Update nextflow_wgs to DSL2

CHANGELOG.md

@@ -1,11 +1,21 @@
 # CHANGELOG
 
+### 3.15.0
+
+* Rewrite main.nf to DSL2
+* Refactor everything into one workflow `NEXTFLOW_WGS`.
+* Remove contamination check for non-wgs profiles
+* Remove `melt_qc_val` process (now exists in main workflow)
+* Remove `dummy_svvcf_for_loqusdb` process
+* Temp disable annotation-only runs (will be re-added later)
+
 ### 3.14.5
 * Include --case-id flag with group-ID in Gens load command
 
 ### 3.14.4
 * Routine update of bed intersect file
 
+
 ### 3.14.3
 * Fix rankscore parsing in `cnv2bed.pl`
 
@@ -15,7 +25,7 @@
 ### 3.14.1
 
 * Adds basic flake8-based linting 
-* Removes unused scripts from /
+* Removes unused scripts from `bin/`
 * Fixes wrong var name in `bin/normalize_caller_names_in_svdb_fields.py`
 * Fix wrong var assignment in `bin/normalize_caller_names_in_svdb_fields.py` that led to caller names not being normalized for wgs trios.
 

configs/nextflow.hopper.config

@@ -26,8 +26,7 @@ params {
 
   // SENTIEON CONFIGS //
   sentieon_model = '/fs1/resources/ref/sw/sentieon/SentieonDNAscopeModelBeta0.4a-201808.05.model'
-  bwa_shards = 8
-  shardbwa = false
+  bwa_K_size = 100000000
   git = "$baseDir/git.hash"
 
   // CPU counts //
@@ -63,7 +62,7 @@ params {
   PHASTCONS         = "${refpath}/annotation_dbs/hg38.phastCons100way.bw"
 
   // ANNOTATION DBS GENERAL //
-  KNOWN             = "${refpath}/annotation_dbs/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz"
+  KNOWN_SITES       = "${refpath}/annotation_dbs/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz"
   CLINVAR           = "${refpath}/annotation_dbs/clinvar38_latest.vcf.gz"
   OMIM_GENES        = "${refpath}/annotation_dbs/omim/2020-10-05_omim_genes.tsv"
 
@@ -113,6 +112,7 @@ params {
 
   run_chanjo2       = true
   reanalyze         = false
+  annotate_only     = false
 }
 
 process {

docs/annotation_files.md

@@ -9,7 +9,7 @@ To run the pipeline, you need to setup a number of annotation files. Default val
 | `rCRS_fasta`              | Reference genome     | `fasta`         | Mitochondrial FASTA reference sequence found [here](https://www.ncbi.nlm.nih.gov/nuccore/251831106)                                                                                                                                                     |
 | `bwa_shards`              | Alignment            | integer         | Number of shards to split the reads into prior to alignment                                                                                                                                                                                             |
 | `shardbwa`                | Alignment            | boolean         | Boolean specifying whether to do alignment in sharded mode                                                                                                                                                                                              |
-| `KNOWN`                   | Alignment            | `vcf`           | Gold-standard indels used in Sentieon's base quality score recalibration (BQSR)                                                                                                                                                                         |
+| `KNOWN_SITES`                   | Alignment            | `vcf`           | Gold-standard indels used in Sentieon's base quality score recalibration (BQSR)                                                                                                                                                                         |
 | `VEP_CACHE`               | Annotation (VEP)     | folder          | VEP files for offline run. Instructions on how to setup a cache can be found [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#cache).                                                                                           |
 | `VEP_FASTA`               | Annotation (VEP)     | `fasta`         | Reference sequence used for optimization within the VEP cache                                                                                                                                                                                           |
 | `SYNONYMS`                | Annotation (VEP)     | `tsv`           | Chromosome synonyms used by VEP (for instance to recognize `M` as `MT`)                                                                                                                                                                                 |