Merge pull request #4 from nf-core/dev

update dev

Dockerfile

@@ -1,4 +1,4 @@
-FROM ghcr.io/pangenome/pggb:latest
+FROM ghcr.io/pangenome/pggb:20201125163549e465b0
 LABEL authors="Simon Heumos, Michael Heuer, Lukas Heumos, Erik Garrison, Andrea Guarracino" \
       description="Docker image containing all software requirements for the nf-core/pangenome pipeline"
 

README.md

@@ -4,7 +4,7 @@
 
 [![GitHub Actions CI Status](https://github.com/nf-core/pangenome/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/pangenome/actions)
 [![GitHub Actions Linting Status](https://github.com/nf-core/pangenome/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/pangenome/actions)
-[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A520.04.0-brightgreen.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A520.10.0-brightgreen.svg)](https://www.nextflow.io/)
 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](https://bioconda.github.io/)
 [![Docker](https://img.shields.io/docker/automated/nfcore/pangenome.svg)](https://hub.docker.com/r/nfcore/pangenome)

main.nf

@@ -11,35 +11,18 @@
 
 nextflow.enable.dsl = 2
 
-params.input="${baseDir}/**.fa.gz"
-params.map_pct_id=90//false
-params.align_pct_id=90// false
-params.n_secondary=10//false
-params.segment_length=1000//false
-params.mash_kmer=16
-params.min_match_length=8
-params.max_block_weight=10000
-params.max_path_jump=5000
-params.min_subpath=0
-params.max_edge_jump=5000
-params.max_poa_length=10000
-params.do_viz=false
-params.do_layout=false
-params.do_stats=false
-params.consensus_jump_max="10,100,1000,10000"
-
 def makeBaseName = { f -> """\
 ${f.getSimpleName()}.pggb-\
-s${params.segment_length}-\
-p${params.map_pct_id}-\
-n${params.n_secondary}-\
-a${params.align_pct_id}-\
-K${params.mash_kmer}-\
-k${params.min_match_length}-\
-w${params.max_block_weight}-\
-j${params.max_path_jump}-\
-W${params.min_subpath}-\
-e${params.max_edge_jump}\
+s${params.edyeet_segment_length}-\
+p${params.edyeet_map_pct_id}-\
+n${params.edyeet_n_secondary}-\
+a${params.edyeet_align_pct_id}-\
+K${params.edyeet_mash_kmer}-\
+k${params.seqwish_min_match_length}-\
+w${params.smoothxg_max_block_weight}-\
+j${params.smoothxg_max_path_jump}-\
+W${params.smoothxg_min_subpath}-\
+e${params.smoothxg_max_edge_jump}\
 """ }
 
 fasta = channel.fromPath("${params.input}").map { f -> tuple(makeBaseName(f), f) }
@@ -53,11 +36,11 @@ process edyeet {
 
   """
   edyeet -X \
-     -s ${params.segment_length} \
-     -p ${params.map_pct_id} \
-     -n ${params.n_secondary} \
-     -a ${params.align_pct_id} \
-     -k ${params.mash_kmer} \
+     -s ${params.edyeet_segment_length} \
+     -p ${params.edyeet_map_pct_id} \
+     -n ${params.edyeet_n_secondary} \
+     -a ${params.edyeet_align_pct_id} \
+     -k ${params.edyeet_mash_kmer} \
      -t ${task.cpus} \
      $fasta $fasta \
      >${f}.paf 
@@ -78,7 +61,7 @@ process seqwish {
       -t ${task.cpus} \
       -s $fasta \
       -p $alignment \
-      -k ${params.min_match_length} \
+      -k ${params.seqwish_min_match_length} \
       -g ${f}.seqwish.gfa -P
     """
 }
@@ -97,15 +80,15 @@ process smoothxg {
     smoothxg \
       -t ${task.cpus} \
       -g $graph \
-      -w ${params.max_block_weight} \
-      -j ${params.max_path_jump} \
-      -e ${params.max_edge_jump} \
-      -l ${params.max_poa_length} \
+      -w ${params.smoothxg_max_block_weight} \
+      -j ${params.smoothxg_max_path_jump} \
+      -e ${params.smoothxg_max_edge_jump} \
+      -l ${params.smoothxg_max_poa_length} \
       -o ${f}.smooth.gfa \
       -m ${f}.smooth.maf \
       -s ${f}.consensus \
       -a \
-      -C ${params.consensus_jump_max}
+      -C ${params.smoothxg_consensus_jump_max}
     """  
 }
 

nextflow.config

@@ -8,14 +8,40 @@
 // Global default params, used in configs
 params {
 
-  // Workflow flags
-  // TODO nf-core: Specify your pipeline's command line flags
-  genome = false
-  input = "data/*.fa.gz"
+  // Input options
+  input="${baseDir}/**.fa.gz"
+
+  // Reporting
+  do_stats=true
+
+  // Edyeet options
+  edyeet_map_pct_id=90
+  edyeet_align_pct_id=90
+  edyeet_n_secondary=10
+  edyeet_segment_length=1000
+  edyeet_mash_kmer=16
+
+  // Seqwish options
+  seqwish_min_match_length=8
+
+  // Smoothxg options
+  smoothxg_max_block_weight=10000
+  smoothxg_max_path_jump=5000
+  smoothxg_min_subpath=0
+  smoothxg_max_edge_jump=5000
+  smoothxg_max_poa_length=10000
+  smoothxg_consensus_jump_max="10,100,1000,10000"
+
+  // Visualization
+  do_viz = false
+  do_layout = false
+
+  // Output options
   outdir = './results'
   publish_dir_mode = 'copy'
 
   // Boilerplate options
+  genome = ''
   name = false
   multiqc_config = false
   email = false
@@ -27,6 +53,8 @@ params {
   igenomes_base = 's3://ngi-igenomes/igenomes/'
   tracedir = "${params.outdir}/pipeline_info"
   igenomes_ignore = false
+
+  // Config options
   custom_config_version = 'master'
   custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}"
   hostnames = false
@@ -115,7 +143,7 @@ manifest {
   homePage = 'https://github.com/nf-core/pangenome'
   description = 'The pangenome graph construction pipeline renders a collection of sequences into a pangenome graph. Its goal is to build a graph that is locally directed and acyclic while preserving large-scale variation. Maintaining local linearity is important for interpretation, visualization, mapping, comparative genomics, and reuse of pangenome graphs'
   mainScript = 'main.nf'
-  nextflowVersion = '>=20.04.0'
+  nextflowVersion = '>=20.10.0'
   version = '1.0dev'
 }