ahcore 0.1.0__tar.gz

ahcore-0.1.0/.gitignore

@@ -0,0 +1,19 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.eggs/
+build/
+dist/
+
+# Tooling caches
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+
+# Environments
+.venv/
+venv/
+
+# OS / editor
+.DS_Store

ahcore-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

ahcore-0.1.0/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.5
+Name: ahcore
+Version: 0.1.0
+Summary: Core building blocks for whole-slide-image deep learning pipelines
+Project-URL: Homepage, https://github.com/NKI-AI/ahcore
+Project-URL: Repository, https://github.com/NKI-AI/ahcore
+Project-URL: Issues, https://github.com/NKI-AI/ahcore/issues
+Author-email: Jonas Teuwen <j.teuwen@nki.nl>, Joren Brunekreef <j.brunekreef@nki.nl>
+Maintainer-email: AI for Oncology <j.teuwen@nki.nl>
+License: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Healthcare Industry
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Requires-Python: >=3.11
+Requires-Dist: dlup>=0.9.4
+Requires-Dist: filelock>=3.12
+Requires-Dist: h5py>=3.12
+Requires-Dist: imageio>=2.37
+Requires-Dist: kornia>=0.8
+Requires-Dist: lightning>=2.6
+Requires-Dist: numcodecs>=0.13
+Requires-Dist: numpy>=2.0
+Requires-Dist: omegaconf>=2.3
+Requires-Dist: pandas>=2.0
+Requires-Dist: pillow>=10.0
+Requires-Dist: pydantic>=2.10
+Requires-Dist: rich>=13
+Requires-Dist: sqlalchemy>=2.0
+Requires-Dist: torch>=2.6
+Requires-Dist: tqdm>=4.66
+Requires-Dist: typing-extensions>=4.10
+Requires-Dist: zarr>=3.0
+Provides-Extra: dev
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest-mock; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Provides-Extra: logging
+Requires-Dist: mlflow>=3.4; extra == 'logging'
+Requires-Dist: tensorboard>=2.19; extra == 'logging'
+Provides-Extra: tracing
+Requires-Dist: huggingface-hub; extra == 'tracing'
+Requires-Dist: pyyaml; extra == 'tracing'
+Requires-Dist: timm; extra == 'tracing'
+Requires-Dist: transformers; extra == 'tracing'
+Description-Content-Type: text/markdown
+
+# ahcore
+
+`ahcore` is the AI for Oncology core toolkit for computational-pathology pipelines: the reusable building
+blocks that sit between whole-slide images and a training run. It is a pure-Python library, meant to be
+composed inside a larger pipeline rather than run on its own.
+
+This repository is automatically synced from the AI for Oncology monorepo.
+
+## What ahcore offers
+
+`ahcore` is a toolkit of composable building blocks for whole-slide-image deep learning, not an end-to-end
+application. A consumer pipeline assembles these pieces and owns the experiment logic. It decides how data
+is split, whether to cross-validate, and how runs are orchestrated. `ahcore` provides the parts.
+
+- **A data catalog.** A SQLAlchemy-backed manifest of patients, slides, masks, labels, and named splits,
+  queried through a `DataManager`. `ahcore` _stores and serves_ splits (e.g. fit/validate/test membership,
+  or membership supplied in memory). How you _draw_ them is up to you.
+- **Views and adapters.** Lazy per-slide and per-tile accessors over the catalog, plus an adapter seam
+  (`view → AdapterBundle`) that turns them into named, model-ready tensors. Ships adapters for
+  foundation-model tile features, patient labels, bulk RNA expression, and image+mask pairs. Adapters are
+  the main extension point.
+- **Feature extraction and caching.** Run a packaged foundation-model encoder over a slide's tiles and
+  persist the per-slide features to HDF5, keyed deterministically. This is a distinct precompute step: at
+  training time the feature adapters read from that cache, they do not extract on the fly (doing so would
+  be too slow for a realistic training run).
+- **Datamodules and models.** PyTorch Lightning datamodules that assemble batches from adapters (single-
+  or multi-modal), plus model heads: attention-based MIL (ABMIL), mean-pool MIL (MeanMIL), encoders, a
+  concatenation fusion head, and segmentation wrappers.
+- **Task and training scaffolding.** A `Task` protocol (choose inputs and targets, compute loss and
+  metrics) and a thin `MultiModalLightningModule` that runs training/validation/test by delegating to the
+  task. You supply the concrete tasks.
+- **Slide-sized raster I/O.** Stream model outputs (segmentation masks, attention or probability maps)
+  tile-by-tile into a chunked Zarr store, then read arbitrary regions back like a slide, to stitch,
+  overlay, or export to a pyramidal TIFF.
+- **Transforms and augmentations.** Tile transforms (including polygon-to-mask) and feature-space
+  augmentations.
+
+`ahcore` ships no end-to-end command-line application; it is a library.
+
+## Installation
+
+```bash
+pip install ahcore
+```
+
+Requires Python ≥ 3.11. The training stack (PyTorch Lightning) is a core dependency. `ahcore` is a
+training-scaffolding library, not an optional add-on.
+
+## Development
+
+`ahcore` is developed in the AI for Oncology monorepo and synced to this repository. To work on it here,
+standalone:
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+Inside the monorepo it is built and tested with Bazel (`bazelisk test //aifo/ahcore/tests/...`).
+
+## License
+
+Apache 2.0 — see [LICENSE](LICENSE).

ahcore-0.1.0/README.md

@@ -0,0 +1,63 @@
+# ahcore
+
+`ahcore` is the AI for Oncology core toolkit for computational-pathology pipelines: the reusable building
+blocks that sit between whole-slide images and a training run. It is a pure-Python library, meant to be
+composed inside a larger pipeline rather than run on its own.
+
+This repository is automatically synced from the AI for Oncology monorepo.
+
+## What ahcore offers
+
+`ahcore` is a toolkit of composable building blocks for whole-slide-image deep learning, not an end-to-end
+application. A consumer pipeline assembles these pieces and owns the experiment logic. It decides how data
+is split, whether to cross-validate, and how runs are orchestrated. `ahcore` provides the parts.
+
+- **A data catalog.** A SQLAlchemy-backed manifest of patients, slides, masks, labels, and named splits,
+  queried through a `DataManager`. `ahcore` _stores and serves_ splits (e.g. fit/validate/test membership,
+  or membership supplied in memory). How you _draw_ them is up to you.
+- **Views and adapters.** Lazy per-slide and per-tile accessors over the catalog, plus an adapter seam
+  (`view → AdapterBundle`) that turns them into named, model-ready tensors. Ships adapters for
+  foundation-model tile features, patient labels, bulk RNA expression, and image+mask pairs. Adapters are
+  the main extension point.
+- **Feature extraction and caching.** Run a packaged foundation-model encoder over a slide's tiles and
+  persist the per-slide features to HDF5, keyed deterministically. This is a distinct precompute step: at
+  training time the feature adapters read from that cache, they do not extract on the fly (doing so would
+  be too slow for a realistic training run).
+- **Datamodules and models.** PyTorch Lightning datamodules that assemble batches from adapters (single-
+  or multi-modal), plus model heads: attention-based MIL (ABMIL), mean-pool MIL (MeanMIL), encoders, a
+  concatenation fusion head, and segmentation wrappers.
+- **Task and training scaffolding.** A `Task` protocol (choose inputs and targets, compute loss and
+  metrics) and a thin `MultiModalLightningModule` that runs training/validation/test by delegating to the
+  task. You supply the concrete tasks.
+- **Slide-sized raster I/O.** Stream model outputs (segmentation masks, attention or probability maps)
+  tile-by-tile into a chunked Zarr store, then read arbitrary regions back like a slide, to stitch,
+  overlay, or export to a pyramidal TIFF.
+- **Transforms and augmentations.** Tile transforms (including polygon-to-mask) and feature-space
+  augmentations.
+
+`ahcore` ships no end-to-end command-line application; it is a library.
+
+## Installation
+
+```bash
+pip install ahcore
+```
+
+Requires Python ≥ 3.11. The training stack (PyTorch Lightning) is a core dependency. `ahcore` is a
+training-scaffolding library, not an optional add-on.
+
+## Development
+
+`ahcore` is developed in the AI for Oncology monorepo and synced to this repository. To work on it here,
+standalone:
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+Inside the monorepo it is built and tested with Bazel (`bazelisk test //aifo/ahcore/tests/...`).
+
+## License
+
+Apache 2.0 — see [LICENSE](LICENSE).

ahcore-0.1.0/ahcore/__init__.py

@@ -0,0 +1,27 @@
+# Copyright 2025 Jonas Teuwen & Joren Brunekreef. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""ahcore: reusable building blocks for whole-slide-image deep learning pipelines.
+
+A manifest-backed data catalog, pluggable adapters, a foundation-model feature store, MIL / encoder /
+fusion and segmentation model heads, a Task-driven PyTorch-Lightning module, and Zarr tile readers /
+writers. Import the pieces from their subpackages (e.g. ``ahcore.models``, ``ahcore.data``,
+``ahcore.tasks``, ``ahcore.readers``).
+"""
+
+# Single source of truth for the version; pyproject.toml reads it via hatch's version hook.
+__version__ = "0.1.0"
+
+import ahcore.writers as writers
+
+__all__ = ["writers"]

ahcore-0.1.0/ahcore/augmentations/__init__.py

@@ -0,0 +1,26 @@
+# Copyright 2025 Joren Brunekreef. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from .adapter_augmentation import AdapterAugmentation
+from .interfaces import AdapterAugmentor
+from .tile_features import SelectRandomTiles, TileFeaturesAugmentation
+from .tile_mask_pair import HEDColorAugmentation, TileMaskPairAugmentation
+
+__all__ = [
+    "AdapterAugmentation",
+    "AdapterAugmentor",
+    "HEDColorAugmentation",
+    "SelectRandomTiles",
+    "TileFeaturesAugmentation",
+    "TileMaskPairAugmentation",
+]

ahcore-0.1.0/ahcore/augmentations/adapter_augmentation.py

@@ -0,0 +1,35 @@
+# Copyright 2025 Joren Brunekreef. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+import torch.nn as nn
+
+from ahcore.augmentations.interfaces import AdapterAugmentor
+from ahcore.data.interfaces import AdapterBundle
+
+
+class AdapterAugmentation(nn.Module):
+    """Composes an ordered list of :class:`AdapterAugmentor` modules into one bundle-to-bundle transform.
+
+    ``forward`` threads the ``AdapterBundle`` through each augmentor in turn and returns the result.
+    """
+
+    def __init__(self, augmentors: list[AdapterAugmentor]) -> None:
+        super().__init__()
+        self._augmentors = nn.ModuleList(augmentors)
+
+    def forward(self, bundle: AdapterBundle) -> AdapterBundle:
+        for augmentor in self._augmentors:
+            bundle = augmentor(bundle)
+        return bundle

ahcore-0.1.0/ahcore/augmentations/interfaces.py

@@ -0,0 +1,25 @@
+# Copyright 2025 Joren Brunekreef. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+import torch.nn as nn
+
+from ahcore.data.interfaces import AdapterBundle
+
+
+class AdapterAugmentor(nn.Module):
+    """Interface for an augmentor that maps an :class:`AdapterBundle` to an augmented ``AdapterBundle``."""
+
+    def __call__(self, bundle: AdapterBundle) -> AdapterBundle:
+        raise NotImplementedError

ahcore-0.1.0/ahcore/augmentations/tile_features.py

@@ -0,0 +1,104 @@
+# Copyright 2025 Joren Brunekreef. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import annotations
+
+import hashlib
+from typing import Callable
+
+import torch
+import torch.nn as nn
+
+from ahcore.data.interfaces import AdapterBundle
+
+
+class TileFeaturesAugmentation(nn.Module):
+    """Runs an ordered list of bundle-to-bundle transforms over a tile-features :class:`AdapterBundle`.
+
+    Each transform maps an ``AdapterBundle`` to an ``AdapterBundle``; ``forward`` applies them in order.
+    Use :meth:`for_classification` for the default tile-subsampling pipeline.
+    """
+
+    def __init__(self, transforms: list[Callable[[AdapterBundle], AdapterBundle]]) -> None:
+        super().__init__()
+        self._transforms = transforms
+
+    @classmethod
+    def for_classification(
+        cls, num_tiles: int = 1000, seed: int | None = None, per_sample: bool = False, meta_key: str = "slide_id"
+    ) -> TileFeaturesAugmentation:
+        transforms: list[Callable[[AdapterBundle], AdapterBundle]] = [
+            SelectRandomTiles(num_tiles=num_tiles, seed=seed, per_sample=per_sample, meta_key=meta_key),
+        ]
+        return TileFeaturesAugmentation(transforms)
+
+    def forward(self, data: AdapterBundle) -> AdapterBundle:
+        for transform in self._transforms:
+            data = transform(data)
+        return data
+
+
+class SelectRandomTiles(nn.Module):
+    """Randomly subsample a fixed number of tiles from a bundle, keeping all per-tile tensors aligned.
+
+    Samples ``num_tiles`` rows without replacement (with replacement if the bag is smaller) and applies
+    the same indices to every per-tile tensor in ``bundle.data`` so features/coords stay row-aligned.
+    With ``seed`` set the choice is deterministic; ``per_sample=True`` derives the seed from
+    ``bundle.meta[meta_key]`` so each slide gets its own reproducible selection.
+    """
+
+    def __init__(
+        self, num_tiles: int, seed: int | None = None, per_sample: bool = False, meta_key: str = "slide_id"
+    ) -> None:
+        super().__init__()
+        self._num_tiles = num_tiles
+        self._seed = seed
+        self._per_sample = per_sample
+        self._meta_key = meta_key
+
+    def _make_generator(self, bundle: AdapterBundle, device: torch.device | str) -> torch.Generator | None:
+        if self._seed is None:
+            return None
+        derived_seed = self._seed
+        if (
+            self._per_sample
+            and hasattr(bundle, "meta")
+            and isinstance(bundle.meta, dict)
+            and self._meta_key in bundle.meta
+        ):
+            key = str(bundle.meta[self._meta_key])
+            digest = hashlib.sha256(f"{self._seed}:{key}".encode("utf-8")).digest()
+            derived_seed = int.from_bytes(digest[:8], "little", signed=False)
+        gen = torch.Generator(device=device)
+        gen.manual_seed(derived_seed)
+        return gen
+
+    def forward(self, bundle: AdapterBundle) -> AdapterBundle:
+        features = bundle.data["features"]
+        num_features = features.shape[0]
+
+        gen = self._make_generator(bundle, features.device)
+
+        if num_features < self._num_tiles:
+            # If there are fewer features than num_tiles, we sample with replacement.
+            indices = torch.randint(0, num_features, (self._num_tiles,), device=features.device, generator=gen)
+        else:
+            # Otherwise, we sample without replacement.
+            indices = torch.randperm(num_features, device=features.device, generator=gen)[: self._num_tiles]
+
+        # Subsample every per-tile tensor by the same indices so features / coords / (future)
+        # patch_tokens stay row-aligned — no per-key hardcoding.
+        for key, value in bundle.data.items():
+            if isinstance(value, torch.Tensor) and value.shape[0] == num_features:
+                bundle.data[key] = value[indices]
+        return bundle