fix: schema and README update

Author: m-jahn

README.md

@@ -1,7 +1,7 @@
 # snakemake-assembly-postprocessing
 
 [![Snakemake](https://img.shields.io/badge/snakemake-≥8.24.1-brightgreen.svg)](https://snakemake.github.io)
-[![GitHub actions status](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/main.yml/badge.svg)](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/main.yml)
+[![GitHub Actions](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/snakemake-tests.yml/badge.svg)](https://github.com/MPUSP/snakemake-assembly-postprocessing/actions/workflows/snakemake-tests.yml)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with apptainer](https://img.shields.io/badge/run%20with-apptainer-1D355C.svg?labelColor=000000)](https://apptainer.org/)
 [![workflow catalog](https://img.shields.io/badge/Snakemake%20workflow%20catalog-darkgreen)](https://snakemake.github.io/snakemake-workflow-catalog/docs/workflows/MPUSP/snakemake-assembly-postprocessing)

config/README.md

@@ -23,33 +23,3 @@ The samplesheet table has the following layout:
 | ...    | ...                      | ...    | ...       | ...            |
 
 **Note:** Pangenome analysis with `Panaroo` requires at least two samples.
-
-### Parameters
-
-This table lists all parameters that can be used to run the workflow.
-
-| Parameter | Type | Details | Default |
-|:---|:---|:---|:---|
-| **samplesheet** | string | Path to the sample sheet file in csv format | |
-| **tool** | array[string] | Annotation tool to use (one of `prokka`, `pgap`, `bakta`) | |
-| **pgap** | | PGAP configuration object |  |
-| bin | string | Path to the PGAP script | |
-| use_yaml_config | boolean | Whether to use YAML configuration for PGAP | `False` |
-| _prepare_yaml_files_ | | Paths to YAML templates for PGAP | |
-| generic | string | Path to the generic YAML configuration file | |
-| submol | string | Path to the submol YAML configuration file | |
-| **prokka** | | Prokka configuration object | |
-| center | string | Center name for Prokka annotation (used in sequence IDs) | |
-| extra | string | Extra command-line arguments for Prokka | `--addgenes` |
-| **bakta** | | Bakta configuration object | |
-| download_db | string | Bakta database type (`full`, `light`, or `none`) | `light` |
-| existing_db | string | Path to an existing Bakta database (optional). Needs to be combined with `download_db='none'` | `--keep-contig-headers --compliant` |
-| extra | string | Extra command-line arguments for Bakta | |
-| **quast** | | QUAST configuration object | |
-| reference_fasta | string | Path to the reference genome for QUAST | |
-| reference_gff | string | Path to the reference annotation for QUAST |
-| extra | string | Extra command-line arguments for QUAST | |
-| **panaroo** | | Panaroo configuration object | |
-| remove_source | string | Source types to remove in Panaroo (regex supported) | `cmsearch` |
-| remove_feature | string | Feature types to remove in Panaroo (regex supported) | `tRNA\|rRNA\|ncRNA\|exon\|sequence_feature` |
-| extra | string | Extra command-line arguments for Panaroo | `--clean-mode strict --remove-invalid-genes` |

config/schemas/config.schema.yml

@@ -5,12 +5,16 @@ type: object
 properties:
   samplesheet:
     type: string
-    description: Path to the sample sheet file
+    description: Path to the sample sheet in CSV format
+    default: "config/samples.csv"
   tool:
     type: array
-    description: Annotation tool to use
+    description: Annotation tool(s) to use
+    default: ["prokka"]
     items:
       type: string
+      description: Name of the annotation tool
+      default: "prokka"
       enum:
         - prokka
         - pgap
@@ -21,18 +25,22 @@ properties:
       bin:
         type: string
         description: Path to the PGAP script
+        default: "path/to/pgap.py"
       use_yaml_config:
         type: boolean
         description: Whether to use YAML configuration for PGAP
+        default: true
       prepare_yaml_files:
         type: object
         properties:
           generic:
             type: string
             description: Path to the generic YAML configuration file
+            default: "config/generic.yaml"
           submol:
             type: string
             description: Path to the submol YAML configuration file
+            default: "config/submol.yaml"
         required:
           - generic
           - submol
@@ -46,9 +54,11 @@ properties:
       center:
         type: string
         description: Center name for Prokka annotation (used in sequence IDs)
+        default: ""
       extra:
         type: string
         description: Extra command-line arguments for Prokka
+        default: "--addgenes"
     required:
       - center
       - extra
@@ -58,12 +68,15 @@ properties:
       download_db:
         type: string
         description: Bakta database type, one of 'full', 'light', or 'none' if existing is used
+        default: "light"
       existing_db:
         type: string
         description: Path to an existing Bakta database (optional)
+        default: ""
       extra:
         type: string
         description: Extra command-line arguments for Bakta
+        default: "--keep-contig-headers --compliant"
     required:
       - download_db
       - existing_db
@@ -74,27 +87,38 @@ properties:
       reference_fasta:
         type: string
         description: Path to the reference genome for QUAST
+        default: ""
       reference_gff:
         type: string
         description: Path to the reference annotation for QUAST
+        default: ""
       extra:
         type: string
         description: Extra command-line arguments for QUAST
+        default: ""
+    required:
+      - reference_fasta
+      - reference_gff
+      - extra
   panaroo:
     type: object
     properties:
       skip:
         type: boolean
         description: Whether to skip Panaroo analysis
+        default: false
       remove_source:
         type: string
         description: Source types to remove in Panaroo (regex supported)
+        default: "cmsearch"
       remove_feature:
         type: string
         description: Feature types to remove in Panaroo (regex supported)
+        default: "tRNA|rRNA|ncRNA|exon|sequence_feature"
       extra:
         type: string
         description: Extra command-line arguments for Panaroo
+        default: "--clean-mode strict --remove-invalid-genes"
 
 required:
   - samplesheet
@@ -103,3 +127,4 @@ required:
   - prokka
   - bakta
   - quast
+  - panaroo