Merge dev: plotting functions, bug fixes including handling of multiallelics

.pre-commit-config.yaml

@@ -32,6 +32,7 @@ repos:
         types: [python]
       - id: mypy
         name: mypy
-        entry: mypy
+        entry: mypy vartracker tests
         language: system
+        pass_filenames: false
         types: [python]

CITATION.cff

@@ -1,12 +1,12 @@
 cff-version: 1.2.0
 message: "If you use this software, please cite it as below."
 title: "vartracker"
-version: "2.1.0"
-date-released: "2026-02-11"
+version: "2.2.0"
+date-released: "2026-05-05"
 license: MIT
 repository-code: "https://github.com/charlesfoster/vartracker"
 url: "https://github.com/charlesfoster/vartracker"
-doi: "10.5281/zenodo.XXXXXXX"
+doi: "10.5281/zenodo.18452274"
 keywords:
   - bioinformatics
   - genomics
@@ -22,7 +22,7 @@ preferred-citation:
     - family-names: Foster
       given-names: Charles
   title: "vartracker"
-  version: "2.1.0"
-  doi: "10.5281/zenodo.XXXXXXX"
+  version: "2.2.0"
+  doi: "10.5281/zenodo.18452274"
   url: "https://github.com/charlesfoster/vartracker"
-  date-released: "2026-02-11"
+  date-released: "2026-05-05"

docs/DEPENDENCIES.md

@@ -14,6 +14,9 @@ The recommended micromamba environment pins the same versions for reproducibilit
 | snakemake | 9.0.1 | 9.0.1 | Snakemake API used for workflows. |
 | bgzip | 1.21 | 1.21 (via htslib) | Provided by htslib; used for VCF compression. |
 
+Consensus FASTA outputs in `bam` and `end-to-end` mode are produced with
+`bcftools consensus` and `samtools depth`; `bedtools` is not required.
+
 If you validate compatibility with older tool versions, update the minimum tested version here and
 consider expanding CI coverage.
 

docs/OUTPUT_SCHEMA.md

@@ -1,6 +1,6 @@
 # Output schema
 
-Schema version: `1.0`
+Schema version: `1.1`
 
 Generated from `vartracker.schemas.RESULTS_SCHEMA`.
 
@@ -28,7 +28,8 @@ Columns that encode per-sample values are slash-separated and ordered by the inp
 | presence_absence | string (slash-separated) | Per-sample presence (Y) or absence (N), ordered by input. |  | Y/N |
 | first_appearance | string | Sample name where the variant first appears. |  |  |
 | last_appearance | string | Sample name where the variant last appears. |  |  |
-| overall_variant_qc | string | Aggregated QC status across samples. |  | PASS, FAIL |
+| all_samples_pass_qc | boolean | True if every sample passes per-sample variant QC. |  | true, false |
+| proportion_samples_passing_qc | number | Proportion of samples passing per-sample variant QC. | fraction | 0-1 |
 | per_sample_variant_qc | string (slash-separated) | Per-sample QC flags (P/F) ordered by input. |  | P, F |
 | aa1_total_properties | string | Physicochemical properties for the reference amino acid. |  | semicolon-separated properties |
 | aa2_total_properties | string | Physicochemical properties for the alternate amino acid. |  | semicolon-separated properties |
@@ -42,4 +43,5 @@ Columns that encode per-sample values are slash-separated and ordered by the inp
 | variant_site_depth | string (slash-separated) | Total read depth at the variant site per sample. | reads |  |
 | variant_window_depth | string (slash-separated) | Mean read depth in the variant window per sample. | reads |  |
 | samples | string (slash-separated) | Sample names corresponding to per-sample fields. |  |  |
+| sample_number | string (slash-separated) | Sample ordering values corresponding to per-sample fields. |  | integer-like sample numbers |
 | total_genome_coverage | string (slash-separated) | Total genome coverage (bases covered) per sample. | bases |  |

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "vartracker"
-version = "2.1.1"
+version = "2.2.0"
 authors = [
     {name = "Dr Charles Foster"},
 ]
@@ -63,7 +63,7 @@ dev = [
     "pytest-cov",
     "black",
     "flake8",
-    "mypy",
+    "mypy>=1.19,<1.20",
     "pre-commit>=3.6",
 ]