Merge pull request #23 from phac-nml/dev

Version 2.1.0 release

.editorconfig

@@ -22,3 +22,18 @@ indent_size = unset
 
 [/assets/email*]
 indent_size = unset
+
+[/assets/ArborView.html]
+trim_trailing_whitespace = unset
+
+# ignore Readme
+[README.md]
+indent_style = unset
+
+# ignore python
+[*.{py}]
+indent_style = unset
+
+#ignore License-Apachev2
+[LICENSE-Apachev2]
+indent_style = unset

.pre-commit-config.yaml

@@ -1,5 +1,10 @@
 repos:
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: "v2.7.1"
+    rev: "v3.1.0"
     hooks:
       - id: prettier
+  - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
+    rev: "2.7.3"
+    hooks:
+      - id: editorconfig-checker
+        alias: ec

.prettierignore

@@ -10,3 +10,4 @@ testing/
 testing*
 *.pyc
 bin/
+/assets/ArborView.html

CHANGELOG.md

@@ -3,6 +3,13 @@
 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).
 
+## 2.1.0 - 2024/07/09
+
+### `Added`
+
+- Support for including contextual metadata in the input samplesheet: See [PR 22](https://github.com/phac-nml/snvphylnfc/pull/22)
+- ArborView HTML app functionality for viewing dendograms with contextual metadata: See [PR 22](https://github.com/phac-nml/snvphylnfc/pull/22)
+
 ## 2.0.2 - 2024/05/21
 
 ### `Added`

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) Aaron Petkau
+Copyright (c) Government of Canada
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -8,17 +8,18 @@ This is the [nf-core](https://nf-co.re/)-based pipeline for [SNVPhyl](https://sn
 
 Input is provided to SNVPhyl in the form of a samplesheet (passed as `--input samplesheet.csv`). This samplesheet is a CSV-formated file, which may be provided as a URI (ex: a file path or web address), and has the following format:
 
-| sample  | fastq_1                    | fastq_2                    | reference_assembly           |
-| ------- | -------------------------- | -------------------------- | ---------------------------- |
-| SAMPLE1 | /path/to/sample1_fastq1.fq | /path/to/sample1_fastq2.fq | /path/to/sample1_assembly.fa |
-| SAMPLE2 | /path/to/sample2_fastq1.fq |                            |                              |
+| sample  | fastq_1                    | fastq_2                    | reference_assembly           | metadata_1 | metadata_2 | metadata_3 | metadata_4 | metadata_5 | metadata_6 | metadata_7 | metadata_8 |
+| ------- | -------------------------- | -------------------------- | ---------------------------- | ---------- | ---------- | ---------- | ---------- | ---------- | ---------- | ---------- | ---------- |
+| SAMPLE1 | /path/to/sample1_fastq1.fq | /path/to/sample1_fastq2.fq | /path/to/sample1_assembly.fa | meta1      | meta2      | meta3      | meta4      | meta5      | meta6      | meta7      | meta8      |
+| SAMPLE2 | /path/to/sample2_fastq1.fq |                            |                              | meta1      | meta2      | meta3      | meta4      | meta5      | meta6      | meta7      | meta8      |
 
 The columns are defined as follows:
 
 - `sample`: The unique sample identifier to associate with the reads (and optionally the reference assembly).
 - `fastq_1`: A URI (ex: a file path or web address) to either single-end FASTQ-formatted reads or one pair of pair-end FASTQ-formatted reads.
 - `fastq_2`: (Optional) If `fastq_1` is paired-end, then this field is a URI to reads that are the other pair of reads associated with `fastq_1`.
 - `reference_assembly`: (Optional) A URI to a reference assembly associated with the sample, so that it may be referenced on the command line by the sample identifier for use as the reference for the whole pipeline. However, it may be easier to leave these fields blank and specify the reference using the `--refgenome` parameter.
+- `metadata_1...8`: (Optional) Permits up to 8 columns for user-defined contextual metadata associated with each `sample`. Refer to [Metadata](#metadata) for more information.
 
 The structure of this file is defined in [assets/schema_input.json](assets/schema_input.json). Please see [assets/samplesheet.csv](assets/samplesheet.csv) to see an example of a samplesheet for this pipeline.
 
@@ -33,6 +34,10 @@ The mandatory parameters are as follows:
 
 Additionally, it is mandatory to have one of either `--refgenome` or `--reference_sample_id` (but not both) to specify the reference. Please see the Reference section for more details.
 
+## Metadata
+
+In order to customize metadata headers, the parameters `--metadata_1_header` through `--metadata_8_header` may be specified. These parameters are used to re-name the headers in the final metadata table from the defaults (e.g., rename `metadata_1` to `country`).
+
 ## Optional
 
 The optional parameters are as follows:
@@ -91,6 +96,7 @@ The following output files are generated by the pipeline:
 - `filter/filterStats.txt`: a summary of the number of SNVs filtered within in the SNV Table
 - `phyml/phylogeneticTree.newick`: the maximum likelihood phylogeny generated from an alignment of SNVs extracted from the whole genomes of each input file
 - `phyml/phylogeneticTreeStats.txt`: statistics for the generated phylogenetic tree
+- `arbor/SNVPhyl_ArborView.html`: an HTML file for examining the phylogenetic tree (.newick) dendrogram in the ArborView HTML app, complete with contextual metadata
 - `vcf2snv/snvTable.tsv`: a table of all detected variant sites
 - `vcf2snv/vcf2core.tsv`: a table of the evaluated core positions in each reference fasta sequence
 - `vcf2snv/snvAlignment.phy`: an alignment of SNVs used to generate the phylogenetic tree
@@ -106,6 +112,9 @@ A JSON file for loading the data into IRIDA Next is output by this pipeline. The
 {
     "files": {
         "global": [
+            {
+                "path": "arbor/SNVPhyl__ArborView.html"
+            },
             {
                 "path": "make/snvMatrix.tsv"
             },
@@ -160,7 +169,7 @@ This pipeline uses code and infrastructure developed and maintained by the [nf-c
 
 ## SNVPhyl NF-Core Pipeline
 
-Copyright 2023 Government of Canada
+Copyright 2024 Government of Canada
 
 Licensed under the MIT License (the "License"); you may not use
 this work except in compliance with the License. You may obtain a copy of the