orfdata 0.28.0__tar.gz → 0.29.0__tar.gz

{orfdata-0.28.0 → orfdata-0.29.0}/MANIFEST.in

@@ -1,4 +1,6 @@
 include lint.sh test.sh deploy.sh docs.sh mkdocs.yml
+recursive-include tools *.py
+recursive-include tests/data/viral *.gz
 recursive-include docs *.md *.css
 recursive-include tests *.py *.json *.md *.tsv *.fasta
 recursive-include tests/data/copy *.xlsx *.gz *.soft *.xml *.pdf

{orfdata-0.28.0/orfdata.egg-info → orfdata-0.29.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.28.0
+Version: 0.29.0
 Summary: Reference proteomes with evidence-backed noncanonical ORFs on PyEnsembl genomes
 Author: OpenVax
 License-Expression: Apache-2.0
@@ -11,6 +11,7 @@ Provides-Extra: pyensembl
 Requires-Dist: pyensembl>=2.27.2; extra == "pyensembl"
 Provides-Extra: build-data
 Requires-Dist: openpyxl>=3.1; extra == "build-data"
+Requires-Dist: biopython<2,>=1.80; extra == "build-data"
 Provides-Extra: data
 Requires-Dist: datacache<2,>=1.25.1; extra == "data"
 Provides-Extra: columnar
@@ -21,6 +22,7 @@ Requires-Dist: ruff; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
 Requires-Dist: openpyxl>=3.1; extra == "dev"
+Requires-Dist: biopython<2,>=1.80; extra == "dev"
 Requires-Dist: pyensembl>=2.27.2; extra == "dev"
 Requires-Dist: datacache<2,>=1.25.1; extra == "dev"
 Provides-Extra: docs
@@ -102,6 +104,13 @@ Human evidence is never transferred to another species. Viral proteomes can be a
 orfdata also provides [RNA, ribosome and protein measurements](https://openvax.github.io/orfdata/measurements/)
 for human, mouse, dog and yeast.
 
+`viral_orfs(reference_dna, contig="HPV16")` loads source-defined viral CDSs as
+existing RNA/ORF models, offline and qualified by exact reference sequence.
+The first [coding reference](https://openvax.github.io/orfdata/viral/) contains
+the nine RefSeq NC_001526.4 HPV16 CDSs, with native and GDC placements;
+`viral_references()` lists the available identities and coverage. Broader
+imports remain in [the viral roadmap](https://github.com/openvax/orfdata/issues/91).
+
 ## Measurement datasets
 
 RNA, ribosome and protein measurements are separate, downloadable datasets with

{orfdata-0.28.0 → orfdata-0.29.0}/README.md

@@ -72,6 +72,13 @@ Human evidence is never transferred to another species. Viral proteomes can be a
 orfdata also provides [RNA, ribosome and protein measurements](https://openvax.github.io/orfdata/measurements/)
 for human, mouse, dog and yeast.
 
+`viral_orfs(reference_dna, contig="HPV16")` loads source-defined viral CDSs as
+existing RNA/ORF models, offline and qualified by exact reference sequence.
+The first [coding reference](https://openvax.github.io/orfdata/viral/) contains
+the nine RefSeq NC_001526.4 HPV16 CDSs, with native and GDC placements;
+`viral_references()` lists the available identities and coverage. Broader
+imports remain in [the viral roadmap](https://github.com/openvax/orfdata/issues/91).
+
 ## Measurement datasets
 
 RNA, ribosome and protein measurements are separate, downloadable datasets with

orfdata-0.29.0/docs/viral.md

@@ -0,0 +1,45 @@
+# Viral coding references
+
+`viral_orfs()` returns existing `TranscriptORF` objects for source-annotated
+viral CDSs. Supply the complete reference DNA that the RNA was aligned to:
+
+```python
+from orfdata import viral_orfs, viral_references
+
+print([(r["id"], r["coding_models"]) for r in viral_references()])
+# [('NC_001526.4', 9), ('GRCh38.d1.vd1:HPV16', 9)]
+
+orfs = viral_orfs(reference_dna, contig="HPV16")
+for orf in orfs:
+    print(orf.orf_id, orf.gene_name, orf.coding_blocks, orf.protein_sequence)
+```
+
+The small bundled catalogue loads offline without PyEnsembl, Biopython or a
+human genome. Its nine HPV16 CDSs come from RefSeq NC_001526.4. The loader
+requires an exact full-DNA hash and separately qualifies native and GDC
+circular rotations. A contig name or related strain is insufficient.
+An unavailable reference raises `ValueError`, distinct from a valid empty query.
+`viral_references()` exposes exact identities, coding coverage, source pins
+and product names without loading other data.
+
+Each model uses a `SourceRNA` containing only the available CDS, including
+ordered splice blocks. Full transcript ends are not asserted. The existing
+`TranscriptORF.at()` validates its source protein and coding boundaries.
+These models have `orf_type="reference_CDS"`. Their internal kind `extra_orf`
+describes a source-defined ORF outside a loaded PyEnsembl annotation, not a
+claim that a RefSeq CDS is biologically noncanonical. No Ribo-seq or MS
+support is inferred from the reference annotation.
+
+The nine annotations are not an exhaustive HPV16 ORF catalogue. Other HPV
+types/lineages, EBV/KSHV, CMV, hepatitis viruses including HDV, HTLV-1/HIV,
+and polyomaviruses remain explicit coverage work in
+[issues #91–98](https://github.com/openvax/orfdata/issues/91).
+
+Isovar owns reconstructed sample RNA and read evidence. It can use these
+coding paths to anchor a frame on observed sequence, preserving variants
+and incomplete starts/stops. ORFdata does not assemble sample RNA, replace
+missing bases, infer protein abundance or establish viral tumor causality.
+RNA and coding-reference matches are not direct protein evidence.
+
+Source attribution and rebuilding instructions are in
+[`orfdata/data/viral/NOTICE.md`](https://github.com/openvax/orfdata/blob/main/orfdata/data/viral/NOTICE.md).

{orfdata-0.28.0 → orfdata-0.29.0}/mkdocs.yml

@@ -21,6 +21,7 @@ nav:
   - Home: index.md
   - Proteomes:
       - Build a reference proteome: proteome.md
+      - Viral coding references: viral.md
   - Noncanonical ORFs:
       - ORFs and evidence: reference.md
       - Examples: examples.md

{orfdata-0.28.0 → orfdata-0.29.0}/orfdata/__init__.py

@@ -70,8 +70,11 @@ from .rna import IRES, ProteinProduct, RNAFeature, SourceRNA, products_from_unip
 from .search_reference import SearchMembership, SearchReference, SearchReferenceSpec, SearchSequence
 from .sequence import GeneticCode, genetic_code
 from .version import __version__
+from .viral import viral_orfs, viral_references
 
 __all__ = [
+    "viral_orfs",
+    "viral_references",
     "__version__",
     "Proteome",
     "ProteomeEntry",

orfdata-0.29.0/orfdata/data/viral/NOTICE.md

@@ -0,0 +1,31 @@
+# HPV16 coding reference
+
+Source: NCBI RefSeq **NC_001526.4**, complete GenBank record:
+https://www.ncbi.nlm.nih.gov/sviewer/viewer.fcgi?id=NC_001526.4&db=nuccore&report=genbank&retmode=text
+
+Source record SHA256:
+`282be442f226cc809fefbda616ac136b8d20dfde23fad09558f3f653a3de96a4`.
+Source authors and annotation provenance remain in the versioned record,
+preserved as a compressed test fixture. NCBI database usage policies apply:
+https://www.ncbi.nlm.nih.gov/home/about/policies/ . No endorsement is implied.
+
+The catalogue contains nine source-annotated CDSs, including two joined paths.
+It does not claim all reported HPV16 ORFs or complete transcript models.
+RNA support does not establish translation or protein expression.
+
+Native DNA MD5: `08d2b3849496d12cc45fd4df713d5c2f`.
+GDC GRCh38.d1.vd1 HPV16 DNA MD5: `f2463721818c29998ef5ab917e6df74a`.
+GDC DNA is the source circle rotated by 864 bases. Both placements retain
+their own SHA256 and ordered, 1-based inclusive coding blocks.
+GDC reference files: https://gdc.cancer.gov/about-data/gdc-data-processing/gdc-reference-files .
+
+Rebuild with `orfdata[build-data]` installed:
+
+```sh
+python tools/build_hpv16_cds.py tests/data/viral/NC_001526.4.gb.gz \
+  orfdata/data/viral/hpv16-refseq-CDS.json.gz
+```
+
+The builder checks source DNA identity, the exact GDC rotation and all nine
+source translations. The resource checksum is pinned in `orfdata/viral.py`.
+Broader coverage: https://github.com/openvax/orfdata/issues/91 through 98.

orfdata-0.29.0/orfdata/version.py

@@ -0,0 +1 @@
+__version__ = "0.29.0"

orfdata-0.29.0/orfdata/viral.py

@@ -0,0 +1,111 @@
+"""Offline, sequence-qualified viral CDSs bound to the existing RNA/ORF models."""
+
+import copy
+import gzip
+import hashlib
+import json
+from functools import lru_cache
+from importlib.resources import files
+
+from .model import TranscriptORF
+from .reference import ReferenceContext
+from .rna import SourceRNA
+
+_CATALOG_SHA256 = "52ab8181b9d3f199dde3afabc8440ee9a8c912291c6425c99fb4225e29ad1a70"
+_COMPLEMENT = str.maketrans("ACGT", "TGCA")
+
+
+@lru_cache(maxsize=1)
+def _catalog():
+    raw = files("orfdata").joinpath("data/viral/hpv16-refseq-CDS.json.gz").read_bytes()
+    if hashlib.sha256(raw).hexdigest() != _CATALOG_SHA256:
+        raise ValueError("Bundled viral CDS catalogue checksum mismatch")
+    data = json.loads(gzip.decompress(raw))
+    if data["schema"] != "orfdata.viral_cds.v1":
+        raise ValueError("Unsupported viral CDS catalogue schema")
+    return data
+
+
+def viral_references():
+    """List released viral coding-reference identities, without network access.
+
+    Returns
+    -------
+    tuple of dict
+        Exact sequence hashes, accession/source pins, coding-model counts and
+        coverage scope. A listed reference is not a complete transcript or
+        exhaustive ORF catalogue. Returned dictionaries are independent copies.
+    """
+    data = _catalog()
+    return tuple(dict(**{key: copy.deepcopy(value) for key, value in row.items()
+                         if key != "coding_blocks"},
+                      coding_models=len(row["coding_blocks"]), scope=data["scope"],
+                      catalogue_sha256=_CATALOG_SHA256,
+                      products=[dict(protein_id=cds["protein_id"], gene=cds["gene"],
+                                     product=cds["product"]) for cds in data["cds"]])
+                 for row in data["references"])
+
+
+def viral_orfs(reference_sequence, *, contig=None):
+    """Load source-defined CDSs for one exactly matching viral DNA reference.
+
+    Parameters
+    ----------
+    reference_sequence : str
+        Complete forward reference DNA, not sample RNA. No annotation is
+        transferred to mismatching strains or by contig name alone.
+    contig : str, optional
+        The caller's name for this exact DNA in an alignment reference. The
+        original versioned source identity remains on every ORF's context.
+
+    Returns
+    -------
+    tuple of TranscriptORF
+        Source CDS fragments represented with SourceRNA and TranscriptORF.at.
+        Their genomic blocks are 1-based inclusive and their RNA sequence is
+        only the available CDS. Full transcript boundaries are not asserted.
+        No ribosome, peptide or sample protein-expression evidence is inferred.
+
+    Raises
+    ------
+    ValueError
+        No released coding reference matches, or a source model fails to bind
+        and translate exactly. Discovery is available through viral_references.
+    """
+    sequence = str(reference_sequence).upper()
+    fingerprint = hashlib.sha256(sequence.encode("ascii")).hexdigest()
+    data = _catalog()
+    matches = [row for row in data["references"] if row["sequence_sha256"] == fingerprint
+               and row["length"] == len(sequence)]
+    if len(matches) != 1:
+        raise ValueError("No unique released viral coding reference matches this DNA; "
+                         "inspect viral_references() for available sequence identities")
+    reference = matches[0]
+    source = reference["source"]
+    label = contig if contig is not None else reference["id"]
+    if not isinstance(label, str) or not label:
+        raise ValueError("contig must be a nonempty name")
+    context = ReferenceContext(
+        taxon_id=reference["taxon_id"], species=reference["species"],
+        genome_build=reference["id"], annotation_name="NCBI RefSeq",
+        annotation_version=source["accession"], sequence_sha256=fingerprint,
+        source_sha256=source["sha256"])
+    result = []
+    for cds in data["cds"]:
+        protein_id = cds["protein_id"]
+        blocks = reference["coding_blocks"][protein_id]
+        coding = "".join(sequence[a - 1:b] if cds["strand"] == "+" else
+                         sequence[a - 1:b].translate(_COMPLEMENT)[::-1] for a, b in blocks)
+        if cds["phase"] != 0:
+            raise ValueError(f"Unsupported partial source codon: {protein_id}")
+        rna = SourceRNA(
+            id=f"{source['accession']}:CDS:{protein_id}", sequence=coding, reference=context,
+            source=f"NCBI RefSeq {source['accession']}", contig=label, strand=cds["strand"],
+            exons=blocks, gene_name=cds["gene"], biotype="source_CDS_fragment")
+        orf = TranscriptORF.at(rna, 0, orf_id=protein_id, source=rna.source,
+                               protein=cds["protein_sequence"], translation_table=cds["translation_table"],
+                               orf_type="reference_CDS", start_complete=cds["start_complete"])
+        if orf.coding_sequence != coding or orf.stop_complete != cds["stop_complete"]:
+            raise ValueError(f"Source coding boundaries do not translate exactly: {protein_id}")
+        result.append(orf)
+    return tuple(result)

{orfdata-0.28.0 → orfdata-0.29.0/orfdata.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.28.0
+Version: 0.29.0
 Summary: Reference proteomes with evidence-backed noncanonical ORFs on PyEnsembl genomes
 Author: OpenVax
 License-Expression: Apache-2.0
@@ -11,6 +11,7 @@ Provides-Extra: pyensembl
 Requires-Dist: pyensembl>=2.27.2; extra == "pyensembl"
 Provides-Extra: build-data
 Requires-Dist: openpyxl>=3.1; extra == "build-data"
+Requires-Dist: biopython<2,>=1.80; extra == "build-data"
 Provides-Extra: data
 Requires-Dist: datacache<2,>=1.25.1; extra == "data"
 Provides-Extra: columnar
@@ -21,6 +22,7 @@ Requires-Dist: ruff; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
 Requires-Dist: openpyxl>=3.1; extra == "dev"
+Requires-Dist: biopython<2,>=1.80; extra == "dev"
 Requires-Dist: pyensembl>=2.27.2; extra == "dev"
 Requires-Dist: datacache<2,>=1.25.1; extra == "dev"
 Provides-Extra: docs
@@ -102,6 +104,13 @@ Human evidence is never transferred to another species. Viral proteomes can be a
 orfdata also provides [RNA, ribosome and protein measurements](https://openvax.github.io/orfdata/measurements/)
 for human, mouse, dog and yeast.
 
+`viral_orfs(reference_dna, contig="HPV16")` loads source-defined viral CDSs as
+existing RNA/ORF models, offline and qualified by exact reference sequence.
+The first [coding reference](https://openvax.github.io/orfdata/viral/) contains
+the nine RefSeq NC_001526.4 HPV16 CDSs, with native and GDC placements;
+`viral_references()` lists the available identities and coverage. Broader
+imports remain in [the viral roadmap](https://github.com/openvax/orfdata/issues/91).
+
 ## Measurement datasets
 
 RNA, ribosome and protein measurements are separate, downloadable datasets with

{orfdata-0.28.0 → orfdata-0.29.0}/orfdata.egg-info/SOURCES.txt

@@ -24,6 +24,7 @@ docs/search-references.md
 docs/source-references.md
 docs/species.md
 docs/storage.md
+docs/viral.md
 docs/stylesheets/docs.css
 orfdata/__init__.py
 orfdata/_pinned_genome.py
@@ -56,6 +57,7 @@ orfdata/rna.py
 orfdata/search_reference.py
 orfdata/sequence.py
 orfdata/version.py
+orfdata/viral.py
 orfdata.egg-info/PKG-INFO
 orfdata.egg-info/SOURCES.txt
 orfdata.egg-info/dependency_links.txt
@@ -75,6 +77,8 @@ orfdata/data/uorf-evidence/AUTHOR-LICENSE.txt
 orfdata/data/uorf-evidence/NOTICE.txt
 orfdata/data/uorf-evidence/catalog.json.gz
 orfdata/data/uorf-evidence/manifest.json
+orfdata/data/viral/NOTICE.md
+orfdata/data/viral/hpv16-refseq-CDS.json.gz
 orfdata/sources/__init__.py
 orfdata/sources/copy.py
 orfdata/sources/ingolia.py
@@ -116,6 +120,7 @@ tests/test_search_reference.py
 tests/test_selectors.py
 tests/test_storage.py
 tests/test_uorf_catalog.py
+tests/test_viral.py
 tests/test_wang.py
 tests/data/aggregate_evidence.json
 tests/data/copy/GSM1905474.soft
@@ -221,6 +226,7 @@ tests/data/storage/v2.json
 tests/data/storage/v2.sqlite
 tests/data/storage/v3.json
 tests/data/storage/v3.sqlite
+tests/data/viral/NC_001526.4.gb.gz
 tests/data/wang/NOTICE.md
 tests/data/wang/annotation.gtf.gz
 tests/data/wang/copies.zip
@@ -228,4 +234,6 @@ tests/data/wang/expected.json
 tests/data/wang/manifest.json
 tests/data/wang/protein.zip
 tests/data/wang/rna.zip
-tests/data/wang/search.fasta.gz
+tests/data/wang/search.fasta.gz
+tools/__init__.py
+tools/build_hpv16_cds.py

{orfdata-0.28.0 → orfdata-0.29.0}/orfdata.egg-info/requires.txt

@@ -1,6 +1,7 @@
 
 [build-data]
 openpyxl>=3.1
+biopython<2,>=1.80
 
 [columnar]
 pyarrow>=14
@@ -14,6 +15,7 @@ ruff
 build
 twine
 openpyxl>=3.1
+biopython<2,>=1.80
 pyensembl>=2.27.2
 datacache<2,>=1.25.1
 

{orfdata-0.28.0 → orfdata-0.29.0}/pyproject.toml

@@ -14,10 +14,10 @@ dependencies = []
 
 [project.optional-dependencies]
 pyensembl = ["pyensembl>=2.27.2"]
-build-data = ["openpyxl>=3.1"]
+build-data = ["openpyxl>=3.1", "biopython>=1.80,<2"]
 data = ["datacache>=1.25.1,<2"]
 columnar = ["pyarrow>=14"]
-dev = ["pytest", "ruff", "build", "twine", "openpyxl>=3.1", "pyensembl>=2.27.2", "datacache>=1.25.1,<2"]
+dev = ["pytest", "ruff", "build", "twine", "openpyxl>=3.1", "biopython>=1.80,<2", "pyensembl>=2.27.2", "datacache>=1.25.1,<2"]
 docs = ["mkdocs>=1.6,<2", "mkdocs-material>=9.5,<10"]
 
 [project.scripts]
@@ -30,7 +30,7 @@ version = {attr = "orfdata.version.__version__"}
 include = ["orfdata*"]
 
 [tool.setuptools.package-data]
-orfdata = ["data/uorf-evidence/*", "data/orf-evidence/*", "data/ires/*", "data/datasets.json", "data/catalogs.json", "data/chains.json", "data/genomes.json"]
+orfdata = ["data/uorf-evidence/*", "data/orf-evidence/*", "data/ires/*", "data/viral/*", "data/datasets.json", "data/catalogs.json", "data/chains.json", "data/genomes.json"]
 
 [tool.ruff]
 target-version = "py39"

orfdata-0.29.0/tests/test_viral.py

@@ -0,0 +1,110 @@
+"""Qualify real, versioned viral CDS paths independently of sample assembly."""
+
+import gzip
+import hashlib
+import io
+import json
+from importlib.resources import files
+from pathlib import Path
+
+import pytest
+from Bio import SeqIO
+
+from orfdata import SourceRNA, viral_orfs, viral_references
+from tools.build_hpv16_cds import build
+
+FIXTURE = Path(__file__).parent / "data/viral/NC_001526.4.gb.gz"
+EXPECTED = {
+    "YP_009268708.1": 92, "NP_041327.2": 649, "NP_041328.1": 365,
+    "NP_041330.2": 83, "NP_041331.2": 473, "NP_041332.2": 505,
+    "NP_041325.1": 158, "YP_009268707.1": 50, "NP_041326.1": 98,
+}
+
+
+@pytest.fixture
+def source():
+    raw = gzip.decompress(FIXTURE.read_bytes())
+    assert hashlib.sha256(raw).hexdigest() == "282be442f226cc809fefbda616ac136b8d20dfde23fad09558f3f653a3de96a4"
+    return raw, SeqIO.read(io.StringIO(raw.decode()), "genbank")
+
+
+def test_catalogue_rebuilds_from_the_pinned_public_annotation(source):
+    raw, _ = source
+    packaged = json.loads(gzip.decompress(files("orfdata").joinpath(
+        "data/viral/hpv16-refseq-CDS.json.gz").read_bytes()))
+    assert build(raw) == packaged
+    assert len(packaged["cds"]) == 9
+
+
+def test_native_source_paths_match_all_nine_source_proteins(source):
+    _, record = source
+    orfs = viral_orfs(str(record.seq))
+    definitions = {f.qualifiers["protein_id"][0]: f for f in record.features if f.type == "CDS"}
+    assert {orf.orf_id: len(orf.protein_sequence) for orf in orfs} == EXPECTED
+    for orf in orfs:
+        feature = definitions[orf.orf_id]
+        assert isinstance(orf.transcript, SourceRNA)
+        assert orf.transcript.biotype == "source_CDS_fragment"
+        assert orf.transcript.genome is None
+        assert orf.protein_sequence == feature.qualifiers["translation"][0]
+        assert orf.coding_sequence == str(feature.extract(record.seq))
+        assert orf.start_complete and orf.stop_complete
+        assert orf.context.annotation_version == "NC_001526.4"
+        assert orf.context.taxon_id == 333760
+        assert not orf.evidence.has_evidence("ms")
+        assert not orf.evidence.has_evidence("ribosome")
+
+
+def test_gdc_rotation_is_exact_and_retains_spliced_coding_positions(source):
+    _, record = source
+    native = str(record.seq)
+    gdc = native[-864:] + native[:-864]
+    assert hashlib.md5(gdc.encode()).hexdigest() == "f2463721818c29998ef5ab917e6df74a"
+    orfs = {orf.orf_id: orf for orf in viral_orfs(gdc, contig="HPV16")}
+    assert orfs["YP_009268708.1"].coding_blocks == ((865, 880), (3358, 3620))
+    assert orfs["YP_009268707.1"].coding_blocks == ((83, 226), (409, 417))
+    assert orfs["NP_041326.1"].coding_blocks == ((562, 858),)
+    for orf in orfs.values():
+        assert orf.transcript.contig == "HPV16"
+        assert orf.context.genome_build == "GRCh38.d1.vd1:HPV16"
+        assert orf.protein_sequence == next(o.protein_sequence for o in viral_orfs(native)
+                                            if o.orf_id == orf.orf_id)
+
+
+def test_mutated_same_name_reference_and_partial_dna_are_not_qualified(source):
+    _, record = source
+    native = str(record.seq)
+    changed = ("A" if native[0] != "A" else "C") + native[1:]
+    for sequence in (changed, native[1:], native[::-1]):
+        with pytest.raises(ValueError, match="No unique released"):
+            viral_orfs(sequence, contig="HPV16")
+
+
+def test_discovery_is_offline_and_returned_metadata_cannot_change_loading(source):
+    _, record = source
+    references = viral_references()
+    assert {row["id"] for row in references} == {"NC_001526.4", "GRCh38.d1.vd1:HPV16"}
+    assert all(row["coding_models"] == 9 for row in references)
+    assert all(row["catalogue_sha256"] and row["source"]["sha256"] for row in references)
+    references[0]["source"]["accession"] = "changed"
+    assert viral_references()[0]["source"]["accession"] == "NC_001526.4"
+    assert viral_orfs(str(record.seq))[0].context.annotation_version == "NC_001526.4"
+
+
+def test_corrupt_packaged_catalogue_fails_before_returning_models(monkeypatch):
+    import orfdata.viral as module
+
+    class CorruptResource:
+        def joinpath(self, path):
+            return self
+
+        def read_bytes(self):
+            return b"corrupt catalogue"
+
+    module._catalog.cache_clear()
+    try:
+        monkeypatch.setattr(module, "files", lambda name: CorruptResource())
+        with pytest.raises(ValueError, match="checksum mismatch"):
+            viral_references()
+    finally:
+        module._catalog.cache_clear()

orfdata-0.29.0/tools/__init__.py

@@ -0,0 +1 @@
+"""Source catalogue builders, excluded from the installed runtime package."""

orfdata-0.29.0/tools/build_hpv16_cds.py

@@ -0,0 +1,89 @@
+"""Rebuild the small HPV16 CDS catalogue from its versioned RefSeq GenBank record.
+
+Requires Biopython only for building, not for loading the released catalogue.
+The GDC placement is an exact circular rotation, verified against the DNA MD5
+of the pinned GDC reference, not an alignment-based annotation transfer.
+"""
+
+import argparse
+import gzip
+import hashlib
+import io
+import json
+from pathlib import Path
+
+from Bio import SeqIO
+
+ACCESSION = "NC_001526.4"
+NATIVE_MD5 = "08d2b3849496d12cc45fd4df713d5c2f"
+GDC_MD5 = "f2463721818c29998ef5ab917e6df74a"
+ROTATION = 864
+SOURCE = ("https://www.ncbi.nlm.nih.gov/sviewer/viewer.fcgi?"
+          "id=NC_001526.4&db=nuccore&report=genbank&retmode=text")
+
+
+def build(genbank):
+    record = SeqIO.read(io.StringIO(genbank.decode()), "genbank")
+    native = str(record.seq).upper()
+    gdc = native[-ROTATION:] + native[:-ROTATION]
+    if record.id != ACCESSION or hashlib.md5(native.encode()).hexdigest() != NATIVE_MD5:
+        raise ValueError("The source is not the pinned NC_001526.4 DNA")
+    if hashlib.md5(gdc.encode()).hexdigest() != GDC_MD5:
+        raise ValueError("The circular rotation does not match the GDC DNA")
+    definitions = []
+    native_blocks, gdc_blocks = {}, {}
+    for feature in record.features:
+        if feature.type != "CDS":
+            continue
+        q = feature.qualifiers
+        if feature.location.strand != 1 or int(q.get("codon_start", [1])[0]) != 1:
+            raise ValueError("This source builder requires complete plus-strand CDSs")
+        protein_id = q["protein_id"][0]
+        blocks = [[int(part.start) + 1, int(part.end)] for part in feature.location.parts]
+        moved = [[(a - 1 + ROTATION) % len(native) + 1,
+                  (b - 1 + ROTATION) % len(native) + 1] for a, b in blocks]
+        if any(a > b for a, b in moved):
+            raise ValueError("A rotated coding block crosses the origin; qualify it explicitly")
+        coding = feature.extract(record.seq)
+        protein = q["translation"][0]
+        table = int(q.get("transl_table", [1])[0])
+        if str(coding.translate(table=table, cds=True)) != protein:
+            raise ValueError(f"Source translation mismatch: {protein_id}")
+        definitions.append(dict(protein_id=protein_id, gene=q.get("gene", [None])[0],
+                                product=q["product"][0], protein_sequence=protein,
+                                translation_table=table, strand="+", phase=0,
+                                start_complete=True, stop_complete=True))
+        native_blocks[protein_id] = blocks
+        gdc_blocks[protein_id] = moved
+    if len(definitions) != 9:
+        raise ValueError("Expected the nine annotated CDSs in this source version")
+    source = dict(accession=ACCESSION, url=SOURCE, sha256=hashlib.sha256(genbank).hexdigest())
+    references = []
+    for name, sequence, blocks, offset in (
+            (ACCESSION, native, native_blocks, 0),
+            ("GRCh38.d1.vd1:HPV16", gdc, gdc_blocks, ROTATION)):
+        references.append(dict(id=name, taxon_id=333760, species="human_papillomavirus_16",
+            length=len(sequence), sequence_md5=hashlib.md5(sequence.encode()).hexdigest(),
+            sequence_sha256=hashlib.sha256(sequence.encode()).hexdigest(),
+            source=source, native_to_reference_rotation=offset, coding_blocks=blocks))
+    return dict(schema="orfdata.viral_cds.v1", source=source,
+                scope="Nine source-annotated HPV16 CDSs; not all HPV ORFs or complete transcript models",
+                references=references, cds=definitions)
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("genbank", type=Path)
+    parser.add_argument("output", type=Path)
+    args = parser.parse_args()
+    raw = args.genbank.read_bytes()
+    if args.genbank.suffix == ".gz":
+        raw = gzip.decompress(raw)
+    payload = json.dumps(build(raw), sort_keys=True, separators=(",", ":")).encode() + b"\n"
+    args.output.parent.mkdir(parents=True, exist_ok=True)
+    args.output.write_bytes(gzip.compress(payload, mtime=0))
+    print(hashlib.sha256(args.output.read_bytes()).hexdigest())
+
+
+if __name__ == "__main__":
+    main()

orfdata-0.28.0/orfdata/version.py

@@ -1 +0,0 @@
-__version__ = "0.28.0"