orfdata 0.40.0__tar.gz → 0.41.0__tar.gz

{orfdata-0.40.0/orfdata.egg-info → orfdata-0.41.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: orfdata
-Version: 0.40.0
+Version: 0.41.0
 Summary: Reference proteomes with evidence-backed noncanonical ORFs on PyEnsembl genomes
 Author: OpenVax
 License-Expression: Apache-2.0
@@ -10,29 +10,21 @@ License-File: LICENSE
 Requires-Dist: datacache<2,>=1.29.3
 Requires-Dist: pandas<4,>=3
 Requires-Dist: pyyaml<7,>=6
-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: pyensembl>=2.27.2
+Requires-Dist: openpyxl<4,>=3.1
+Requires-Dist: pyarrow>=14
+Requires-Dist: biotite<3,>=1.6
+Requires-Dist: pyahocorasick<3,>=2.3
 Provides-Extra: canine-extraction
 Requires-Dist: apsw<4,>=3.54; extra == "canine-extraction"
-Requires-Dist: pyahocorasick<3,>=2.3; extra == "canine-extraction"
-Provides-Extra: viral
-Provides-Extra: data
-Requires-Dist: datacache<2,>=1.29.3; extra == "data"
-Provides-Extra: columnar
-Requires-Dist: pyarrow>=14; extra == "columnar"
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Requires-Dist: twine; extra == "dev"
-Requires-Dist: openpyxl>=3.1; extra == "dev"
-Requires-Dist: pyensembl>=2.27.2; extra == "dev"
-Requires-Dist: datacache<2,>=1.29.3; extra == "dev"
 Requires-Dist: gb-io<0.5,>=0.4; extra == "dev"
 Requires-Dist: apsw<4,>=3.54; extra == "dev"
-Requires-Dist: pyahocorasick<3,>=2.3; extra == "dev"
+Requires-Dist: biopython<2,>=1.88; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: mkdocs<2,>=1.6; extra == "docs"
 Requires-Dist: mkdocs-material<10,>=9.5; extra == "docs"
@@ -56,12 +48,19 @@ evidence.
 Use Python 3.11 or later. Install orfdata and one PyEnsembl annotation:
 
 ```sh
-python -m pip install 'orfdata[pyensembl,build-data]'
+python -m pip install 'orfdata'
 pyensembl install --release 115 --species human
 # For the ncORF evidence presets and "all":
 orfdata setup --species human --catalogs all
 ```
 
+The normal installation includes PyEnsembl, spreadsheet source readers, PyArrow
+exports and Biotite alignment support. Reference and measurement data are still
+downloaded explicitly and checked against their pinned checksums. The
+`canine-extraction` extra adds APSW only for extracting the original vendor
+database through its custom VFS; released dataset queries and rebuilds from
+normalized sources do not need it.
+
 List every bundled, downloadable or buildable resource and what is installed:
 
 ```sh
@@ -143,7 +142,7 @@ immunopeptidomics: peptides eluted from HLA molecules.
 | Dog | none: no public dog Ribo-seq or ncORF MS exists | |
 
 Human's bundled catalogue needs no setup. For the others, `pip install
-"orfdata[data,build-data]"`, then `orfdata setup --species mouse` (or
+"orfdata"`, then `orfdata setup --species mouse` (or
 `zebrafish`, `worm`, `yeast`, or `human --catalogs all`) builds the catalogues
 from their sources' own files ([details](https://openvax.github.io/orfdata/catalogs/)).
 After `orfdata chains download` (add
@@ -216,11 +215,10 @@ Promoting further source records into the curated
 ## Measurement datasets
 
 RNA, ribosome and protein measurements are separate, downloadable datasets with
-the same species-scoped API. Install the `data` extra, then download and query
-one:
+the same species-scoped API. Download and query one explicitly:
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets list
 orfdata datasets download ingolia-yeast-rna-ribo
 ```

{orfdata-0.40.0 → orfdata-0.41.0}/README.md

@@ -16,12 +16,19 @@ evidence.
 Use Python 3.11 or later. Install orfdata and one PyEnsembl annotation:
 
 ```sh
-python -m pip install 'orfdata[pyensembl,build-data]'
+python -m pip install 'orfdata'
 pyensembl install --release 115 --species human
 # For the ncORF evidence presets and "all":
 orfdata setup --species human --catalogs all
 ```
 
+The normal installation includes PyEnsembl, spreadsheet source readers, PyArrow
+exports and Biotite alignment support. Reference and measurement data are still
+downloaded explicitly and checked against their pinned checksums. The
+`canine-extraction` extra adds APSW only for extracting the original vendor
+database through its custom VFS; released dataset queries and rebuilds from
+normalized sources do not need it.
+
 List every bundled, downloadable or buildable resource and what is installed:
 
 ```sh
@@ -103,7 +110,7 @@ immunopeptidomics: peptides eluted from HLA molecules.
 | Dog | none: no public dog Ribo-seq or ncORF MS exists | |
 
 Human's bundled catalogue needs no setup. For the others, `pip install
-"orfdata[data,build-data]"`, then `orfdata setup --species mouse` (or
+"orfdata"`, then `orfdata setup --species mouse` (or
 `zebrafish`, `worm`, `yeast`, or `human --catalogs all`) builds the catalogues
 from their sources' own files ([details](https://openvax.github.io/orfdata/catalogs/)).
 After `orfdata chains download` (add
@@ -176,11 +183,10 @@ Promoting further source records into the curated
 ## Measurement datasets
 
 RNA, ribosome and protein measurements are separate, downloadable datasets with
-the same species-scoped API. Install the `data` extra, then download and query
-one:
+the same species-scoped API. Download and query one explicitly:
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets list
 orfdata datasets download ingolia-yeast-rna-ribo
 ```

{orfdata-0.40.0 → orfdata-0.41.0}/docs/catalogs.md

@@ -77,7 +77,7 @@ existing standalone local-file workflow.
 ## Mouse
 
 ```sh
-pip install "orfdata[data,build-data]"
+pip install "orfdata"
 orfdata setup --species mouse --accept-terms   # Three catalogues and the chains; about 130 MB of sources
 ```
 
@@ -116,8 +116,7 @@ ATG, CTG, GTG or TTG. Its types are uORF (8,294), lncORF (3,576), uoORF
 (1,950), iORF (1,749), dORF (741) and doORF (174).
 
 - **Sources.** The authors' BED and protein FASTA (MIT, pinned commit), the
-  paper's Table S3 (CC BY 4.0) and Ensembl 107's GTF; about 40 MB. Building
-  needs `orfdata[build-data]` for the spreadsheet.
+  paper's Table S3 (CC BY 4.0) and Ensembl 107's GTF; about 40 MB.
 - **Coding paths.** The BED garbles multi-exon block sizes, so each ORF's
   path comes from its representative transcript and transcript coordinates
   in Ensembl 107, checked against its genomic start, stop, BED span and
@@ -163,8 +162,7 @@ floor, remains available explicitly as `--version 1`.
   51,881 place on Ensembl 115.
 - **Sources.** Supplementary Data 3 (CC BY 4.0) and Ensembl 107's GTF, cDNA
   and ncRNA FASTAs; about 115 MB, of which the 32 MB GTF is the one Chang et
-  al.'s catalogue uses, so `orfdata setup` downloads it once. Building needs
-  `orfdata[build-data]`.
+  al.'s catalogue uses, so `orfdata setup` downloads it once.
 - **Evidence.** Presence in the source's set is aggregate Ribo-seq support:
   `RiboSeq()` selects every ORF, `RiboSeq(min_studies=2)` none.
 - **Length policy.** `catalog.query(min_protein_length=5)` and
@@ -430,7 +428,7 @@ silently dropped.
 
 PyEnsembl's `EnsemblRelease` has no T2T-CHM13 annotation, so orfdata pins
 Ensembl's rapid-release one (2022_07) and installs it on request, checking each
-file's size and SHA-256 (it needs `orfdata[pyensembl]`). The T2T Consortium's
+file's size and SHA-256. The T2T Consortium's
 GRCh38-to-CHM13 chain is public domain (CC0):
 
 ```sh
@@ -481,8 +479,7 @@ orfdata lift --species human --to GRCh37 --output orfs-grch37.json.gz
 error. `--catalog FILE` lifts a local catalogue instead, and `--chain FILE` uses
 your own chain file instead of a downloaded pin. Pass the result back with
 `--nc-orf-sources` for `orfdata proteome`; JSON and TSV exports include
-each record's original and the chain. Downloading chains needs the
-`orfdata[data]` extra, which adds DataCache. In Python:
+each record's original and the chain. In Python:
 
 ```python
 from orfdata import download_chain, lift_catalog, load_catalog, load_chain

{orfdata-0.40.0 → orfdata-0.41.0}/docs/copy-yeast.md

@@ -7,7 +7,7 @@ grown in glucose-limited chemostats. The strain is EUROSCARF Y11335 BY4742,
 with the reported genotype retained on each sample.
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets info copy-yeast-abundance
 orfdata datasets download copy-yeast-abundance
 orfdata datasets pairs copy-yeast-abundance --basis condition_aggregate
@@ -101,7 +101,7 @@ between species, and different cultures/calibrations remain different experiment
 See [pairing and orthology](pairing.md).
 
 To rebuild the release from the pinned public workbook, standards, metadata and
-four RNA files, install `orfdata[data,build-data]` and run
+four RNA files, install `orfdata` and run
 `orfdata datasets build copy-yeast-abundance`. Python uses
 `DatasetRegistry().build("copy-yeast-abundance")`. Local verified inputs can be
 supplied with repeated `--source-path ASSET=PATH` or `source_paths={...}`.

{orfdata-0.40.0 → orfdata-0.41.0}/docs/human-tissue.md

@@ -17,7 +17,7 @@ yeast data.
 The download is approximately 397 MB and installs to a 3.86 GB SQLite database.
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets download wang-human-tissue-abundance --version 2026-10-12.1
 ```
 

{orfdata-0.40.0 → orfdata-0.41.0}/docs/index.md

@@ -12,7 +12,7 @@ is a recorded host of the virus.
 Use Python 3.11 or later. Install orfdata and one PyEnsembl annotation:
 
 ```sh
-python -m pip install 'orfdata[pyensembl,build-data]'
+python -m pip install 'orfdata'
 pyensembl install --release 115 --species human
 orfdata setup --species human --catalogs all  # For ncORF presets and "all"
 ```

{orfdata-0.40.0 → orfdata-0.41.0}/docs/ingolia-yeast.md

@@ -6,7 +6,7 @@ measurements from [Ingolia et al. (2009)](https://doi.org/10.1126/science.116897
 It uses the same dataset API as human, mouse and dog.
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets info ingolia-yeast-rna-ribo
 orfdata datasets download ingolia-yeast-rna-ribo
 ```
@@ -56,7 +56,7 @@ libraries and creates no assay pairs or translation-efficiency ratios. It also
 does not pair these cultures with the separate [CoPY protein study](copy-yeast.md).
 [Issue #11](https://github.com/openvax/orfdata/issues/11) tracks these source gaps.
 
-To rebuild, install `orfdata[data,build-data]` and run
+To rebuild, install `orfdata` and run
 `orfdata datasets build ingolia-yeast-rna-ribo`, or
 `DatasetRegistry().build("ingolia-yeast-rna-ribo")`. All 17 source inputs have
 pinned URLs, sizes and checksums. Verified local inputs can be supplied through

{orfdata-0.40.0 → orfdata-0.41.0}/docs/measurements.md

@@ -23,7 +23,7 @@ Its pooled PSM counts describe spectra, not sample-level protein abundance.
 
 ## Discover, download and query
 
-Install `orfdata[data]` to manage datasets. Creating a registry and listing
+Install `orfdata` to manage datasets. Creating a registry and listing
 releases reads metadata only:
 
 ```python
@@ -252,7 +252,7 @@ composite foreign keys, so human, mouse, dog, yeast and arbitrary other taxa use
 the same schema. [Compact storage and compatibility](storage.md) describes new
 SQLite v4 writes, legacy readers and actual-source size/query benchmarks.
 
-The core API needs neither pandas nor PyArrow. The optional `orfdata[columnar]`
-extra enables `dataset.export_parquet(path)`. Its query columns accompany the
+The normal installation includes pandas and PyArrow. Use
+`dataset.export_parquet(path)` to export query columns alongside the
 full measurement JSON, preserving exact values and provenance even when a
 floating-point analysis column cannot represent an integer exactly.

{orfdata-0.40.0 → orfdata-0.41.0}/docs/pfizer-protein.md

@@ -21,7 +21,7 @@ copies per cell. These are pooled tissue samples; rodent condition labels also
 include sex. Channels and technical runs do not count as independent donors.
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets list --species dog
 orfdata datasets download pfizer-atlas-dog-protein
 orfdata datasets query pfizer-atlas-dog-protein --quantity protein_abundance --unit iBAQ --scale linear

{orfdata-0.40.0 → orfdata-0.41.0}/docs/pfizer-rna.md

@@ -19,7 +19,7 @@ Zeros stay measured zeros: 4,218,202 dog observations and 18,019,555 mouse
 observations. Every value retains the native numeric text and source line.
 
 ```sh
-pip install 'orfdata[data]'
+pip install 'orfdata'
 orfdata datasets download pfizer-atlas-dog-rna --version 2026-10-12.1
 orfdata datasets query pfizer-atlas-dog-rna --sample 1 --unit counts
 ```
@@ -74,7 +74,7 @@ and remain candidates for separate releases through the same importer.
 
 `registry.build(name, source_paths=...)` or `orfdata datasets build NAME` rebuilds
 from pinned counts, GEO metadata, factual Table S5 sample records and the
-historical GTF; workbook rebuilding needs `orfdata[build-data]`. Python returns
+historical GTF. Python returns
 a `QuantitativeDataset` ready to query. Reopen it offline with
 `registry.open_build(name)` or inspect it with `registry.inspect_build(name)`.
 The CLI selects that source build explicitly with `orfdata datasets query NAME

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/catalog.py

@@ -1040,10 +1040,7 @@ def load_catalog(path=None, *, species=None, genome_build=None, registry=None, e
     root = getattr(registry, "_cache_root", None)
     needs = [_install_hint(c) for c, _ in plan if c.registry is not None and _installed(c) in (None, "damaged")]
     chains = list(dict.fromkeys(c for _, route in plan for c in route))
-    try:
-        missing = [c for c in chains if not chain_downloaded(c, cache_root=root)]
-    except ImportError:  # Without DataCache no chain can have been downloaded.
-        missing = chains
+    missing = [c for c in chains if not chain_downloaded(c, cache_root=root)]
     cli_root = "" if root is None else f" --cache-root {root}"
     if missing:
         accept = " --accept-terms" if any(c.restricted for c in missing) else ""
@@ -1052,17 +1049,10 @@ def load_catalog(path=None, *, species=None, genome_build=None, registry=None, e
                      f"download_chains(species={species!r}{', accept_terms=True' if accept else ''}"
                      f"{'' if root is None else f', cache_root={str(root)!r}'})")
     if needs:
-        try:
-            from .datasets import _datacache
-
-            _datacache()
-            step = ""
-        except ImportError:
-            step = "orfdata[data] installed, then "
         accept = " --accept-terms" if any(c.restricted for c in missing) else ""
         chosen = ("" if catalogs is None else " --catalogs " + (
             catalogs if isinstance(catalogs, str) else ",".join(catalogs)))
-        raise ValueError(f"{species} {genome_build} ORFs need {step}" + "; and ".join(needs)
+        raise ValueError(f"{species} {genome_build} ORFs need " + "; and ".join(needs)
                          + f". Or install everything at once with 'orfdata setup --species {species}{chosen}{accept}"
                          f"{cli_root}'")
     # Lifting and merging take seconds; one process reuses the result for exactly the same inputs.
@@ -1235,16 +1225,13 @@ def _releases(found):
 def _installed(choice):
     """How a registered release is installed: "downloaded", "built", "damaged" or None. Offline, unhashed."""
     registry, name, version = choice.registry, choice.name, choice.version
-    try:
-        damaged = False
-        if registry.published(name, version):
-            status = registry.inspect(name, version, verify_files=False).status
-            if status == "available":
-                return "downloaded"
-            damaged = status != "missing"
-        status = registry.inspect_build(name, version, verify_files=False).status
-    except ImportError:  # Without DataCache nothing can have been downloaded or built.
-        return None
+    damaged = False
+    if registry.published(name, version):
+        status = registry.inspect(name, version, verify_files=False).status
+        if status == "available":
+            return "downloaded"
+        damaged = status != "missing"
+    status = registry.inspect_build(name, version, verify_files=False).status
     if status == "available":
         return "built"
     return "damaged" if damaged or status != "missing" else None
@@ -1260,12 +1247,6 @@ def _open_registered(choice, expected_sha256):
         how = (f"{verb} it{when} with CatalogRegistry().{verb}({name!r}, {version!r}"
                f"{', force=True' if installed else ''}) or 'orfdata catalogs {verb} {name} --version {version}"
                f"{' --force' if installed else ''}'")
-        try:
-            from .datasets import _datacache
-
-            _datacache()
-        except ImportError:
-            how = "install orfdata[data], then " + how
         state = "damaged" if installed else "not installed"
         raise ValueError(f"The {name} {version} ORF catalogue is {state}; {how}")
     if installed == "built":
@@ -1334,10 +1315,7 @@ def catalog_status(*, registry=None):
         return plans[species, build, catalogs]
 
     def downloaded(chain):
-        try:
-            return chain_downloaded(chain, cache_root=root)
-        except ImportError:  # Without DataCache nothing can be downloaded.
-            return False
+        return chain_downloaded(chain, cache_root=root)
 
     rows = []
     for c in choices:

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/data/viral/NOTICE.md

@@ -137,7 +137,7 @@ 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:
+Rebuild with `orfdata` installed:
 
 ```sh
 python tools/build_hpv16_cds.py tests/data/viral/NC_001526.4.gb.gz \

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/dataset.py

@@ -722,12 +722,10 @@ class QuantitativeDataset:
         return result
 
     def export_parquet(self, path, **query):
-        """Export query results in bounded batches; requires orfdata[columnar]."""
-        try:
-            import pyarrow as pa
-            import pyarrow.parquet as pq
-        except ImportError as exc:
-            raise ImportError("Install orfdata[columnar] to export Parquet") from exc
+        """Export query results to Parquet in bounded batches."""
+        import pyarrow as pa
+        import pyarrow.parquet as pq
+
         schema = pa.schema([(name, pa.string()) for name in
                             ("dataset_id", "version", "reference_key", "measurement_id",
                              "sample_id", "assay_id", "target_kind", "target_namespace",

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/datasets.py

@@ -13,10 +13,8 @@ from .reference import species_taxon
 
 
 def _datacache():
-    try:
-        import datacache
-    except ImportError as exc:
-        raise ImportError("Install orfdata[data] (OpenVax DataCache) to download, build or cache data files") from exc
+    import datacache
+
     return datacache
 
 

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/genomes.py

@@ -73,7 +73,6 @@ def install_genome(name, *, force=False, source_paths=None, cache_root=None):
     Returns the opened genome.
     """
     genome = _pinned(name)
-    _require_pyensembl()  # Before downloading anything it would be needed to open.
     paths = None
     if source_paths:
         unknown = set(source_paths) - set(_ROLES)
@@ -92,7 +91,6 @@ def _install_command(name, cache_root, force=False):
 def load_genome(name, *, cache_root=None):
     """The installed pinned annotation as a PyEnsembl genome, offline; indexed on first use."""
     genome = _pinned(name)
-    _require_pyensembl()
     status = _registry(genome, cache_root).inspect(genome.name, "1", verify_files=False).status
     root = "" if cache_root is None else f", cache_root={str(cache_root)!r}"
     if status == "missing":
@@ -104,13 +102,6 @@ def load_genome(name, *, cache_root=None):
     return _open(genome, cache_root)
 
 
-def _require_pyensembl():
-    try:
-        import pyensembl  # noqa: F401
-    except ImportError as error:
-        raise ImportError("Pinned genomes are PyEnsembl genomes: pip install 'orfdata[pyensembl]'") from error
-
-
 def _open(genome, cache_root, *, rebuild=False):
     import pickle
     import sqlite3

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/install.py

@@ -128,8 +128,6 @@ def _install_collections(names, species, *, force, cache_root, timeout, failed):
                                timeout=timeout)
             installed[name] = {"missing": "downloaded",
                                "available": "reinstalled"}.get(state, "repaired")
-        except ImportError as error:  # An optional dependency is a skip, as restricted terms are.
-            installed[name] = f"skipped: {error}"
         except Exception as error:  # Reported with the rest, after everything else is tried.
             installed[name] = f"failed: {error}"
             failed.append((name, str(error)))

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/liftover_cli.py

@@ -87,10 +87,7 @@ def chains(argv=None, prog=None):
         if args.command == "list":
             output = []
             for chain in pinned_chains(species=args.species):
-                try:
-                    downloaded = chain_downloaded(chain, cache_root=args.cache_root)
-                except ImportError:
-                    downloaded = False
+                downloaded = chain_downloaded(chain, cache_root=args.cache_root)
                 output.append(dict(asdict(chain), downloaded=downloaded))
         elif args.source_build is None:
             if args.source_path:

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/proteome.py

@@ -2341,10 +2341,8 @@ def _cached_snapshot(key, make, cache_root):
 
 
 def _pyensembl_version():
-    try:
-        from pyensembl import __version__
-    except ImportError:
-        return None
+    from pyensembl import __version__
+
     return __version__
 
 

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/proteome_cli.py

@@ -10,10 +10,7 @@ from .proteome import Proteome
 
 
 def _ensembl_genome(release, species):
-    try:
-        from pyensembl import EnsemblRelease
-    except ImportError as error:
-        raise ImportError("Proteomes are built from PyEnsembl genomes: pip install 'orfdata[pyensembl]'") from error
+    from pyensembl import EnsemblRelease
 
     return EnsemblRelease(release, species=species)
 

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/copy.py

@@ -43,10 +43,7 @@ def _quantity(value):
 
 
 def _workbook(path, expected_counts):
-    try:
-        from openpyxl import load_workbook
-    except ImportError as exc:
-        raise ImportError("Install orfdata[build-data] to rebuild the CoPY workbook") from exc
+    from openpyxl import load_workbook
     workbook = load_workbook(path, read_only=True, data_only=True)
     tables = {}
     try:

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/ncorf_mammals.py

@@ -47,10 +47,7 @@ def _fasta(path):
 
 
 def _table(path, sheet, species):
-    try:
-        from openpyxl import load_workbook
-    except ImportError as error:
-        raise ImportError("Install orfdata[build-data] to build this catalogue from its spreadsheet") from error
+    from openpyxl import load_workbook
 
     with open(path, "rb") as handle:  # Cached files have no extension for openpyxl to go by.
         workbook = load_workbook(handle, read_only=True)

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/pfizer_attribution.py

@@ -3,7 +3,7 @@
 Reported source links and sequence-compatible candidates are independent facts.
 Neither converts a shared peptide or protein group into a uniquely measured
 protein. Decoy records retain their partition and are not biological assignments.
-Only the explicit builder uses the optional sequence-matching dependency.
+Only the explicit builder runs sequence matching; downloaded queries use its retained results.
 """
 
 import hashlib

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/pfizer_rna.py

@@ -68,10 +68,7 @@ def _geo_samples(inputs, assets):
 
 
 def _sample_table(path):
-    try:
-        from openpyxl import load_workbook
-    except ImportError as exc:
-        raise ImportError("Install orfdata[build-data] to read the atlas sample workbook") from exc
+    from openpyxl import load_workbook
     book = load_workbook(path, read_only=True, data_only=True)
     records = {}
     try:

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/pfizer_vendor.py

@@ -144,10 +144,8 @@ def peptide_candidates(peptides, search_reference, *, max_residues=250000, equat
             sequences.add(peptide)
     if not sequences:
         return
-    try:
-        import ahocorasick
-    except ImportError:
-        raise ImportError("Peptide extraction requires orfdata[canine-extraction]") from None
+    import ahocorasick
+
     normalized = {}
     for peptide in sorted(sequences):
         key = peptide.replace("I", "L") if equate_il else peptide

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/riborf.py

@@ -53,10 +53,7 @@ STOPS = {"TAA", "TAG", "TGA"}
 
 
 def _rows(path, sheet):
-    try:
-        from openpyxl import load_workbook
-    except ImportError as error:
-        raise ImportError("Install orfdata[build-data] to build this catalogue from its spreadsheet") from error
+    from openpyxl import load_workbook
 
     with open(path, "rb") as handle:  # Cached files have no extension for openpyxl to go by.
         workbook = load_workbook(handle, read_only=True)

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/sources/wang.py

@@ -41,10 +41,7 @@ def search_references(manifest):
 
 
 def _sheet(path, member, sheet):
-    try:
-        from openpyxl import load_workbook
-    except ImportError as exc:
-        raise ImportError("Install orfdata[build-data] to read healthy-tissue workbooks") from exc
+    from openpyxl import load_workbook
     with zipfile.ZipFile(path) as archive, archive.open(member) as stream:
         book = load_workbook(stream, read_only=True, data_only=True)
         try:

orfdata-0.41.0/orfdata/version.py

@@ -0,0 +1 @@
+__version__ = "0.41.0"

{orfdata-0.40.0 → orfdata-0.41.0}/orfdata/viral_panel.py

@@ -1189,12 +1189,8 @@ def viral_genome(
     """
     if not isinstance(reference_set, ViralReferenceFiles):
         raise TypeError("viral_genome needs ViralReferenceFiles")
-    try:
-        from pyensembl import Genome
-    except ImportError as error:
-        raise ImportError(
-            "Opening viral references as a genome needs PyEnsembl: pip install 'orfdata[pyensembl]'"
-        ) from error
+    from pyensembl import Genome
+
     from .datasets import get_data_dir
 
     collection = viral_collection(reference_set.collection)