ont-bed-generator 0.4.0__tar.gz

ont_bed_generator-0.4.0/.github/workflows/ci.yml

@@ -0,0 +1,38 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+    tags: ["v*"]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0        # required for hatch-vcs (tags)
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install bedtools (parity test)
+        run: sudo apt-get update && sudo apt-get install -y bedtools
+
+      - name: Install package
+        run: pip install -e '.[dev]'
+
+      - name: Lint
+        run: ruff check .
+
+      - name: Type-check
+        run: mypy
+
+      - name: Tests
+        run: pytest -ra

ont_bed_generator-0.4.0/.github/workflows/release.yml

@@ -0,0 +1,49 @@
+name: release
+
+on:
+  push:
+    tags: ["v*"]          # étape 1 : dry-run TestPyPI
+  release:
+    types: [published]    # étape 2 : production PyPI
+  workflow_dispatch:      # dry-run TestPyPI manuel (voir la note sur v0.3.0)
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0                    # tags requis par hatch-vcs
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.x" }
+      - run: python -m pip install build
+      - run: python -m build
+      - run: pipx run twine check dist/*
+      - uses: actions/upload-artifact@v4
+        with: { name: dist, path: dist/ }
+
+  testpypi:
+    needs: build
+    if: github.event_name != 'release'      # tag push OU dispatch manuel
+    runs-on: ubuntu-latest
+    environment: testpypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with: { name: dist, path: dist/ }
+      - uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+
+  pypi:
+    needs: build
+    if: github.event_name == 'release'      # Release GitHub publiée
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with: { name: dist, path: dist/ }
+      - uses: pypa/gh-action-pypi-publish@release/v1

ont_bed_generator-0.4.0/.gitignore

@@ -0,0 +1,13 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.venv/
+venv/
+# version file generated by hatch-vcs
+src/ont_bed_generator/_version.py

ont_bed_generator-0.4.0/CHANGELOG.md

@@ -0,0 +1,70 @@
+# Changelog
+
+All notable changes to this project are documented here.
+Format: [Keep a Changelog](https://keepachangelog.com/en/1.1.0/);
+versioning: [SemVer](https://semver.org/).
+
+## [Unreleased]
+### Added
+- Transparent gzip (`.gz`) support for all input files (genome, genelist, GFF,
+  Entrez map).
+
+### Changed
+- **Breaking:** simplified the genelist format to three columns
+  `Gene | Left_extension_bp | Right_extension_bp` (dropped the Chromosome,
+  Extended_region and Comment columns). The extended-region flag is now derived
+  (a gene is extended iff Left or Right is non-zero); a header row is
+  auto-detected. Existing six-column lists must be converted.
+- Output BEDs are now sorted in canonical karyotypic order (chr1..chrN, then
+  X, Y, then M/MT, contigs last), organism-agnostic. The genome file's line
+  order no longer affects the output; `read_genome` returns sizes only and the
+  internal `rank` ordering was removed in favour of `ordering.chrom_sort_key`.
+
+## [0.1.0] - TBD
+### Added
+- Generation of `targets.bed` and `merged-extended.bed`.
+- Symbol resolution restricted to official HGNC symbols via the Entrez key
+  (GFF `Name=`), handling pseudoautosomal regions and IG/TCR loci.
+- Reporting of invalid / ambiguous symbols (`--strict`).
+- Unit tests + optional `bedtools merge` parity test.
+
+## [0.2.0] - 2026-07-12
+
+### Added
+- Structural invariant tests: merged intervals never overlap within a
+  `(chromosome, strand)` group, every interval stays within `[0, chrom_size]`,
+  and per-strand merging is idempotent.
+
+### Changed
+- **Breaking — genelist format** is now `Gene | Left_extension_bp |
+  Right_extension_bp` with an auto-detected header. The Chromosome,
+  Extended_region and Comment columns were dropped; the extended-region flag is
+  now derived (a gene is extended iff Left or Right is non-zero).
+- Output BEDs are sorted in canonical karyotypic order, independent of the
+  genome file's line order; `read_genome` now returns chromosome sizes only.
+- `GffIndex.by_geneid` renamed to `geneid_to_features`.
+- (internal) Split-line variable unified to `fields` across the readers.
+
+### Removed
+- Dead internal state: `GffGene.strand` and the never-read `geneid_name` index.
+
+## [0.3.0] - 2026-07-13
+
+### Added
+- **Annotation dataset build pipeline** (`annotation/`). A scripted, reproducible
+  chain (`build_gene_gff.sh`) that derives a gene-feature-only, `chr`-named GFF3
+  for T2T-CHM13v2.0 from the official NCBI RefSeq release (RS_2025_08): it keeps
+  only `gene` features, renames RefSeq accessions to `chr` names via the
+  assembly report, and restores the pseudoautosomal chrX copy of *P2RY8*
+  (absent from the NCBI build) from the curated `NM_178129.5` coordinates under
+  the shared `GeneID:286530`, so *P2RY8* resolves on both chrX and chrY like
+  *CRLF2*. The built asset is archived on Zenodo
+  (DOI [10.5281/zenodo.21341240](https://doi.org/10.5281/zenodo.21341240)); the
+  pipeline and its documentation live in `annotation/`. No change to the package
+  code or CLI.
+
+## [0.4.0] - 2026-07-14
+
+### Added
+- **Automated PiPy publishing workflow** (`.github/workflows/release.yml`).
+

ont_bed_generator-0.4.0/CITATION.cff

@@ -0,0 +1,16 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+title: "ont-bed-generator"
+abstract: "Generate BED files for Oxford Nanopore adaptive sampling from a gene list and a RefSeq GFF3."
+type: software
+authors:
+  - family-names: Antoniewski
+    given-names: Christophe
+    orcid: "https://orcid.org/0000-0001-7709-2116"
+license: MIT
+repository-code: "https://github.com/CHANGE-ME/ont-bed-generator"
+keywords:
+  - nanopore
+  - adaptive-sampling
+  - bioinformatics
+  - genomics

ont_bed_generator-0.4.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Christophe Antoniewski
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ont_bed_generator-0.4.0/PKG-INFO

@@ -0,0 +1,143 @@
+Metadata-Version: 2.4
+Name: ont-bed-generator
+Version: 0.4.0
+Summary: Generate BED files for Oxford Nanopore adaptive sampling from a gene list and a RefSeq GFF3.
+Project-URL: Homepage, https://github.com/Institut-Leucemie/ont-bed-generator
+Project-URL: Issues, https://github.com/Institut-Leucemie/ont-bed-generator/issues
+Author: Christophe Antoniewski
+License: MIT License
+        
+        Copyright (c) 2026 Christophe Antoniewski
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: adaptive-sampling,bed,bioinformatics,genomics,nanopore
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == 'dev'
+Requires-Dist: mypy>=1.8; extra == 'dev'
+Requires-Dist: pytest>=7; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Description-Content-Type: text/markdown
+
+![CI](https://github.com/Institut-Leucemie/ont-bed-generator/actions/workflows/ci.yml/badge.svg)
+
+# ont-bed-generator
+
+Generate **BED** files for **Oxford Nanopore adaptive sampling** from a gene
+list and a RefSeq GFF3. Standalone reimplementation (Python standard library
+only, **no runtime dependencies**) of the Galaxy workflow "Adaptative ONT BED
+file generation" (which replaced BED-Craft).
+
+Given a list of target genes and a GFF3 annotation, the tool produces:
+
+- `targets.bed` — the raw locus of each gene (BED6);
+- `merged-extended.bed` — two intervals per locus (`+` / `-` strands),
+  extended, clamped to chromosome bounds, then merged per strand.
+
+## Installation
+
+```bash
+# from source
+git clone https://github.com/CHANGE-ME/ont-bed-generator.git
+cd ont-bed-generator
+pip install .
+```
+
+Conda development environment (includes `bedtools`, used only by the parity
+test):
+
+```bash
+conda env create -f environment.yml   # or: mamba/micromamba env create -f environment.yml
+conda activate ont-bed-generator
+```
+
+## Usage
+
+```bash
+ont-bed-generator \
+    --genelist genelist.tsv \
+    --gff annotation.genes.gff3 \
+    --genome hs1.len \
+    --out-targets targets.bed \
+    --out-merged  merged-extended.bed
+# or: python -m ont_bed_generator --genelist ... --gff ... --genome ...
+```
+
+### Inputs
+
+1. **genelist TSV** — columns `Gene | Left_extension_bp | Right_extension_bp`,
+   with an (auto-detected) header row. Coordinates come from the GFF, so no
+   chromosome column is needed; a gene is treated as an extended region when
+   Left or Right is non-zero (no separate flag). A bare `Gene` line (no
+   extensions) is valid and gets only the default flank. Symbols must be
+   **official HGNC symbols** (check them with the
+   [multi-symbol checker](https://www.genenames.org/tools/multi-symbol-checker/)).
+2. **GFF3** — a RefSeq GFF3 whose `gene` features carry `Name=` and
+   `Dbxref=GeneID:`. The **full NCBI annotation works as-is**: the tool reads
+   only `gene` features and ignores everything else, so pre-extracting them is
+   just an optional speed-up. Gzip-compressed (`.gz`) input is read transparently
+   (this applies to every input file). Example (T2T-CHM13v2.0 / hs1):
+   ```bash
+   curl -sO https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz
+   ```
+3. **genome sizes** — `chrom<TAB>size`, one line per chromosome. Used for
+   telomere clamping only; the line order does not matter (output BEDs are
+   sorted in canonical karyotypic order).
+   ```bash
+   curl -sO https://hgdownload.soe.ucsc.edu/goldenPath/hs1/bigZips/hs1.chrom.sizes
+   ```
+
+### Symbol resolution
+
+Official symbol → GeneID (GFF `Name=`, or external `--entrez-map`) → collect
+**all** loci carrying that GeneID. The Entrez key handles pseudoautosomal
+regions (one GeneID on chrX and chrY yields two loci) and IG/TCR loci. A symbol
+that is not found, or that maps to several GeneIDs, is **reported** (on stderr),
+never guessed. `--strict` returns a non-zero exit code if any symbol is invalid
+or ambiguous.
+
+## Development
+
+```bash
+pip install -e '.[dev]'
+pytest            # unit tests (+ bedtools parity if bedtools is present)
+ruff check .
+mypy
+```
+
+Versioning is driven by git tags (`hatch-vcs`): a release is
+`git tag vX.Y.Z && git push --tags`.
+
+## Intentional differences from the original Galaxy workflow
+
+- The workflow patched non-official symbols (`MKL1→MKLN1`, a bug — MKLN1 is a
+  different gene; `LYL→LYL1`). Here **no patching**: such symbols are reported
+  for correction at the source.
+- The Galaxy output contained a missing merge (`bedtools merge` on
+  genome-order-sorted input without `-g`). This tool performs the correct merge.
+
+## License
+
+MIT — see [LICENSE](LICENSE).

ont_bed_generator-0.4.0/README.md

@@ -0,0 +1,100 @@
+![CI](https://github.com/Institut-Leucemie/ont-bed-generator/actions/workflows/ci.yml/badge.svg)
+
+# ont-bed-generator
+
+Generate **BED** files for **Oxford Nanopore adaptive sampling** from a gene
+list and a RefSeq GFF3. Standalone reimplementation (Python standard library
+only, **no runtime dependencies**) of the Galaxy workflow "Adaptative ONT BED
+file generation" (which replaced BED-Craft).
+
+Given a list of target genes and a GFF3 annotation, the tool produces:
+
+- `targets.bed` — the raw locus of each gene (BED6);
+- `merged-extended.bed` — two intervals per locus (`+` / `-` strands),
+  extended, clamped to chromosome bounds, then merged per strand.
+
+## Installation
+
+```bash
+# from source
+git clone https://github.com/CHANGE-ME/ont-bed-generator.git
+cd ont-bed-generator
+pip install .
+```
+
+Conda development environment (includes `bedtools`, used only by the parity
+test):
+
+```bash
+conda env create -f environment.yml   # or: mamba/micromamba env create -f environment.yml
+conda activate ont-bed-generator
+```
+
+## Usage
+
+```bash
+ont-bed-generator \
+    --genelist genelist.tsv \
+    --gff annotation.genes.gff3 \
+    --genome hs1.len \
+    --out-targets targets.bed \
+    --out-merged  merged-extended.bed
+# or: python -m ont_bed_generator --genelist ... --gff ... --genome ...
+```
+
+### Inputs
+
+1. **genelist TSV** — columns `Gene | Left_extension_bp | Right_extension_bp`,
+   with an (auto-detected) header row. Coordinates come from the GFF, so no
+   chromosome column is needed; a gene is treated as an extended region when
+   Left or Right is non-zero (no separate flag). A bare `Gene` line (no
+   extensions) is valid and gets only the default flank. Symbols must be
+   **official HGNC symbols** (check them with the
+   [multi-symbol checker](https://www.genenames.org/tools/multi-symbol-checker/)).
+2. **GFF3** — a RefSeq GFF3 whose `gene` features carry `Name=` and
+   `Dbxref=GeneID:`. The **full NCBI annotation works as-is**: the tool reads
+   only `gene` features and ignores everything else, so pre-extracting them is
+   just an optional speed-up. Gzip-compressed (`.gz`) input is read transparently
+   (this applies to every input file). Example (T2T-CHM13v2.0 / hs1):
+   ```bash
+   curl -sO https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz
+   ```
+3. **genome sizes** — `chrom<TAB>size`, one line per chromosome. Used for
+   telomere clamping only; the line order does not matter (output BEDs are
+   sorted in canonical karyotypic order).
+   ```bash
+   curl -sO https://hgdownload.soe.ucsc.edu/goldenPath/hs1/bigZips/hs1.chrom.sizes
+   ```
+
+### Symbol resolution
+
+Official symbol → GeneID (GFF `Name=`, or external `--entrez-map`) → collect
+**all** loci carrying that GeneID. The Entrez key handles pseudoautosomal
+regions (one GeneID on chrX and chrY yields two loci) and IG/TCR loci. A symbol
+that is not found, or that maps to several GeneIDs, is **reported** (on stderr),
+never guessed. `--strict` returns a non-zero exit code if any symbol is invalid
+or ambiguous.
+
+## Development
+
+```bash
+pip install -e '.[dev]'
+pytest            # unit tests (+ bedtools parity if bedtools is present)
+ruff check .
+mypy
+```
+
+Versioning is driven by git tags (`hatch-vcs`): a release is
+`git tag vX.Y.Z && git push --tags`.
+
+## Intentional differences from the original Galaxy workflow
+
+- The workflow patched non-official symbols (`MKL1→MKLN1`, a bug — MKLN1 is a
+  different gene; `LYL→LYL1`). Here **no patching**: such symbols are reported
+  for correction at the source.
+- The Galaxy output contained a missing merge (`bedtools merge` on
+  genome-order-sorted input without `-g`). This tool performs the correct merge.
+
+## License
+
+MIT — see [LICENSE](LICENSE).

ont_bed_generator-0.4.0/annotation/README.md

@@ -0,0 +1,96 @@
+# T2T-CHM13v2.0 gene annotation asset for ont-bed-generator
+
+`T2T-CHM13v2.0_genes.chr.gff3.gz` — a **gene-feature-only**, **`chr`-named** GFF3
+derived from the official NCBI RefSeq annotation of T2T-CHM13v2.0, with one
+documented addition (the chrX pseudoautosomal copy of *P2RY8*).
+
+It is the annotation input for `ont-bed-generator --gff`. Everything below is
+reproducible with `build_gene_gff.sh`; nothing is hand-edited except the single,
+sourced line described in step 3.
+
+> **The pre-built asset is archived on Zenodo:**
+> [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.21341240.svg)](https://doi.org/10.5281/zenodo.21341240)
+> Download it there, or rebuild it byte-for-byte with `build_gene_gff.sh`.
+
+## Source
+
+| | |
+|---|---|
+| Assembly | T2T-CHM13v2.0 (`GCF_009914755.1`) |
+| Annotation release | NCBI RefSeq `RS_2025_08` |
+| GFF | `.../GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz` |
+| Assembly report | `.../GCF_009914755.1_T2T-CHM13v2.0_assembly_report.txt` |
+
+Base URL: `https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0`
+
+## Production chain (`build_gene_gff.sh`)
+
+1. **Contig map.** Build a `RefSeq-accession -> chr` table from the official
+   `assembly_report.txt` (column *RefSeq-Accn* -> column *UCSC-style-name*). No
+   hard-coded list: the mapping is read from NCBI's own file.
+2. **Filter + rename.** Keep only `gene` features (column 3 == `gene`; the only
+   thing ont-bed-generator reads) and rename column 1 from the RefSeq accession
+   to the `chr` name using the map. Comment/header lines are dropped. This turns
+   the ~78 MB full annotation into a ~2 MB gene-only file (41 561 genes).
+3. **PAR patch — one added line, fully sourced.** The NCBI `genomic.gff` build
+   annotates *P2RY8* only on chrY, although *P2RY8* is a **PAR1 gene** and is
+   therefore present on both sex chromosomes (its neighbour *CRLF2*, also PAR1,
+   *is* annotated on both by NCBI). We add the missing chrX copy:
+
+   ```
+   chrX  NCBI_RefSeq_curated_NM_178129.5_PAR1  gene  1304499  1338509  .  -  .  \
+     ID=gene-P2RY8-chrX-PAR1;Dbxref=GeneID:286530;Name=P2RY8;gene_biotype=protein_coding
+   ```
+
+   - **Coordinates are not invented.** They are the alignment of NCBI's curated
+     transcript `NM_178129.5` to chrX of hs1, as distributed by UCSC
+     (`chrX:1304499-1338509`). Confirmed against HGNC (symbol `P2RY8` <-> `ENSG`
+     <-> Entrez `286530`) and against the PAR1 gene lists.
+   - **Same `GeneID:286530` as the chrY copy**, so ont-bed-generator groups both
+     loci under one gene and resolves *P2RY8* to **both** chrX and chrY (it is
+     *not* flagged ambiguous — same mechanism as *CRLF2*).
+   - The `source` column records the provenance so the line is auditable in-file.
+
+4. **Compress.** `gzip` the result. Feature order is irrelevant —
+   ont-bed-generator sorts karyotypically itself.
+
+## Get the asset
+
+Either download the archived build from Zenodo
+([10.5281/zenodo.21341240](https://doi.org/10.5281/zenodo.21341240)), or
+regenerate it:
+
+```bash
+bash build_gene_gff.sh          # -> T2T-CHM13v2.0_genes.chr.gff3.gz
+```
+
+Both routes yield the same file for a given NCBI release.
+
+## Verification (performed on this asset)
+
+- 41 562 lines, **all** `gene` features (0 non-gene).
+- `P2RY8` present on chrX (1304499-1338509) **and** chrY (1325951-1401516).
+- `ont-bed-generator` resolves both `P2RY8` and `CRLF2` to two loci each, with
+  **no** invalid and **no** ambiguous symbols.
+
+## Scope & limitations
+
+- Only *P2RY8* is patched. *CRLF2* needs no patch (NCBI annotates it on both X
+  and Y natively). No other PAR1 gene in the target panels required a chrX/chrY
+  copy; audit the PAR1 gene list against this file if your panel adds one.
+- PAR-gene annotation is **inconsistent across all sources** (NCBI, UCSC,
+  Ensembl each differ and each is incomplete for PAR1). This asset takes the
+  NCBI annotation as the traceable base and adds the single, biologically
+  required, NCBI-sourced chrX *P2RY8* copy — rather than switching to a source
+  with its own, different PAR gaps.
+- Tied to NCBI release `RS_2025_08`. Regenerate (and deposit a new Zenodo
+  version) when NCBI publishes a new annotation release — ideally after the
+  upstream *P2RY8* chrX omission is fixed, at which point step 3 becomes
+  unnecessary.
+
+## Citation
+
+If you use this asset, please cite the Zenodo record:
+**DOI [10.5281/zenodo.21341240](https://doi.org/10.5281/zenodo.21341240)**.
+It derives from the NCBI RefSeq annotation of T2T-CHM13v2.0 (`GCF_009914755.1`,
+release RS_2025_08); please also credit NCBI RefSeq as the primary source.

ont_bed_generator-0.4.0/annotation/build_gene_gff.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+# Produce the gene-only, chr-named, PAR-patched GFF3 asset consumed by
+# ont-bed-generator, from the official NCBI RefSeq T2T-CHM13v2.0 annotation.
+set -euo pipefail
+
+BASE="https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0"
+GFF_URL="$BASE/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz"
+REPORT_URL="$BASE/GCF_009914755.1_T2T-CHM13v2.0_assembly_report.txt"
+OUT="T2T-CHM13v2.0_genes.chr.gff3.gz"
+
+# 1) accession -> chr map, from the official assembly report
+curl -s "$REPORT_URL" | tr -d '\r' \
+  | awk -F'\t' '!/^#/ && $7!="na"{print $7"\t"$10}' > map.tsv
+
+# 2) keep only 'gene' features + rename column 1 (accession -> chr); drop comments
+curl -s "$GFF_URL" | zcat \
+  | awk -F'\t' -v OFS='\t' '
+      NR==FNR { m[$1]=$2; next }
+      /^#/    { next }
+      $3=="gene" { if ($1 in m) $1=m[$1]; print }
+    ' map.tsv - > genes.chr.gff3
+
+# 3) append the chrX PAR1 copy of P2RY8 (absent from the NCBI annotation build).
+#    Coordinates = NCBI curated transcript NM_178129.5 aligned to chrX (hs1),
+#    same GeneID:286530 as the chrY copy -> ont-bed resolves both loci, not ambiguous.
+STRAND=$(awk -F'\t' 'index($9,"Name=P2RY8;"){print $7; exit}' genes.chr.gff3)
+printf 'chrX\tNCBI_RefSeq_curated_NM_178129.5_PAR1\tgene\t1304499\t1338509\t.\t%s\t.\tID=gene-P2RY8-chrX-PAR1;Dbxref=GeneID:286530;Name=P2RY8;gene_biotype=protein_coding\n' "$STRAND" >> genes.chr.gff3
+
+# 4) compress (order is irrelevant; ont-bed-generator sorts karyotypically itself)
+gzip -c genes.chr.gff3 > "$OUT"
+echo "written: $OUT"

ont_bed_generator-0.4.0/environment.yml

@@ -0,0 +1,11 @@
+name: ont-bed-generator
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - python>=3.10
+  - pip
+  # bedtools is used ONLY by the parity test (the package has no runtime dep on it)
+  - bedtools>=2.31
+  - pip:
+      - -e .[dev]

ont_bed_generator-0.4.0/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "ont-bed-generator"
+description = "Generate BED files for Oxford Nanopore adaptive sampling from a gene list and a RefSeq GFF3."
+readme = "README.md"
+license = { file = "LICENSE" }
+requires-python = ">=3.10"
+authors = [{ name = "Christophe Antoniewski" }]
+keywords = ["nanopore", "adaptive-sampling", "bed", "bioinformatics", "genomics"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Operating System :: OS Independent",
+]
+# No runtime dependencies: standard library only.
+dependencies = []
+dynamic = ["version"]
+
+[project.urls]
+Homepage = "https://github.com/Institut-Leucemie/ont-bed-generator"
+Issues = "https://github.com/Institut-Leucemie/ont-bed-generator/issues"
+
+[project.optional-dependencies]
+dev = ["pytest>=7", "ruff>=0.4", "mypy>=1.8", "build>=1.2"]
+
+[project.scripts]
+ont-bed-generator = "ont_bed_generator.cli:main"
+
+# ── Versioning driven by git tags (hatch-vcs) ──
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "src/ont_bed_generator/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/ont_bed_generator"]
+
+# ── Quality tools ──
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+files = ["src"]
+
+[[tool.mypy.overrides]]
+module = "ont_bed_generator._version"
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra"