orfdata 0.13.0__tar.gz → 0.14.0__tar.gz

{orfdata-0.13.0/orfdata.egg-info → orfdata-0.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.13.0
+Version: 0.14.0
 Summary: Reference open reading frames and experimental translation evidence on annotated transcripts
 Author: OpenVax
 License-Expression: Apache-2.0

{orfdata-0.13.0 → orfdata-0.14.0}/docs/measurements.md

@@ -2,8 +2,8 @@
 
 ORFdata adds evidence to PyEnsembl's reference transcripts and proteins. Its
 quantitative layer stores measurements of genes, transcripts, reference ORFs,
-proteins, protein groups and peptides. A measurement stays at the resolution
-the experiment supports. Parent-gene RNA abundance is useful context for an ORF;
+proteins, protein groups, peptides and source-defined regions. A measurement stays
+at the resolution the experiment supports. Parent-gene RNA abundance is useful context for an ORF;
 it is not a separate measurement of each ORF in that gene.
 
 Install `orfdata[data]` to manage datasets. The registry includes downloadable
@@ -50,6 +50,14 @@ mapping table. The default PyEnsembl target uses its unversioned `id`; request
 mapping across annotation releases, gene isoforms, ORFs or species. A variant or
 fusion product does not inherit a native reference protein measurement.
 
+Use `ScopedTarget(reference, "region", source_id, source_namespace)` for a
+quantified UTR, intron or other source-defined window. Keep its native feature
+type and target length in measurement provenance. A region ID does not assert
+known genomic coordinates or a translated ORF. RNA and Ribo measurements of the
+same region can be compared through an explicit `same_target` relationship;
+such a density ratio describes that region, not a particular uORF inside it.
+Regions do not automatically bind to PyEnsembl or participate in gene/ORF orthology.
+
 For native sources with unreported genomic metadata, use explicit
 [source references and mapping views](source-references.md) to retain the original
 observation alongside its mapping to a PyEnsembl target.

{orfdata-0.13.0 → orfdata-0.14.0}/orfdata/reference.py

@@ -210,7 +210,11 @@ class ReferenceContext:
 
 @dataclass(frozen=True)
 class ScopedTarget:
-    """A source identifier whose reference, kind and dataset cannot be discarded."""
+    """A source identifier whose reference, kind and dataset cannot be discarded.
+
+    ``region`` names a source-defined quantification window (for example a UTR
+    or intron). It does not assert resolved coordinates or a complete ORF.
+    """
 
     reference: ReferenceContext
     kind: str
@@ -220,7 +224,7 @@ class ScopedTarget:
     def __post_init__(self):
         if not isinstance(self.reference, ReferenceContext):
             raise TypeError("Target requires a ReferenceContext")
-        if self.kind not in ("gene", "transcript", "orf", "protein", "protein_group", "peptide"):
+        if self.kind not in ("gene", "transcript", "orf", "protein", "protein_group", "peptide", "region"):
             raise ValueError("Unknown target kind")
         if not all(isinstance(x, str) and x.strip() for x in (self.identifier, self.namespace)):
             raise ValueError("Target identifier and source namespace are required")

orfdata-0.14.0/orfdata/version.py

@@ -0,0 +1 @@
+__version__ = "0.14.0"

{orfdata-0.13.0 → orfdata-0.14.0/orfdata.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.13.0
+Version: 0.14.0
 Summary: Reference open reading frames and experimental translation evidence on annotated transcripts
 Author: OpenVax
 License-Expression: Apache-2.0

{orfdata-0.13.0 → orfdata-0.14.0}/orfdata.egg-info/SOURCES.txt

@@ -67,6 +67,7 @@ tests/test_pfizer_rna.py
 tests/test_reference_context.py
 tests/test_reference_mapping.py
 tests/test_reference_orf.py
+tests/test_region_targets.py
 tests/test_search_reference.py
 tests/test_selectors.py
 tests/test_storage.py
@@ -120,6 +121,8 @@ tests/data/references/context-keys-v0.4.json
 tests/data/references/homo_sapiens.json
 tests/data/references/mus_musculus.json
 tests/data/references/saccharomyces_cerevisiae.json
+tests/data/regions/NOTICE.md
+tests/data/regions/ingolia.json
 tests/data/search_reference/NOTICE.md
 tests/data/search_reference/dog.fasta
 tests/data/search_reference/ensembl83-expected.json

orfdata-0.14.0/tests/data/regions/NOTICE.md

@@ -0,0 +1 @@
+Small factual slices of Ingolia et al. (2009), DOI10.1126/science.1168978, GSE13750. Native columns and original line numbers are preserved; full-source URLs, SHA-256 and sizes are recorded in ingolia.json. GEO unrestricted reuse with attribution. This fixture validates source-defined region targets only, not full reference/ORF mapping or a production source importer.

orfdata-0.14.0/tests/data/regions/ingolia.json

@@ -0,0 +1,110 @@
+[
+  {
+    "sample": "GSM346111",
+    "source": {
+      "url": "https://ftp.ncbi.nlm.nih.gov/geo/samples/GSM346nnn/GSM346111/suppl/GSM346111_fp_rich1_quant.txt.gz",
+      "size": 131843,
+      "sha256": "492f3a630d662de165309628b37ec5c89862f86b80c66391f7421e0f633efe76"
+    },
+    "rows": [
+      {
+        "line": 25,
+        "native": {
+          "yorf": "YAL001C",
+          "norm": "7.306",
+          "dens": "12.406",
+          "count": "43",
+          "len": "3466",
+          "total": "1698134"
+        }
+      },
+      {
+        "line": 26,
+        "native": {
+          "yorf": "YAL001C_3'utr",
+          "norm": "0.000",
+          "dens": "0.000",
+          "count": "0",
+          "len": "50",
+          "total": "1698134"
+        }
+      },
+      {
+        "line": 27,
+        "native": {
+          "yorf": "YAL001C_intron",
+          "norm": "0.000",
+          "dens": "0.000",
+          "count": "0",
+          "len": "82",
+          "total": "1698134"
+        }
+      },
+      {
+        "line": 32,
+        "native": {
+          "yorf": "YAL005C_5'utr",
+          "norm": "134.952",
+          "dens": "229.167",
+          "count": "11",
+          "len": "48",
+          "total": "1698134"
+        }
+      }
+    ]
+  },
+  {
+    "sample": "GSM346117",
+    "source": {
+      "url": "https://ftp.ncbi.nlm.nih.gov/geo/samples/GSM346nnn/GSM346117/suppl/GSM346117_mrna_rich1_quant.txt.gz",
+      "size": 175847,
+      "sha256": "907ddaf47268ea6f36e2363c74a8c001ba48d1dc34617c1461ad5923e57def5b"
+    },
+    "rows": [
+      {
+        "line": 25,
+        "native": {
+          "yorf": "YAL001C",
+          "norm": "33.798",
+          "dens": "49.048",
+          "count": "170",
+          "len": "3466",
+          "total": "1451219"
+        }
+      },
+      {
+        "line": 26,
+        "native": {
+          "yorf": "YAL001C_3'utr",
+          "norm": "55.126",
+          "dens": "80.000",
+          "count": "4",
+          "len": "50",
+          "total": "1451219"
+        }
+      },
+      {
+        "line": 27,
+        "native": {
+          "yorf": "YAL001C_intron",
+          "norm": "0.000",
+          "dens": "0.000",
+          "count": "0",
+          "len": "82",
+          "total": "1451219"
+        }
+      },
+      {
+        "line": 32,
+        "native": {
+          "yorf": "YAL005C_5'utr",
+          "norm": "229.692",
+          "dens": "333.333",
+          "count": "16",
+          "len": "48",
+          "total": "1451219"
+        }
+      }
+    ]
+  }
+]

orfdata-0.14.0/tests/test_region_targets.py

@@ -0,0 +1,104 @@
+"""Source windows stay distinct from complete ORFs across storage and queries."""
+
+import hashlib
+import json
+from dataclasses import replace
+from pathlib import Path
+
+import pytest
+from test_measurements import definition, write_dataset
+
+from orfdata import (
+    Assay,
+    DatasetManifest,
+    Measurement,
+    OrthologyMapping,
+    QuantitativeDataset,
+    ReferenceContext,
+    Sample,
+    ScopedTarget,
+    SourceAsset,
+)
+from orfdata.cli import run
+from orfdata.pairing import AssayPair, MatchedMeasurements, TargetRelation
+
+
+def test_native_regions_roundtrip_and_cli(tmp_path, capsys):
+    path = Path(__file__).parent / "data/regions/ingolia.json"
+    source = json.loads(path.read_text())
+    sha = hashlib.sha256(path.read_bytes()).hexdigest()
+    reference = ReferenceContext(4932, "yeast", None, "SGD", "2008-06-22",
+                                 source_sha256=sha)
+    manifest = DatasetManifest(
+        "regions", "fixture", "Native Ingolia quantification slices", (reference,),
+        (SourceAsset("slice.json", path.as_uri(), sha, path.stat().st_size,
+                     "GEO factual source slice; Ingolia et al. 2009", redistributable=True),),
+        ("https://doi.org/10.1126/science.1168978",), ("rna_seq", "ribo_seq"),
+        dict(source_features=4, source_assays=2, genomic_mapping="unresolved"),
+        dict(scope="native source-region round-trip; not a full source importer"))
+    samples, assays, values = [], [], []
+    for entry in source:
+        sid = entry["sample"]
+        rna = sid == "GSM346117"
+        samples.append(Sample(sid, reference, attributes=dict(strain="BY4741")))
+        assays.append(Assay(sid, sid, "rna_seq" if rna else "ribo_seq", reference))
+        for record in entry["rows"]:
+            row = record["native"]
+            target = ScopedTarget(reference, "region", row["yorf"], "Ingolia2009:feature")
+            for column, unit in (("count", "counts"), ("norm", "RPKM"), ("dens", "reads/kb")):
+                values.append(Measurement(
+                    f"{sid}:{record['line']}:{column}", target, sid, sid,
+                    "rna_abundance" if rna else "ribosome_occupancy", float(row[column]),
+                    unit, manifest.dataset_id, manifest.version,
+                    provenance=dict(source_asset="slice.json", upstream=entry["source"],
+                                    row=record["line"], column=column, native_value=row[column],
+                                    feature_length_nt=int(row["len"]), total_cds_reads=int(row["total"]))))
+    dataset = QuantitativeDataset.create(tmp_path / "source.sqlite", manifest,
+                                         samples=samples, assays=assays, measurements=values)
+    assert dataset.counts["measurement"] == 24 and dataset.counts["target"] == 4
+    assert {m.measurement_id: m for m in dataset.measurements()} == {m.measurement_id: m for m in values}
+    target = ScopedTarget(reference, "region", "YAL005C_5'utr", "Ingolia2009:feature")
+    expected = list(dataset.measurements(target=target, unit="RPKM"))
+    assert len(expected) == 2 and {m.quantity for m in expected} == {"rna_abundance", "ribosome_occupancy"}
+    assert not list(dataset.measurements(target=replace(target, kind="orf")))
+    assert all(Measurement.from_dict(m.to_dict()) == m for m in expected)
+    registry = tmp_path / "registry.json"
+    registry.write_text(json.dumps(definition(dataset)))
+    args = ["datasets", "--registry", str(registry), "--cache-root", str(tmp_path / "cache")]
+    run(args + ["download", "regions", "--quiet"])
+    capsys.readouterr()
+    run(args + ["query", "regions", "--reference", reference.key, "--kind", "region",
+                "--namespace", target.namespace, "--target", target.identifier, "--unit", "RPKM"])
+    assert [Measurement.from_dict(json.loads(line)) for line in capsys.readouterr().out.splitlines()] == expected
+
+
+def test_region_ids_do_not_cross_species_or_reference(tmp_path, experiment):
+    observations = tuple(replace(m, target=replace(m.target, kind="region")) for m in experiment[3])
+    dataset = write_dataset(tmp_path / "regions.sqlite", experiment, measurements=observations)
+    for value in observations:
+        assert list(dataset.measurements(target=value.target)) == [value]
+        wrong = replace(value.target, reference=replace(value.target.reference, annotation_version="111"))
+        with pytest.raises(ValueError, match="not present"):
+            list(dataset.measurements(target=wrong))
+
+
+def test_same_region_ratio_does_not_become_an_orf_estimate(experiment):
+    rna = experiment[3][-1]
+    rna = replace(rna, target=replace(rna.target, kind="region"), value=2, unit="RPKM")
+    rpf = replace(rna, measurement_id="rpf", assay_id="rpf", quantity="ribosome_occupancy", value=6)
+    reference = rna.target.reference
+    pair = AssayPair("pair", reference, "fixture", "1", "rna", "rpf", "same_material",
+                     dict(scope="synthetic assay pairing"))
+    relation = TargetRelation("region", "fixture", "1", rna.target, rpf.target, "same_target",
+                              "one_to_one", dict(scope="same synthetic region"))
+    ratio = MatchedMeasurements(pair, relation, (rna,), (rpf,)).ratio(
+        rpf, rna, measurement_id="ratio", method="explicit source-window density ratio",
+        normalization=dict(scope="same synthetic quantification window"))
+    assert ratio.value == 3 and ratio.target.kind == "region"
+    assert ratio.quantity == "translation_efficiency" and ratio.origin == "derived"
+    with pytest.raises(ValueError, match="gene or transcript"):
+        ScopedTarget.from_pyensembl(object(), kind="region", namespace="test")
+    with pytest.raises(ValueError, match="canonical genes or independently supported ORFs"):
+        OrthologyMapping("regions", rna.target,
+                         replace(rna.target, reference=experiment[0].references[0]),
+                         experiment[0].sources[0], "test", "one_to_one", {"score": 1}, {"source": "synthetic"})

orfdata-0.13.0/orfdata/version.py

@@ -1 +0,0 @@
-__version__ = "0.13.0"