Merge pull request #89 from nf-core/wfmash_power_up

update wfmash for better short/medium sequence alignment
nf-core · Sep 23, 2022 · a9003c0 · a9003c0
2 parents 4d94b22 + ae292d7
commit a9003c0
Show file tree

Hide file tree

Showing 5 changed files with 25 additions and 26 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -55,10 +55,10 @@ jobs:
         # Remember that you can parallelise this by using strategy.matrix
         # We also test basic visualization and reporting options here
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --no_viz --no_layout
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --smoothxg consensus_spec 10,100,1000
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --vcf_spec "gi|568815561:#,gi|568815567:#"
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --smoothxg_write_maf
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --wfmash_chunks 2
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_mappings 11 --wfmash_only
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --no_viz --no_layout
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --smoothxg consensus_spec 10,100,1000
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --vcf_spec "gi|568815561:#,gi|568815567:#"
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --smoothxg_write_maf
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --wfmash_chunks 2
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --n_haplotypes 12 --wfmash_only
diff --git a/Dockerfile b/Dockerfile
@@ -1,4 +1,4 @@
-FROM ghcr.io/pangenome/pggb:2022092217355879ede8
+FROM ghcr.io/pangenome/pggb:20220923074038f629fc
 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"
 

diff --git a/main.nf b/main.nf
@@ -27,10 +27,10 @@ if (params.input == null) {
     exit 1
 }
 
-if (params.n_mappings == null) {
+if (params.n_haplotypes == null) {
         log.info"""
 
-    Mandatory argument --n_mappings missing! For more details run with --help.
+    Mandatory argument --n_haplotypes missing! For more details run with --help.
 
     """.stripIndent()  
 
@@ -42,8 +42,8 @@ ch_multiqc_config = file("$projectDir/assets/multiqc_config.yaml", checkIfExists
 
 // We can't change global parameters inside this scope, so we build the ones we need locally
 def n_haps = 0
-if (!params.smoothxg_num_haps) {
-  n_haps = params.n_mappings
+if (!params.smoothxg_haplotypes_smooth) {
+  n_haps = params.n_haplotypes
 }
 
 def wfmash_merge_cmd = params.wfmash_merge_segments ? "-M" : ""
@@ -52,7 +52,7 @@ def wfmash_split_cmd = params.wfmash_no_splits ? "-N" : ""
 def wfmash_block_length_cmd = params.wfmash_block_length ? "-l${params.wfmash_block_length}" : ""
 def wfmash_mash_kmer_cmd = params.wfmash_mash_kmer ? "-k${params.wfmash_mash_kmer}" : ""
 def wfmash_kmer_thres_cmd = params.wfmash_mash_kmer_thres ? "-H${params.wfmash_kmer_thres}" : ""
-def wfmash_n_mappings_minus_1 = params.n_mappings - 1
+def wfmash_n_mappings_minus_1 = params.n_haplotypes - 1
 def wfmash_sparse_map_cmd = ""
 if (params.wfmash_sparse_map == "auto") {
   n = n_haps
@@ -612,7 +612,7 @@ def helpMessage() {
 
     Mandatory arguments:
       --input [file]                  Path to bgzipped input FASTA (must be surrounded with quotes)
-      -- n_mappings [int]             Number of mappings to retain for each segment.
+      -- n_haplotypes [int]             Number of mappings to retain for each segment.
       -profile [str]                  Configuration profile to use. Can use multiple (comma separated)
                                       Available: conda, docker, singularity, test, awsbatch, <institute> and more
     PAF options:
@@ -639,7 +639,7 @@ def helpMessage() {
       --seqwish_temp_dir [str]          directory for temporary files
 
     Smoothxg options:
-      --smoothxg_num_haps [n]         number of haplotypes in the given FASTA [default: wfmash_n_mappings]
+      --smoothxg_haplotypes-smooth [n]number of haplotypes if different than set with --n_haplotypes [default: n_haplotypes]
       --smoothxg_max_path_jump [n]    maximum path jump to include in block [default: 0]
       --smoothxg_max_edge_jump [n]    maximum edge jump before breaking [default: 0]
       --smoothxg_poa_length [n]       maximum sequence length to put into POA, can be a comma-separated list; 

diff --git a/nextflow.config b/nextflow.config
@@ -14,7 +14,7 @@ params {
   // FASTA
   input = null
   // number of mappings
-  n_mappings = null // default could be the number of input sequences, but then I would have to add another process
+  n_haplotypes = null // default could be the number of input sequences, but then I would have to add another process
 
   // Optional PAF input
   paf = null
@@ -50,7 +50,7 @@ params {
   seqwish_temp_dir = null
 
   // Smoothxg options
-  smoothxg_num_haps = null
+  smoothxg_haplotypes_smooth = null
   smoothxg_max_path_jump = 0
   smoothxg_max_edge_jump = 0
   smoothxg_poa_length = "700,900,1100"

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -12,7 +12,7 @@
             "description": "Define where the pipeline should find input data and save output data.",
             "required": [
                 "input",
-                "n_mappings"
+                "n_haplotypes"
             ],
             "properties": {
                 "input": {
@@ -21,10 +21,10 @@
                     "description": "Input FASTA file.",
                     "help_text": "Use this to specify the location of your input FASTA file. For example:\n\n```bash\n--input 'path/to/data/input.fa.gz'\n```\n\n."
                 },
-                "n_mappings": {
-                    "type": "integer",
-                    "fa_icon": "fas fa-dna",
-                    "description": "Number of mappings to retain for each segment."
+                "n_haplotypes": {
+                    "type": "string",
+                    "default": null,
+                    "fa_icon": "fas fa-dna"
                 },
                 "outdir": {
                     "type": "string",
@@ -148,10 +148,9 @@
             "description": "Options for graph smoothing phase.",
             "default": "",
             "properties": {
-                "smoothxg_num_haps": {
-                    "type": "integer",
-                    "default": 0,
-                    "description": "number of haplotypes in the given FASTA"
+                "smoothxg_haplotypes_smooth": {
+                    "type": "string",
+                    "default": null
                 },
                 "smoothxg_max_path_jump": {
                     "type": "integer",