Updates to readme and config

artic-network · Sep 26, 2024 · d429ade · d429ade
1 parent 960e885
commit d429ade
Show file tree

Hide file tree

Showing 3 changed files with 30 additions and 88 deletions.
diff --git a/README.md b/README.md
@@ -1,56 +1,46 @@
 # artic-mpxv-illumina-nf
 A Nextflow pipeline for processing amplicon data generated by Illumina sequencing, with a focus on monkeypox virus (mpxv).
 
-![push master](https://github.com/BCCDC-PHL/mpxv-artic-nf/actions/workflows/push_master.yml/badge.svg)
-
 #### Introduction
 
-This pipeline is based on the [BCCDC-PHL/ncov2019-artic-nf](https://github.com/BCCDC-PHL/ncov2019-artic-nf) pipeline, which is a fork of the [connor-lab/ncov2019-artic-nf](https://github.com/connor-lab/ncov2019-artic-nf) pipeline. It has been modified to support analysis of monkeypox virus.
+This pipeline is based on the [BCCDC-PHL/ncov2019-artic-nf](https://github.com/BCCDC-PHL/ncov2019-artic-nf) pipeline, which is a fork of the [connor-lab/ncov2019-artic-nf](https://github.com/connor-lab/ncov2019-artic-nf) pipeline. It has been modified to support analysis of MPox virus.
 
 ```mermaid
 flowchart TD
-  ref[ref.fa]
-  composite_ref[composite_ref.fa]
+  ref[reference.fasta]
   primers[primer.bed]
-  primer_pairs[primer_pairs.tsv]
-  fastq[fastq_dir]
-  fastq --> normalizeDepth(normalizeDepth)
-  composite_ref --> performHostFilter
-  normalizeDepth(normalizeDepth) --> performHostFilter(performHostFilter) 
-  performHostFilter(performHostFilter) --> readTrimming(readTrimming)
-  readTrimming(readTrimming) --> filterResidualAdapters(filterResidualAdapters)
-  filterResidualAdapters --> readMapping(readMapping)
+  fastq[directory]
+  human-t2t-hla[humanT2Treference]
+  fastq --> performHostFilter
+  humanT2Treference --> performHostFilter
+  performHostFilter(performHostFilter) --> readMapping(readMapping)
   ref --> readMapping(readMapping)
-  readMapping(readMapping) --> trimPrimerSequences(trimPrimerSequences)
-  primers --> trimPrimerSequences(trimPrimerSequences)
-  trimPrimerSequences(trimPrimerSequences) --> callConsensusFreebayes(callConsensusFreebayes)
+  readMapping(readMapping) --> align_trim(align_trim)
+  primers --> align_trim(align_trim)
+  align_trim(align_trim) --> callConsensusFreebayes(callConsensusFreebayes)
   callConsensusFreebayes(callConsensusFreebayes) --> alignConsensusToReference(alignConsensusToReference)
   ref --> alignConsensusToReference
   alignConsensusToReference --> consensusAlignment[consensus.aln.fa]
-  trimPrimerSequences --> makeQCCSV(makeQCCSV)
   callConsensusFreebayes --> makeQCCSV
   callConsensusFreebayes --> consensus[consensus.fa]
   callConsensusFreebayes --> variants[variants.vcf]
+  callConsensusFreebayes --> Squirrel(Squirrel)
   ref --> makeQCCSV
   primers --> makeQCCSV
   primer_pairs --> makeQCCSV
   makeQCCSV --> qcCSV(qc.csv)
   makeQCCSV --> depthPNG(depth.png)
+  Squirrel --> SquirrelReport(squirrel-report.html)
 ```
 
 #### Quick-start
 
 ```
-nextflow run BCCDC-PHL/mpxv-artic-nf -profile conda \
-  --prefix "output_file_prefix" \
-  --bed /path/to/primers.bed \
-  --ref /path/to/ref.fa \
-  --primer_pairs_tsv /path/to/primer_pairs_tsv \
-  --composite_ref /path/to/human_and_mpxv_composite_ref \
-  --directory /path/to/reads \
-  --outdir /path/to/outputs
+nextflow run artic-network/artic-mpxv-illumina-nf --help
 ```
 
+Will print up-to-date information on all command-line parameters for the current version.
+
 # Credits / Acknowledgements
 This pipeline only works due to the ongoing efforts of many people performing the often thankless
 job of developing and maintaining bioinformatics software, including but not limited to:
@@ -70,44 +60,12 @@ Special thanks to the following for writing / modifying / maintaining previous v
 * Jared Simpson, `https://github.com/jts/ncov2019-artic-nf`
 * Dan Fornika et al, `https://github.com/BCCDC-PHL/mpxv-artic-nf`
 
-#### Installation
-An up-to-date version of Nextflow is required because the pipeline is written in DSL2. Following the instructions at https://www.nextflow.io/ to download and install Nextflow should get you a recent-enough version. 
-
-
-#### Conda
-The repo contains a environment.yml files which automatically build the correct conda env if `-profile conda` is specifed in the command. Although you'll need `conda` installed, this is probably the easiest way to run this pipeline.
-
---cache /some/dir can be specified to have a fixed, shared location to store the conda build for use by multiple runs of the workflow.
-
-#### Config
-
-Important config options are:
-
-| Option                           | Default  | Description                                                                                                         |
-|:---------------------------------|---------:|--------------------------------------------------------------------------------------------------------------------:|
-| `normalizationTargetDepth`       | `200`    | Target depth of coverage to normalize to prior to alignment                                                         |
-| `normalizationMinDepth`          | `5`      | Minimum depth of coverage to normalize to prior to alignment                                                        |
-| `keepLen`                        | `50`     | Length of reads to keep after primer trimming                                                                       |
-| `qualThreshold`                  | `20`     | Sliding window quality threshold for keeping reads after primer trimming                                            |
-| `varMinFreqThreshold`            | `0.25`   | Allele frequency threshold for ambiguous variant                                                                    |
-| `varFreqThreshold`               | `0.75`   | Allele frequency threshold for unambiguous variant                                                                  |
-| `varMinDepth`                    | `10`     | Minimum coverage depth to call variant                                                                              |
-
-### Depth Normalization
-By default, sequence depth will be normalized using `bbnorm` to the value specified by the `--normalizationTargetDepth` param (default: 200). To skip depth normalization, add the `--skip_normalize_depth` flag.
-
-#### QC
-A script to do some basic QC is provided in `bin/qc.py`. It measures the % of reference bases are covered by `varMinDepth`, and the longest stretch of consensus sequence with no `N` bases. This script does not make a QC pass/fail call.
-
-#### Output
-A subdirectory for each process in the workflow is created in `--outdir`. A `nml_upload` subdirectory containing dehosted fastq files and consensus sequences is included. 
-
 ### Problems and Solutions
 
-1. Error during `mpxvIllumina:prepareReferenceFiles:get_bed_ref` step
+1. Error during `mpxvIllumina:prepareReferenceFiles:performHostFilter` step
   ```
   httpx.HTTPError: Failed to download https://objectstorage.uk-london-1.oraclecloud.com/n/lrbvkel2wjot/b/human-genome-bucket/o/human-t2t-hla.tar. Ensure you are connected to the internet, or provide a valid path to a local index
   ```
 
-  Currently human read removal is performed with hostile, which downloads an indexed human genome file on the fly. This is an internet problem.
+  Currently human read removal is performed with hostile, which downloads an indexed human genome file on the fly. This is almost certainly a network connectivity problem.
 
diff --git a/main.nf b/main.nf
@@ -2,34 +2,9 @@
 
 nextflow.enable.dsl = 2
 
-// include modules
-include {printHelp} from './modules/help.nf'
-
 // import subworkflows
 include {mpxvIllumina} from './workflows/illuminaMpxv.nf'
 
-if (params.help){
-    printHelp()
-    exit 0
-}
-
-if ( !params.directory ) {
-  println("Please supply a directory containing fastqs or CRAMs with --directory.")
-  println("Use --help to print help")
-  System.exit(1)
-}
-
-if ( ! params.prefix ) {
-     println("Please supply a prefix for your output files with --prefix")
-     println("Use --help to print help")
-     System.exit(1)
-} else {
-     if ( params.prefix =~ /\// ){
-         println("The --prefix that you supplied contains a \"/\", please replace it with another character")
-         System.exit(1)
-     }
-} 
-
 // entrypoint workflow
 WorkflowMain.initialise(workflow, params, log)
 

diff --git a/nextflow.config b/nextflow.config
@@ -5,11 +5,11 @@ manifest {
   description = 'Epi2me compatible Nextflow pipeline for processing ARTIC tiling amplicon Illumina sequencing reads from monkeypox virus (MPXV) samples.'
   mainScript = 'main.nf'
   nextflowVersion = '>=20.01.0'
-  version = '1.2.0'
+  version = '1.2.1'
 }
 
 epi2melabs {
-    tags = 'MPox,artic,amplicon,viruses,public health,illumina'
+    tags = 'mpox,artic,amplicon,viruses,public health,illumina'
     icon = 'faVirusCovid'
 }
 
@@ -31,6 +31,15 @@ def makeFastqSearchPath ( illuminaSuffixes, fastq_exts ) {
 
 params {
 
+wf {
+    example_cmd = [
+        "--directory 'some_directory_containing_fastqs'",
+        "--scheme_version 'artic-mpox/v1.1.1-cladeI'",
+        "--clade 'cladei'",
+
+    ]
+}    
+
   illuminaSuffixes = ['*_R{1,2}_001', '*_R{1,2}', '*_{1,2}' ]
   fastq_exts = ['.fastq.gz', '.fq.gz', '.fastq', '.fq']
   fastqSearchPath = makeFastqSearchPath( params.illuminaSuffixes, params.fastq_exts )
@@ -40,8 +49,8 @@ params {
   max_time                   = '12.h'
 
   // Boilerplate options
-  // directory = false
-  // prefix = false
+  directory = false
+  prefix = false
   // primer_pairs_tsv = 'NO_FILE'
   // profile = false
   help = false