apb2 0.1.0__tar.gz

apb2-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Witold Wolski
+
+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.

apb2-0.1.0/PKG-INFO

@@ -0,0 +1,185 @@
+Metadata-Version: 2.4
+Name: apb2
+Version: 0.1.0
+Summary: Convert proteomics software output to AnnData (rules-driven parser, second generation)
+Keywords: proteomics,mass spectrometry,anndata,mudata,quantification
+Author: Witold Wolski
+Author-email: Witold Wolski <wew@fgcz.ethz.ch>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Typing :: Typed
+Requires-Dist: anndata>=0.11
+Requires-Dist: cyclopts>=3
+Requires-Dist: duckdb>=1.4,<2
+Requires-Dist: loguru>=0.7
+Requires-Dist: mudata>=0.4,<1
+Requires-Dist: numpy>=2
+Requires-Dist: packaging>=24
+Requires-Dist: pandas>=2.2
+Requires-Dist: polars>=1.43,<2
+Requires-Dist: fastexcel>=0.21,<1
+Requires-Dist: python-calamine>=0.5,<1
+Requires-Dist: pydantic>=2.10
+Requires-Dist: pyarrow>=15
+Requires-Dist: pyyaml>=6
+Requires-Dist: scipy>=1.15,<2
+Requires-Python: >=3.13
+Project-URL: Documentation, https://anndata-omics-bridge.github.io/apb2/
+Project-URL: Repository, https://github.com/anndata-omics-bridge/apb2
+Description-Content-Type: text/markdown
+
+# apb2
+
+APB2 is a [rules-driven framework](https://anndata-omics-bridge.github.io/apb2/rule-based/) for converting outputs from proteomics
+software into AnnData or MuData. It supports ion, peptidoform, peptide, protein, and fragment
+quantification levels and can also store the parsed data in Parquet or DuckDB.
+
+“Rules-driven” means that declarative rule documents describe each vendor table: which columns
+contain identifiers, measurements, and metadata, how those columns should be reshaped, and which
+constraints the result must satisfy. One shared parser applies those rules, so a new or revised
+input format can usually be supported by adding or updating a rule instead of writing a dedicated
+reader.
+
+Read the rendered [APB2 documentation](https://anndata-omics-bridge.github.io/apb2/) or its
+[source index](https://github.com/anndata-omics-bridge/apb2/blob/main/docs/index.md). The [supported-software matrix](https://anndata-omics-bridge.github.io/apb2/supported_software/) lists
+every packaged software version, quantification level, vendor input type, table shape, and
+parameter parser.
+
+Choose the documentation for your interface:
+
+- [CLI reference](https://anndata-omics-bridge.github.io/apb2/cli/) and [command-line guides](https://anndata-omics-bridge.github.io/apb2/conversion/)
+- [Python API reference](https://anndata-omics-bridge.github.io/apb2/api/)
+
+## Installation
+
+APB2 requires Python 3.13 or later.
+
+```bash
+pip install apb2
+```
+
+To install only the `apb2` command, use `uv tool install apb2`.
+
+## Motivation and origin
+
+APB2 is a refactoring and performance improvement of the now-discontinued [AnnData Proteomics Bridge (APB v1)](https://github.com/anndata-omics-bridge/anndata-proteomics-bridge).
+
+APB2 is based on the work of [ProteoBench](https://github.com/proteobench/proteobench): it ports ProteoBench's parsing infrastructure — search-parameter parsing, vendor file-format parsing, modification parsing — into one rules-driven converter. See the ProteoBench preprint: [ProteoBench: the community-curated platform for comparing proteomics data analysis workflows](https://www.biorxiv.org/content/10.64898/2025.12.09.692895v2) (bioRxiv, 2025, doi:10.64898/2025.12.09.692895).
+
+Packaged conversion rules include AlphaDIA, AlphaPept, DIA-NN, FragPipe, i2MassChroQ, MaxQuant, MSAngel, PEAKS, ProteoBench Custom, ProlineStudio, quantms, Sage, Spectronaut, and WOMBAT; the complete version and input-format matrix is in [supported software](https://anndata-omics-bridge.github.io/apb2/supported_software/).
+
+The work that became APB2 was discussed and started during the Copenhagen ProteoBench Hackathon,
+13–17 April 2026, as one of the efforts to improve the backend of the
+[ProteoBench platform](https://proteobench.cubimed.rub.de/). The hackathon included the public
+[EuBIC-MS Seminar 2026 on 15 April](https://eubic-ms.org/events/latest-developments-and-tools-for-data-analysis/).
+
+APB2 was also motivated by the vendor-specific readers maintained behind
+[`prolfquapp::preprocess_software()`](https://github.com/prolfqua/prolfquapp/blob/master/R/preprocess_software.R#L137)
+and in
+[`prolfquappPTMreaders`](https://github.com/prolfqua/prolfquappPTMreaders). We plan to move their
+remaining input variants and PTM/site-level formats into APB2 so one rules-driven parser can serve
+both prolfquapp and ProteoBench, and hopefully other tools analysing quantification data.
+
+## Command-line interface
+
+### Convert
+
+Use a packaged rule selected from the vendor parameter file and source header. `DATA` may be one vendor table or a vendor-result directory:
+
+`--software` selects the parameter-file grammar and restricts result recognition to that vendor and its declared quantification software. For FragPipe parameters with DIA-NN output, pass `--software fragpipe`. Omit the hint for recognition across parameter-bearing rules; mismatches and ambiguity are errors, not a fallback to unrelated rules.
+
+ProteoBench Custom uploads have no parameter file: `apb2 convert custom.txt ion --software pb_custom --output results/custom`.
+
+```bash
+apb2 convert DATA LEVEL --params PARAMETER_FILE [--software VENDOR] [--output BASENAME]
+```
+
+Omit `LEVEL` to convert every compatible level into one APB2 result:
+
+```bash
+apb2 convert DATA --params PARAMETER_FILE [--software VENDOR] [--format FORMAT] [--output BASENAME]
+```
+
+Use an explicit schema-0.8 rule document, with optional search-parameter evidence:
+
+```bash
+apb2 convert DATA LEVEL --rule-config RULES_JSON [--params PARAMETER_FILE] \
+  [--software VENDOR] [--output BASENAME]
+```
+
+`LEVEL` is one of `ion`, `peptidoform`, `peptide`, `protein`, or `fragment`. MaxQuant accepts any nonempty subset of evidence, modification-specific peptide, peptide and protein-group exports. Evidence stays separate from the higher-level join; an omitted level converts every available level. `--format` selects `hdf5`, `parquet`, or `duckdb`. HDF5 uses `.h5ad` with an explicit level and `.h5mu` otherwise. Complete one-to-one observation aliases are aligned; fractionated or unmapped resolutions produce separate outputs such as `result.raw_file.h5mu` and `result.experiment.h5mu`. See [output naming](https://anndata-omics-bridge.github.io/apb2/conversion/#output-naming). `--strict` promotes layer-contract warnings to errors. `--timings-output PATH` optionally writes a separate versioned JSON file containing internal compile, read, parse and write durations plus per-level read/parse durations; it does not enter the APB result or its scientific representation. The command performs conversion only; FASTA annotation and protein inference are outside Parser V2.
+
+### Reformat a parsed result
+
+Change only the persisted format; no vendor parsing or annotation runs:
+
+```bash
+apb2 reformat SOURCE TARGET
+```
+
+The suffix selects h5ad, h5mu, an APB2 Parquet directory dataset, or DuckDB.
+
+### Annotate samples
+
+Attach a generic prolfquapp-style CSV/TSV table to any APB2 result format:
+
+```bash
+apb2 annotate INPUT ANNOTATION OUTPUT
+```
+
+The default prolfquapp behavior retains unmatched quantitative observations and writes null
+annotation fields. `--unmatched error` requires complete coverage; `--unmatched drop` explicitly
+subsets every observation-aligned value. ProteoBench-specific module annotation and scoring live
+in the separate `apb-proteobench` package. See the
+[sample-annotation guide](https://anndata-omics-bridge.github.io/apb2/sample_annotation/).
+
+## Python API
+
+The file-to-file facades mirror the CLI operations. The compiler/parser APIs expose
+storage-neutral values for custom pipelines. Result formats also have explicit adapters:
+
+```python
+from pathlib import Path
+
+from apb2.api import read_parsed_levels, write_parsed_levels
+
+parsed = read_parsed_levels(Path("result.parquet"))
+write_parsed_levels(parsed, Path("result.duckdb"))
+```
+
+Parquet and DuckDB preserve Polars result values exactly; h5ad and h5mu apply the stored
+numeric/factor matrix projection. Every public result write also publishes an adjacent compact `.apb.json` scientific representation for inspection without loading the full result. See the [Python API reference](https://anndata-omics-bridge.github.io/apb2/api/) for vendor
+conversion, annotation, result values, and errors.
+
+## Architecture
+
+The CLI delegates conversion to Parser V2 and annotation to the independent annotation facade.
+The controlling designs and dependency boundaries are documented in
+[`docs/architecture_converter.md`](https://anndata-omics-bridge.github.io/apb2/architecture_converter/) and
+[`docs/architecture_annotation.md`](https://anndata-omics-bridge.github.io/apb2/architecture_annotation/).
+
+## Development
+
+```bash
+uv sync --group dev
+make check
+make docs
+.venv/bin/pre-commit install --hook-type pre-commit --hook-type pre-push
+```
+
+All Python commands run from the synchronized project `.venv`.
+`make docs-serve` serves the user documentation locally. GitHub Actions publishes the strict
+Zensical build to GitHub Pages from `main`.
+
+The rule JSON Schema is a packaged artifact. Developers regenerate it from the Parser V2 rule
+package rather than through a user-facing CLI command:
+
+```bash
+uv run python -c 'from apb2.parserV2.vendor_parse_rules.schema_artifact import write_artifact; write_artifact()'
+```

apb2-0.1.0/README.md

@@ -0,0 +1,149 @@
+# apb2
+
+APB2 is a [rules-driven framework](https://anndata-omics-bridge.github.io/apb2/rule-based/) for converting outputs from proteomics
+software into AnnData or MuData. It supports ion, peptidoform, peptide, protein, and fragment
+quantification levels and can also store the parsed data in Parquet or DuckDB.
+
+“Rules-driven” means that declarative rule documents describe each vendor table: which columns
+contain identifiers, measurements, and metadata, how those columns should be reshaped, and which
+constraints the result must satisfy. One shared parser applies those rules, so a new or revised
+input format can usually be supported by adding or updating a rule instead of writing a dedicated
+reader.
+
+Read the rendered [APB2 documentation](https://anndata-omics-bridge.github.io/apb2/) or its
+[source index](https://github.com/anndata-omics-bridge/apb2/blob/main/docs/index.md). The [supported-software matrix](https://anndata-omics-bridge.github.io/apb2/supported_software/) lists
+every packaged software version, quantification level, vendor input type, table shape, and
+parameter parser.
+
+Choose the documentation for your interface:
+
+- [CLI reference](https://anndata-omics-bridge.github.io/apb2/cli/) and [command-line guides](https://anndata-omics-bridge.github.io/apb2/conversion/)
+- [Python API reference](https://anndata-omics-bridge.github.io/apb2/api/)
+
+## Installation
+
+APB2 requires Python 3.13 or later.
+
+```bash
+pip install apb2
+```
+
+To install only the `apb2` command, use `uv tool install apb2`.
+
+## Motivation and origin
+
+APB2 is a refactoring and performance improvement of the now-discontinued [AnnData Proteomics Bridge (APB v1)](https://github.com/anndata-omics-bridge/anndata-proteomics-bridge).
+
+APB2 is based on the work of [ProteoBench](https://github.com/proteobench/proteobench): it ports ProteoBench's parsing infrastructure — search-parameter parsing, vendor file-format parsing, modification parsing — into one rules-driven converter. See the ProteoBench preprint: [ProteoBench: the community-curated platform for comparing proteomics data analysis workflows](https://www.biorxiv.org/content/10.64898/2025.12.09.692895v2) (bioRxiv, 2025, doi:10.64898/2025.12.09.692895).
+
+Packaged conversion rules include AlphaDIA, AlphaPept, DIA-NN, FragPipe, i2MassChroQ, MaxQuant, MSAngel, PEAKS, ProteoBench Custom, ProlineStudio, quantms, Sage, Spectronaut, and WOMBAT; the complete version and input-format matrix is in [supported software](https://anndata-omics-bridge.github.io/apb2/supported_software/).
+
+The work that became APB2 was discussed and started during the Copenhagen ProteoBench Hackathon,
+13–17 April 2026, as one of the efforts to improve the backend of the
+[ProteoBench platform](https://proteobench.cubimed.rub.de/). The hackathon included the public
+[EuBIC-MS Seminar 2026 on 15 April](https://eubic-ms.org/events/latest-developments-and-tools-for-data-analysis/).
+
+APB2 was also motivated by the vendor-specific readers maintained behind
+[`prolfquapp::preprocess_software()`](https://github.com/prolfqua/prolfquapp/blob/master/R/preprocess_software.R#L137)
+and in
+[`prolfquappPTMreaders`](https://github.com/prolfqua/prolfquappPTMreaders). We plan to move their
+remaining input variants and PTM/site-level formats into APB2 so one rules-driven parser can serve
+both prolfquapp and ProteoBench, and hopefully other tools analysing quantification data.
+
+## Command-line interface
+
+### Convert
+
+Use a packaged rule selected from the vendor parameter file and source header. `DATA` may be one vendor table or a vendor-result directory:
+
+`--software` selects the parameter-file grammar and restricts result recognition to that vendor and its declared quantification software. For FragPipe parameters with DIA-NN output, pass `--software fragpipe`. Omit the hint for recognition across parameter-bearing rules; mismatches and ambiguity are errors, not a fallback to unrelated rules.
+
+ProteoBench Custom uploads have no parameter file: `apb2 convert custom.txt ion --software pb_custom --output results/custom`.
+
+```bash
+apb2 convert DATA LEVEL --params PARAMETER_FILE [--software VENDOR] [--output BASENAME]
+```
+
+Omit `LEVEL` to convert every compatible level into one APB2 result:
+
+```bash
+apb2 convert DATA --params PARAMETER_FILE [--software VENDOR] [--format FORMAT] [--output BASENAME]
+```
+
+Use an explicit schema-0.8 rule document, with optional search-parameter evidence:
+
+```bash
+apb2 convert DATA LEVEL --rule-config RULES_JSON [--params PARAMETER_FILE] \
+  [--software VENDOR] [--output BASENAME]
+```
+
+`LEVEL` is one of `ion`, `peptidoform`, `peptide`, `protein`, or `fragment`. MaxQuant accepts any nonempty subset of evidence, modification-specific peptide, peptide and protein-group exports. Evidence stays separate from the higher-level join; an omitted level converts every available level. `--format` selects `hdf5`, `parquet`, or `duckdb`. HDF5 uses `.h5ad` with an explicit level and `.h5mu` otherwise. Complete one-to-one observation aliases are aligned; fractionated or unmapped resolutions produce separate outputs such as `result.raw_file.h5mu` and `result.experiment.h5mu`. See [output naming](https://anndata-omics-bridge.github.io/apb2/conversion/#output-naming). `--strict` promotes layer-contract warnings to errors. `--timings-output PATH` optionally writes a separate versioned JSON file containing internal compile, read, parse and write durations plus per-level read/parse durations; it does not enter the APB result or its scientific representation. The command performs conversion only; FASTA annotation and protein inference are outside Parser V2.
+
+### Reformat a parsed result
+
+Change only the persisted format; no vendor parsing or annotation runs:
+
+```bash
+apb2 reformat SOURCE TARGET
+```
+
+The suffix selects h5ad, h5mu, an APB2 Parquet directory dataset, or DuckDB.
+
+### Annotate samples
+
+Attach a generic prolfquapp-style CSV/TSV table to any APB2 result format:
+
+```bash
+apb2 annotate INPUT ANNOTATION OUTPUT
+```
+
+The default prolfquapp behavior retains unmatched quantitative observations and writes null
+annotation fields. `--unmatched error` requires complete coverage; `--unmatched drop` explicitly
+subsets every observation-aligned value. ProteoBench-specific module annotation and scoring live
+in the separate `apb-proteobench` package. See the
+[sample-annotation guide](https://anndata-omics-bridge.github.io/apb2/sample_annotation/).
+
+## Python API
+
+The file-to-file facades mirror the CLI operations. The compiler/parser APIs expose
+storage-neutral values for custom pipelines. Result formats also have explicit adapters:
+
+```python
+from pathlib import Path
+
+from apb2.api import read_parsed_levels, write_parsed_levels
+
+parsed = read_parsed_levels(Path("result.parquet"))
+write_parsed_levels(parsed, Path("result.duckdb"))
+```
+
+Parquet and DuckDB preserve Polars result values exactly; h5ad and h5mu apply the stored
+numeric/factor matrix projection. Every public result write also publishes an adjacent compact `.apb.json` scientific representation for inspection without loading the full result. See the [Python API reference](https://anndata-omics-bridge.github.io/apb2/api/) for vendor
+conversion, annotation, result values, and errors.
+
+## Architecture
+
+The CLI delegates conversion to Parser V2 and annotation to the independent annotation facade.
+The controlling designs and dependency boundaries are documented in
+[`docs/architecture_converter.md`](https://anndata-omics-bridge.github.io/apb2/architecture_converter/) and
+[`docs/architecture_annotation.md`](https://anndata-omics-bridge.github.io/apb2/architecture_annotation/).
+
+## Development
+
+```bash
+uv sync --group dev
+make check
+make docs
+.venv/bin/pre-commit install --hook-type pre-commit --hook-type pre-push
+```
+
+All Python commands run from the synchronized project `.venv`.
+`make docs-serve` serves the user documentation locally. GitHub Actions publishes the strict
+Zensical build to GitHub Pages from `main`.
+
+The rule JSON Schema is a packaged artifact. Developers regenerate it from the Parser V2 rule
+package rather than through a user-facing CLI command:
+
+```bash
+uv run python -c 'from apb2.parserV2.vendor_parse_rules.schema_artifact import write_artifact; write_artifact()'
+```

apb2-0.1.0/pyproject.toml

@@ -0,0 +1,157 @@
+[build-system]
+requires = ["uv_build>=0.9.26,<0.10.0"]
+build-backend = "uv_build"
+
+[project]
+name = "apb2"
+version = "0.1.0"
+description = "Convert proteomics software output to AnnData (rules-driven parser, second generation)"
+readme = "README.md"
+requires-python = ">=3.13"
+license = "MIT"
+license-files = ["LICENSE"]
+keywords = [
+    "proteomics",
+    "mass spectrometry",
+    "anndata",
+    "mudata",
+    "quantification",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Typing :: Typed",
+]
+dependencies = [
+    "anndata>=0.11",
+    "cyclopts>=3",
+    "duckdb>=1.4,<2",
+    "loguru>=0.7",
+    "mudata>=0.4,<1",
+    "numpy>=2",
+    "packaging>=24",
+    "pandas>=2.2",
+    "polars>=1.43,<2",
+    "fastexcel>=0.21,<1",
+    "python-calamine>=0.5,<1",
+    "pydantic>=2.10",
+    "pyarrow>=15",
+    "pyyaml>=6",
+    "scipy>=1.15,<2",
+]
+
+[[project.authors]]
+name = "Witold Wolski"
+email = "wew@fgcz.ethz.ch"
+
+[project.urls]
+Documentation = "https://anndata-omics-bridge.github.io/apb2/"
+Repository = "https://github.com/anndata-omics-bridge/apb2"
+
+[project.scripts]
+apb2 = "apb2.cli.app:main"
+
+[dependency-groups]
+dev = [
+    "build>=1.3,<2",
+    "deptry>=0.24,<1",
+    "grimp>=3,<4",
+    "import-linter>=2,<3",
+    "pandas-stubs>=3.0.5.260730",
+    "pre-commit>=4,<5",
+    "pyright>=1.1.400,<2",
+    "pytest>=9,<10",
+    "pytest-cov>=7,<8",
+    "ruff>=0.15,<1",
+    "twine>=6,<7",
+]
+docs = [
+    "pymdown-extensions>=11,<12",
+    "zensical==0.0.43",
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py313"
+src = [
+    "src",
+    "tests",
+]
+
+[tool.ruff.lint]
+select = [
+    "ANN",
+    "B",
+    "C4",
+    "C90",
+    "E4",
+    "E7",
+    "E9",
+    "F",
+    "I",
+    "PGH",
+    "PIE",
+    "RUF",
+    "SIM",
+    "UP",
+]
+
+[tool.ruff.lint.mccabe]
+max-complexity = 10
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.pyright]
+include = [
+    "src",
+    "tests",
+    "scripts",
+]
+venvPath = "."
+venv = ".venv"
+pythonVersion = "3.13"
+typeCheckingMode = "strict"
+reportImportCycles = "error"
+reportMissingTypeStubs = "none"
+reportUnnecessaryTypeIgnoreComment = "error"
+reportImplicitOverride = "error"
+enableTypeIgnoreComments = false
+reportUnknownMemberType = "none"
+reportUnknownVariableType = "none"
+reportUnknownArgumentType = "none"
+reportUnknownParameterType = "none"
+reportUnknownLambdaType = "none"
+
+[tool.pytest.ini_options]
+addopts = [
+    "--strict-config",
+    "--strict-markers",
+    "-ra",
+]
+testpaths = ["tests"]
+xfail_strict = true
+
+[tool.deptry]
+known_first_party = ["apb2"]
+exclude = [
+    "documentation",
+    "scripts",
+    "tests",
+    "venv",
+    "[.]venv",
+    "[.]direnv",
+    "[.]git",
+    "[.]claude",
+    "setup[.]py",
+]
+
+[tool.deptry.per_rule_ignores]
+DEP002 = [
+    "pyarrow",
+    "python-calamine",
+]

apb2-0.1.0/pyproject.toml.orig

@@ -0,0 +1,134 @@
+[build-system]
+requires = ["uv_build>=0.9.26,<0.10.0"]
+build-backend = "uv_build"
+
+[project]
+name = "apb2"
+version = "0.1.0"
+description = "Convert proteomics software output to AnnData (rules-driven parser, second generation)"
+readme = "README.md"
+requires-python = ">=3.13"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Witold Wolski", email = "wew@fgcz.ethz.ch" },
+]
+keywords = ["proteomics", "mass spectrometry", "anndata", "mudata", "quantification"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Typing :: Typed",
+]
+dependencies = [
+    "anndata>=0.11",
+    "cyclopts>=3",
+    "duckdb>=1.4,<2",
+    "loguru>=0.7",
+    "mudata>=0.4,<1",
+    "numpy>=2",
+    "packaging>=24",
+    "pandas>=2.2",
+    "polars>=1.43,<2",
+    "fastexcel>=0.21,<1",
+    "python-calamine>=0.5,<1",
+    "pydantic>=2.10",
+    "pyarrow>=15",
+    "pyyaml>=6",
+    "scipy>=1.15,<2",
+]
+
+[project.urls]
+Documentation = "https://anndata-omics-bridge.github.io/apb2/"
+Repository = "https://github.com/anndata-omics-bridge/apb2"
+
+[project.scripts]
+apb2 = "apb2.cli.app:main"
+
+[dependency-groups]
+dev = [
+    "build>=1.3,<2",
+    "deptry>=0.24,<1",
+    "grimp>=3,<4",
+    "import-linter>=2,<3",
+    "pandas-stubs>=3.0.5.260730",
+    "pre-commit>=4,<5",
+    "pyright>=1.1.400,<2",
+    "pytest>=9,<10",
+    "pytest-cov>=7,<8",
+    "ruff>=0.15,<1",
+    "twine>=6,<7",
+]
+docs = [
+    "pymdown-extensions>=11,<12",
+    "zensical==0.0.43",
+]
+[tool.ruff]
+line-length = 100
+target-version = "py313"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "ANN",
+    "B",
+    "C4",
+    "C90",
+    "E4",
+    "E7",
+    "E9",
+    "F",
+    "I",
+    "PGH",
+    "PIE",
+    "RUF",
+    "SIM",
+    "UP",
+]
+
+[tool.ruff.lint.mccabe]
+max-complexity = 10
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.pyright]
+include = ["src", "tests", "scripts"]
+venvPath = "."
+venv = ".venv"
+pythonVersion = "3.13"
+typeCheckingMode = "strict"
+reportImportCycles = "error"
+reportMissingTypeStubs = "none"
+reportUnnecessaryTypeIgnoreComment = "error"
+reportImplicitOverride = "error"
+enableTypeIgnoreComments = false
+# Third-party scientific libraries expose incomplete types even with their
+# canonical stub packages (same rationale and settings as apb). Keep strict
+# first-party checks while suppressing diagnostics whose only signal is a
+# propagated Unknown.
+reportUnknownMemberType = "none"
+reportUnknownVariableType = "none"
+reportUnknownArgumentType = "none"
+reportUnknownParameterType = "none"
+reportUnknownLambdaType = "none"
+
+[tool.pytest.ini_options]
+addopts = ["--strict-config", "--strict-markers", "-ra"]
+testpaths = ["tests"]
+xfail_strict = true
+
+[tool.deptry]
+known_first_party = ["apb2"]
+# documentation/ and scripts/ hold executable tooling, not importable package code; .claude/
+# holds agent worktrees, each a full checkout.
+exclude = ["documentation", "scripts", "tests", "venv", "[.]venv", "[.]direnv", "[.]git", "[.]claude", "setup[.]py"]
+
+[tool.deptry.per_rule_ignores]
+# DuckDB asks Polars for Arrow record batches when a DataFrame is registered. Polars imports
+# PyArrow dynamically at that boundary, so no direct APB2 import exists for Deptry to observe.
+# The parameter-workbook reader still loads python-calamine through Pandas' Excel engine.
+DEP002 = ["pyarrow", "python-calamine"]

apb2-0.1.0/src/apb2/__init__.py

@@ -0,0 +1 @@
+"""Rules-driven proteomics vendor-table conversion."""