feat: added ntSynt and ntSynt-viz for synteny analysis + bug fix

.test/config/config.yml

@@ -2,8 +2,9 @@ samplesheet: "config/samples.csv"
 tool: ["prokka"]
 
 reference:
-  fasta: ""
-  gff: ""
+  fasta: "data/ref_genome.fasta"
+  gff: "data/ref_genome.gff"
+  name: "Ref Genome"
 
 pgap:
   bin: "path/to/pgap.py"
@@ -34,6 +35,18 @@ fastani:
   skip: False
   extra: ""
 
+checkm:
+  skip: True
+  existing_db: ""
+  extra: ""
+
 rgi:
   skip: False
   extra: "--clean --alignment_tool DIAMOND"
+
+synteny:
+  skip: False
+  divergence: 1
+  extra: ""
+  viz_scale: "1e6"
+  viz_extra: "--normalize"

README.md

@@ -117,4 +117,8 @@ snakemake --cores 2 --sdm conda apptainer --directory .test
 
 > Tonkin-Hill G, MacAlasdair N, Ruis C, Weimann A, Horesh G, Lees JA, Gladstone RA, Lo S, Beaudoin C, Floto RA, Frost SDW, Corander J, Bentley SD, Parkhill J. _Producing polished prokaryotic pangenomes with the Panaroo pipeline_. Genome Biol. 21(1):180, **2020**. PMID: 32698896. https://doi.org/10.1186/s13059-020-02090-4.
 
-> Köster, J., Mölder, F., Jablonski, K. P., Letcher, B., Hall, M. B., Tomkins-Tinch, C. H., Sochat, V., Forster, J., Lee, S., Twardziok, S. O., Kanitz, A., Wilm, A., Holtgrewe, M., Rahmann, S., & Nahnsen, S. _Sustainable data analysis with Snakemake_. F1000Research, 10:33, 10, 33, **2021**. https://doi.org/10.12688/f1000research.29032.2.
+> Köster J., Mölder F., Jablonski K. P., Letcher B., Hall M. B., Tomkins-Tinch C. H., Sochat V., Forster J., Lee S., Twardziok S. O., Kanitz A., Wilm A., Holtgrewe M., Rahmann S., & Nahnsen S. _Sustainable data analysis with Snakemake_. F1000Research, 10:33, 10, 33, **2021**. https://doi.org/10.12688/f1000research.29032.2.
+
+> Coombe L, Kazemi P, Wong J, Birol I, Warren RL. _ntSynt: multi-genome synteny detection using minimizer graph mappings_. BMC Biology. 23:367, **2025**. https://doi.org/10.1186/s12915-025-02455-w
+
+> Coombe L, Warren RL, Birol I. _ntSynt-viz: Visualizing synteny patterns across multiple genomes_. bioRxiv 2025.01.15.633221. https://doi.org/10.1101/2025.01.15.633221

config/config.yml

@@ -4,6 +4,7 @@ tool: ["prokka"]
 reference:
   fasta: ""
   gff: ""
+  name: ""
 
 pgap:
   bin: "path/to/pgap.py"
@@ -34,6 +35,18 @@ fastani:
   skip: False
   extra: ""
 
+checkm:
+  skip: True
+  existing_db: ""
+  extra: ""
+
 rgi:
   skip: False
   extra: "--clean --alignment_tool DIAMOND"
+
+synteny:
+  skip: False
+  divergence: 1
+  extra: ""
+  viz_scale: "1e6"
+  viz_extra: "--normalize"

config/schemas/config.schema.yml

@@ -30,6 +30,10 @@ properties:
         type: string
         description: Path to the reference annotation in GFF format (optional)
         default: ""
+      name:
+        type: string
+        description: Name of the reference genome (used in synteny visualization)
+        default: "Ref Genome"
     required:
       - fasta
   pgap:
@@ -122,6 +126,8 @@ properties:
         type: string
         description: Extra command-line arguments for Panaroo
         default: "--clean-mode strict --remove-invalid-genes"
+    required:
+      - extra
   fastani:
     type: object
     properties:
@@ -133,6 +139,26 @@ properties:
         type: string
         description: Extra command-line arguments for FastANI
         default: ""
+    required:
+      - extra
+  checkm:
+    type: object
+    properties:
+      skip:
+        type: boolean
+        description: Whether to skip CheckM analysis
+        default: true
+      existing_db:
+        type: string
+        description: Path to an existing CheckM database (optional)
+        default: ""
+      extra:
+        type: string
+        description: Extra command-line arguments for CheckM
+        default: ""
+    required:
+      - existing_db
+      - extra
   rgi:
     type: object
     properties:
@@ -144,6 +170,36 @@ properties:
         type: string
         description: Extra command-line arguments for RGI
         default: "--clean --alignment_tool DIAMOND"
+    required:
+      - extra
+  synteny:
+    type: object
+    properties:
+      skip:
+        type: boolean
+        description: Whether to skip synteny analysis
+        default: false
+      divergence:
+        type: number
+        description: Maximum divergence range between genomes for synteny analysis
+        default: 1
+      extra:
+        type: string
+        description: Extra command-line arguments for synteny analysis
+        default: ""
+      viz_scale:
+        type: string
+        description: Scale for synteny visualization (e.g., "1e6")
+        default: "1e6"
+      viz_extra:
+        type: string
+        description: Extra command-line arguments for synteny visualization
+        default: "--normalize"
+    required:
+      - divergence
+      - extra
+      - viz_extra
+      - viz_scale
 required:
   - samplesheet
   - tool
@@ -154,4 +210,6 @@ required:
   - quast
   - panaroo
   - fastani
+  - checkm
   - rgi
+  - synteny