLOTYPES } from './modules/haplink/haplotypes'
 include { HAPLINK_HAPLOTYPES as HAPLINK_RAW_HAPLOTYPES } from './modules/haplink/haplotypes'
 include { HAPLINK_SEQUENCES } from './modules/haplink/sequences'
@@ -15,12 +18,18 @@ include { VIQUAS } from './modules/viquas'
 
 workflow {
 
+    validateParameters()
+
     Channel
-        .fromPath("*.fastq.gz")
-        .map { file -> tuple(file.simpleName, file) }
+        .fromSamplesheet("input")
+        .set { ch_sras }
+
+    FASTERQ_DUMP( ch_sras )
+    FASTERQ_DUMP
+        .out
         .set { ch_input }
 
-    EFETCH('NC_036618.1')
+    EFETCH("${params.reference}")
     EFETCH
         .out
         .set { ch_reference }

modules/cliquesnv/main.nf

@@ -13,7 +13,7 @@ process CLIQUESNV {
     tuple val(prefix), path("*.json")
     tuple val(prefix), path("*.fasta")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/efetch/main.nf

@@ -7,7 +7,7 @@ process EFETCH {
     input:
     val(genome)
 
-    publishDir "results", mode: 'copy'
+    publishDir "${params.outdir}", mode: 'copy'
 
     output:
     path 'reference.fasta'

modules/fasterq_dump/main.nf

@@ -0,0 +1,25 @@
+process FASTERQ_DUMP {
+    tag "${prefix} (${sra})"
+    label 'process_single'
+
+    container 'quay.io/biocontainers/sra-tools:3.0.8--h9f5acd7_0'
+
+    input:
+    tuple val(prefix), val(sra)
+
+    output:
+    tuple val(prefix), path("*.fastq.gz")
+
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
+
+    script:
+    """
+    fasterq-dump \\
+            --verbose \\
+            --concatenate-reads \\
+            --stdout \\
+            ${sra} \\
+        | gzip \\
+        > "${prefix}.fastq.gz"
+    """
+}

modules/haplink/haplotypes/main.nf

@@ -12,7 +12,7 @@ process HAPLINK_HAPLOTYPES {
     output:
     tuple val(prefix), path("*.yaml")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/haplink/sequences/main.nf

@@ -12,7 +12,7 @@ process HAPLINK_SEQUENCES {
     output:
     tuple val(prefix), val(method), path("*.fasta")
 
-    publishDir "results/${method}", mode: 'copy'
+    publishDir "${params.outdir}/${method}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/haplink/variants/main.nf

@@ -12,7 +12,7 @@ process HAPLINK_VARIANTS {
     output:
     tuple val(prefix), path("*.vcf")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/minimap2/main.nf

@@ -8,7 +8,7 @@ process MINIMAP2 {
     tuple val(prefix), path(reads)
     path reference
 
-    publishDir "results", mode: 'copy'
+    publishDir "${params.outdir}", mode: 'copy'
 
     output:
     tuple val(prefix), path("*.bam"), path("*.bam.bai")

modules/quasirecomb/main.nf

@@ -11,7 +11,7 @@ process QUASIRECOMB {
     output:
     tuple val(prefix), path("*.fasta")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/shorah/amplicon/main.nf

@@ -13,7 +13,7 @@ process SHORAH_AMPLICON {
     tuple val(prefix), path("*.vcf")
     tuple val(prefix), path("*support.fas")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/shorah/shotgun/main.nf

@@ -13,7 +13,7 @@ process SHORAH_SHOTGUN {
     tuple val(prefix), path("*.vcf")
     tuple val(prefix), path("*support.fas")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

modules/viquas/main.nf

@@ -12,7 +12,7 @@ process VIQUAS {
     output:
     tuple val(prefix), path("*.fa")
 
-    publishDir "results/${task.process}", mode: 'copy'
+    publishDir "${params.outdir}/${task.process}", mode: 'copy'
 
     when:
     task.ext.when == null || task.ext.when

nextflow.config

@@ -1,5 +1,7 @@
 params {
+    input = null
     reference = null
+    outdir = null
 
     // Config options
     config_profile_name = null
@@ -150,6 +152,10 @@ env {
     R_ENVIRON_USER   = "/.Renviron"
 }
 
+plugins {
+    id 'nf-validation'
+}
+
 def check_max(obj, type) {
     if (type == 'memory') {
         try {

nextflow_schema.json

@@ -0,0 +1,166 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema",
+  "$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
+  "title": ". pipeline parameters",
+  "description": "",
+  "type": "object",
+  "definitions": {
+    "input_output_options": {
+      "title": "Input/output options",
+      "type": "object",
+      "fa_icon": "fas fa-terminal",
+      "description": "Define where the pipeline should find input data and save output data.",
+      "required": ["input", "reference", "outdir"],
+      "properties": {
+        "input": {
+          "type": "string",
+          "format": "file-path",
+          "exists": true,
+          "mimetype": "text/csv",
+          "pattern": "^\\S+\\.csv$",
+          "description": "Path to comma-separated file containing information about the samples in the experiment.",
+          "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.",
+          "fa_icon": "fas fa-file-csv",
+          "schema": "assets/schema_input.json"
+        },
+        "reference": {
+          "type": "string",
+          "fa_icon": "fas fa-dna",
+          "description": "NCBI accession number of the reference genome to align reads against"
+        },
+        "outdir": {
+          "type": "string",
+          "format": "directory-path",
+          "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
+          "fa_icon": "fas fa-folder-open"
+        }
+      }
+    },
+    "institutional_config_options": {
+      "title": "Institutional config options",
+      "type": "object",
+      "fa_icon": "fas fa-university",
+      "description": "Parameters used to describe centralised config profiles. These should not be edited.",
+      "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
+      "properties": {
+        "custom_config_version": {
+          "type": "string",
+          "description": "Git commit id for Institutional configs.",
+          "default": "master",
+          "hidden": true,
+          "fa_icon": "fas fa-users-cog"
+        },
+        "custom_config_base": {
+          "type": "string",
+          "description": "Base directory for Institutional configs.",
+          "default": "https://raw.githubusercontent.com/nf-core/configs/master",
+          "hidden": true,
+          "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
+          "fa_icon": "fas fa-users-cog"
+        },
+        "config_profile_name": {
+          "type": "string",
+          "description": "Institutional config name.",
+          "hidden": true,
+          "fa_icon": "fas fa-users-cog"
+        },
+        "config_profile_description": {
+          "type": "string",
+          "description": "Institutional config description.",
+          "hidden": true,
+          "fa_icon": "fas fa-users-cog"
+        },
+        "config_profile_contact": {
+          "type": "string",
+          "description": "Institutional config contact information.",
+          "hidden": true,
+          "fa_icon": "fas fa-users-cog"
+        },
+        "config_profile_url": {
+          "type": "string",
+          "description": "Institutional config URL link.",
+          "hidden": true,
+          "fa_icon": "fas fa-users-cog"
+        }
+      }
+    },
+    "max_job_request_options": {
+      "title": "Max job request options",
+      "type": "object",
+      "fa_icon": "fab fa-acquisitions-incorporated",
+      "description": "Set the top limit for requested resources for any single job.",
+      "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
+      "properties": {
+        "max_cpus": {
+          "type": "integer",
+          "description": "Maximum number of CPUs that can be requested for any single job.",
+          "default": 16,
+          "fa_icon": "fas fa-microchip",
+          "hidden": true,
+          "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
+        },
+        "max_memory": {
+          "type": "string",
+          "description": "Maximum amount of memory that can be requested for any single job.",
+          "default": "128.GB",
+          "fa_icon": "fas fa-memory",
+          "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
+          "hidden": true,
+          "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
+        },
+        "max_time": {
+          "type": "string",
+          "description": "Maximum amount of time that can be requested for any single job.",
+          "default": "240.h",
+          "fa_icon": "far fa-clock",
+          "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
+          "hidden": true,
+          "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
+        }
+      }
+    },
+    "control_flow": {
+      "title": "Control Flow",
+      "type": "object",
+      "description": "",
+      "default": "",
+      "fa_icon": "fas fa-toggle-on",
+      "properties": {
+        "cliquesnv": {
+          "type": "boolean",
+          "default": true
+        },
+        "haplink": {
+          "type": "boolean",
+          "default": true
+        },
+        "quasirecomb": {
+          "type": "boolean",
+          "default": true
+        },
+        "shorah": {
+          "type": "boolean",
+          "default": true
+        },
+        "viquas": {
+          "type": "boolean",
+          "default": true
+        }
+      }
+    }
+  },
+  "allOf": [
+    {
+      "$ref": "#/definitions/input_output_options"
+    },
+    {
+      "$ref": "#/definitions/institutional_config_options"
+    },
+    {
+      "$ref": "#/definitions/max_job_request_options"
+    },
+    {
+      "$ref": "#/definitions/control_flow"
+    }
+  ]
+}