Merge branch 'tag' into 'dev'

tag and template update

See merge request epi2melabs/workflows/wf-bacterial-genomes!42

CHANGELOG.md

@@ -3,9 +3,13 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
-## [unreleased]
+
+## [v0.2.6]
 ### Changes
 - Added quast for assembly stats
+- Remove sanitize option
+### Fixes
+- Update syntax to fix reference error
 
 ## [v0.2.5]
 ### Changes

lib/fastqingress.nf

@@ -87,42 +87,6 @@ def find_fastq(pattern, maxdepth)
 }
 
 
-/**
- * Rework EPI2ME flattened directory structure into standard form
- * files are matched on barcode\d+ and moved into corresponding
- * subdirectories ready for processing.
- *
- * @param input_folder Top-level input directory.
- * @param staging Top-level output_directory.
- * @return A File object representating the staging directory created
- *     under output
- */
-def sanitize_fastq(input_folder, staging)
-{
-    // TODO: this fails if input_folder is an S3 path
-    log.info "Running sanitization."
-    log.info  " - Moving files: ${input_folder} -> ${staging}"
-    staging.mkdirs()
-    files = find_fastq(input_folder.resolve("**"), 1)
-    for (fastq in files) {
-        fname = fastq.getFileName()
-        // find barcode
-        pattern = ~/barcode\d+/
-        matcher = fname =~ pattern
-        if (!matcher.find()) {
-            // not barcoded - leave alone
-            fastq.renameTo(staging.resolve(fname))
-        } else {
-            bc_dir = file(staging.resolve(matcher[0]))
-            bc_dir.mkdirs()
-            fastq.renameTo(staging.resolve("${matcher[0]}/${fname}"))
-        }
-    }
-    log.info " - Finished sanitization."
-    return staging
-}
-
-
 /**
  * Take an input directory return the barcode and non barcode
  * sub directories contained within.
@@ -345,8 +309,6 @@ def create_metamap(Map arguments) {
  * @param input Top level input file or folder to locate fastq data.
  * @param sample string to name single sample data.
  * @param sample_sheet Path to sample sheet CSV file.
- * @param sanitize regularize inputs from EPI2ME platform.
- * @param output output location, required if sanitize==true
  * @param min_barcode Minimum barcode to accept.
  * @param max_barcode Maximum (inclusive) barcode to accept.
  *
@@ -357,15 +319,11 @@ def fastq_ingress(Map arguments)
     def parser = new ArgumentParser(
         args:["input"],
         kwargs:[
-            "sample":null, "sample_sheet":null, "sanitize":false, "output":null,
+            "sample":null, "sample_sheet":null,
             "min_barcode":0, "max_barcode":Integer.MAX_VALUE],
         name:"fastq_ingress")
     Map margs = parser.parse_args(arguments)
 
-    if (margs.sanitize && margs.output == null) {
-        throw new Exception("Argument 'output' required if 'sanitize' is true.")
-    }
-
 
     log.info "Checking fastq input."
     input = file(margs.input)
@@ -382,12 +340,6 @@ def fastq_ingress(Map arguments)
 
     // Handle directory input
     if (input.isDirectory()) {
-        // EPI2ME harness
-        if (margs.sanitize) {
-            staging = file(margs.output).resolve("staging")
-            input = sanitize_fastq(input, staging)
-        }
-
         // Get barcoded and non barcoded subdirectories
         (barcoded, non_barcoded) = get_subdirectories(input)
 

main.nf

@@ -383,9 +383,7 @@ workflow {
     samples = fastq_ingress([
         "input":params.fastq,
         "sample":params.sample,
-        "sample_sheet":params.sample_sheet,
-        "sanitize": params.sanitize_fastq,
-        "output":params.out_dir])
+        "sample_sheet":params.sample_sheet])
 
     reference = params.reference
     results = calling_pipeline(samples, reference)

nextflow.config

@@ -11,14 +11,13 @@ params {
     chunk_size = 1000000
     run_prokka = true
     prokka_opts = null
-    wfversion = "v0.2.5"
+    wfversion = "v0.2.6"
     prokka_version = "1.14.5"
     aws_image_prefix = null
     aws_queue = null
     report_name = "report"
     sample = null
     sample_sheet = null
-    sanitize_fastq = false
     disable_ping = false
     genome_size = 5000000
 

nextflow_schema.json

@@ -73,11 +73,6 @@
                     "default": 5000000,
                     "description": "Estimated genome size to be used in assembly"
                 },
-                "sanitize_fastq": {
-                    "type": "boolean",
-                    "description": "Use additional heuristics to identify barcodes from file paths\"",
-                    "help_text": "Enabling this option will group together files into samples by the presence of strings of the form `barcodeXXX` present in filenames, rather than simply files grouped into directories (as output by MinKNOW and the Guppy basecaller)"
-                },
                 "chunk_size": {
                     "type": "integer",
                     "default": 1000000,
@@ -139,7 +134,7 @@
                 },
                 "wfversion": {
                     "type": "string",
-                    "default": "v0.2.5",
+                    "default": "v0.2.6",
                     "hidden": true
                 },
                 "help": {