feat: add dragen mapper

.github/workflows/ci.yml

@@ -19,10 +19,10 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Install Pixi
-        uses: prefix-dev/setup-pixi@v0.8.3
+        uses: prefix-dev/setup-pixi@v0.9.6
         with:
           environments: format
-          pixi-version: v0.43.3
+          pixi-version: v0.69.0
           cache: false
           locked: false
 
@@ -47,10 +47,10 @@ jobs:
           fetch-depth: 0
 
       - name: Install Pixi
-        uses: prefix-dev/setup-pixi@v0.8.3
+        uses: prefix-dev/setup-pixi@v0.9.6
         with:
           environments: test
-          pixi-version: v0.43.3
+          pixi-version: v0.69.0
           cache: false
           locked: false
 

README.md

@@ -1,6 +1,6 @@
 # aeDNA - a customizable Snakemake workflow for ancient environmental DNA
 
-[![Snakemake](https://img.shields.io/badge/snakemake-≥9.16.3-brightgreen.svg)](https://snakemake.bitbucket.io)
+[![Snakemake](https://img.shields.io/badge/snakemake-≥9.22.0-brightgreen.svg)](https://snakemake.bitbucket.io)
 ![CI](https://github.com/GeoGenetics/aeDNA/actions/workflows/ci.yml/badge.svg)
 
 This workflow combines several modules to build a workflow for ancient environmental DNA (aeDNA) analyses and QC:

examples/README.md

@@ -15,18 +15,18 @@
 </details>
 
 
-# Empty - 1 negative control
+# DRAGEN - 1 sample (simulated) over 2 reference collections
 <details><summary>Rulegraph</summary>
 
-![rulegraph.svg](empty/rulegraph.svg)
+![rulegraph.svg](dragen/rulegraph.svg)
 </details>
 
 <details><summary>DAG</summary>
 
-![dag.svg](empty/dag.svg)
+![dag.svg](dragen/dag.svg)
 </details>
 
 <details><summary>Filegraph</summary>
 
-![filegraph.svg](empty/filegraph.svg)
+![filegraph.svg](dragen/filegraph.svg)
 </details>

examples/dragen/config/config.yaml

@@ -0,0 +1,137 @@
+
+# - Only tested with Phred33 quality scores
+
+samples: config/samples.tsv
+
+units: config/units.tsv
+
+
+
+#############
+### READS ###
+#############
+trim:
+  trim:
+    activate: true
+    tool: adapterremoval
+    params: "--trimns --maxns 10 --trimqualities --minlength 30 --mask-degenerate-bases --seed 12345"
+
+  # Ignored for SE
+  collapse:
+    activate: true
+    params: "--collapse-conservatively"
+
+derep:
+  extension:
+    activate: false
+    k: 16
+    params: "ibb=t prefilter=0 el=100 er=100 ecc=f ecco=f ignorebadquality extendrollback=0"
+
+  derep:
+    activate: true
+    # vsearch or seqkit
+    tool: seqkit
+    params: ""
+
+  low_complex:
+    params: "entropy=0.7 entropywindow=30 entropyk=4"
+
+
+
+#############
+### ALIGN ###
+#############
+prefilter:
+  taxa: "Bacteria,Archaea,Viruses"
+
+  taxonomy:
+    nodes: "data/taxdump/nodes.dmp"
+    names: "data/taxdump/names.dmp"
+
+  ref:
+    hires_organelles_viruses_smags:
+      n_shards: 2
+      path: "/staging/hash_tables/hires-organelles-viruses-smags.{n_shard}"
+      map:
+        tool: dragen
+        params: "--Mapper.edit-mode=1"
+      acc2taxid: "data/prok.acc2taxid.gz"
+    human_genome:
+      n_shards: 1
+      path: "/staging/hash_tables/GCF_000001405.40_GRCh38.p14_genomic"
+      map:
+        tool: dragen
+        params: "--Aligner.global=1 --Aligner.match-score=0 --Aligner.match-n-score=-1 --Aligner.mismatch-pen=4 --Aligner.gap-open-pen=0 --Aligner.gap-ext-pen=4 --Aligner.aln-min-score=0 --Aligner.min-score-coeff=-0.4 --Aligner.sec-aligns=2000 --Aligner.supp-aligns=0 --Aligner.hard-clips=0 --Aligner.sec-score-delta=100 --Mapper.edit-mode=1 --Mapper.max-seed-freq=256 --Mapper.reduce-seed-ext=1 --Mapper.intvl-target-hits=256 --Mapper.intvl-max-hits=256 --Mapper.intvl-sample-hits=256 --Mapper.seed-density=1.0 --Mapper.edit-seed-num=80 --Mapper.edit-read-len=100 --Mapper.edit-chain-limit=29 --filter-flags-from-output=4"
+      acc2taxid: "data/human.acc2taxid.gz"
+
+  filter:
+    saturated_reads:
+      activate: true
+      n_alns: 500
+
+  unicorn:
+    refstats:
+      params: "--minrefl 1 --minreads 1 --rank genus"
+    taxstats:
+      params: "-k 17 --minrefl  1 --minreads 1 --minmani 0 --minalnas -Inf --maxdust 100"
+
+  metadmg:
+    damage:
+      params: "--print_length 15"
+
+    lca:
+      params: "--fix_ncbi 0 --how_many 25 --weight_type 1 --edit_dist_max 10000 --lca_rank genus"
+
+    dfit:
+      params: "--nopt 5 --showfits 2"
+
+
+euk:
+  taxonomy:
+    nodes: "data/taxdump/nodes.dmp"
+    names: "data/taxdump/names.dmp"
+
+  ref:
+    refseq_mitoch:
+      n_shards: 1
+      path: "/staging/hash_tables/refseq_mitochondrion.genomic/"
+      map: &map_euk_dragen
+        tool: dragen
+        params: "--Aligner.global=1 --Aligner.match-score=0 --Aligner.match-n-score=-1 --Aligner.mismatch-pen=4 --Aligner.gap-open-pen=0 --Aligner.gap-ext-pen=4 --Aligner.aln-min-score=0 --Aligner.min-score-coeff=-0.4 --Aligner.sec-aligns=2000 --Aligner.supp-aligns=0 --Aligner.hard-clips=0 --Aligner.sec-score-delta=100 --Mapper.edit-mode=0 --Mapper.max-seed-freq=256 --Mapper.reduce-seed-ext=1 --Mapper.intvl-target-hits=256 --Mapper.intvl-max-hits=256 --Mapper.intvl-sample-hits=256 --Mapper.seed-density=1.0 --Mapper.edit-seed-num=80 --Mapper.edit-read-len=100 --Mapper.edit-chain-limit=29 --filter-flags-from-output=4"
+      acc2taxid: "data/mitoch.acc2taxid.gz"
+    core_nt:
+      n_shards: 4
+      path: "/staging/hash_tables/core_nt.{n_shard}"
+      map:
+        <<: *map_euk_dragen
+      acc2taxid: "data/core_nt.acc2taxid.gz"
+
+  filter:
+    saturated_reads:
+      activate: true
+      n_alns: 500
+
+  unicorn:
+    refstats:
+      params: "--minrefl 1 --minreads 1 --rank genus"
+    taxstats:
+      params: "-k 17 --minrefl  1 --minreads 1 --minmani 0 --minalnas -Inf --maxdust 100"
+
+
+  metadmg:
+    damage:
+      params: "--print_length 15"
+
+    lca:
+      params: "--fix_ncbi 0 --how_many 15 --sim_score_low 0.95 --weight_type 0 --edit_dist_max 10000 --lca_rank genus"
+
+    dfit:
+      params: "--nopt 5 --showfits 2 --seed 12345"
+
+
+############
+## REPORT ##
+############
+report:
+  multiqc: "--no-ai --verbose --cl-config 'custom_logo: data/KU_long.png' --cl-config 'custom_logo_title: CAEG - Center for Ancient Environmental Genomics' --cl-config 'custom_logo_url: https://globe.ku.dk/research/caeg/'"
+  multiqc_db_url: "test_qc.sqlite"