erislib 0.1.0__tar.gz

erislib-0.1.0/.gitignore

@@ -0,0 +1,214 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+/out/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# VScode stuff
+.vscode/
+
+# Visual Studio local state
+.vs/
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

erislib-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Kren-AI Lab
+
+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.

erislib-0.1.0/PKG-INFO

@@ -0,0 +1,251 @@
+Metadata-Version: 2.5
+Name: erislib
+Version: 0.1.0
+Summary: Eris: A modular library for protein structural representations and graph-based encoders.
+Project-URL: Homepage, https://github.com/kren-ai-lab/eris
+Project-URL: Repository, https://github.com/kren-ai-lab/eris
+Project-URL: Issues, https://github.com/kren-ai-lab/eris/issues
+Project-URL: Documentation, https://github.com/kren-ai-lab/eris#readme
+Author: Diego Fernández Villegas, Diego Alvarez-Saravia, David Medina-Ortiz
+Maintainer: Diego Fernández Villegas, Diego Alvarez-Saravia, David Medina-Ortiz
+License-Expression: MIT
+License-File: LICENSE
+Keywords: bioinformatics,geometric-deep-learning,graph-neural-networks,machine-learning,point-cloud,protein,protein-graphs,structural-biology,voxel
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Typing :: Typed
+Requires-Python: <3.15,>=3.11
+Requires-Dist: aaindex<2,>=1.3.2
+Requires-Dist: biotite<2,>=1.6
+Requires-Dist: gemmi<1,>=0.7
+Requires-Dist: numpy<3,>=2.0
+Requires-Dist: platformdirs<5,>=4.0
+Requires-Dist: polars<2,>=1.44
+Requires-Dist: pyyaml<7,>=6
+Requires-Dist: rich<16,>=13.0
+Requires-Dist: typer<1,>=0.27
+Provides-Extra: gearnet
+Requires-Dist: torch<3,>=2.11; extra == 'gearnet'
+Provides-Extra: pyg
+Requires-Dist: torch-geometric<3,>=2.6; extra == 'pyg'
+Requires-Dist: torch<3,>=2.11; extra == 'pyg'
+Description-Content-Type: text/markdown
+
+# Eris
+
+[![PyPI](https://img.shields.io/pypi/v/erislib?style=flat-square)](https://pypi.org/project/erislib/)
+[![PyVersions](https://img.shields.io/pypi/pyversions/erislib?style=flat-square)](https://github.com/kren-ai-lab/eris)
+[![Tests](https://img.shields.io/github/actions/workflow/status/kren-ai-lab/eris/tests.yml?style=flat-square)](https://github.com/kren-ai-lab/eris/actions/workflows/tests.yml)
+![License](https://img.shields.io/github/license/kren-ai-lab/eris?style=flat-square)
+
+Eris is a Python library that turns protein structures (PDB and mmCIF) into numerical
+representations for machine learning. It builds point clouds, graphs, contact maps, distograms and
+voxel grids, and GearNet-Edge embeddings. Every result is a validated `StructureArtifact` that keeps
+the arrays together with the structure selection, parameters and provenance that produced them.
+
+Eris doesn't train models. Its artifacts feed PyTorch, PyTorch Geometric or any NumPy-based
+pipeline.
+
+## Installation
+
+Eris supports Python 3.11 to 3.14.
+
+```bash
+pip install erislib
+# or with uv:
+uv add erislib
+```
+
+Optional extras:
+
+```bash
+pip install "erislib[gearnet]"   # GearNet-Edge embeddings (PyTorch)
+pip install "erislib[pyg]"       # PyTorch Geometric export
+```
+
+For development setup with `uv`, see
+[DEVELOPMENT.md](https://github.com/kren-ai-lab/eris/blob/main/DEVELOPMENT.md).
+
+## Encode a structure
+
+```python
+import eris
+
+artifact = eris.encode(
+    "protein.pdb",
+    representation="residue_knn_graph",
+    chain_id="A",
+    k=8,
+    output="artifacts/protein_knn",
+)
+artifact.data["edge_index"].shape   # (2, n_edges)
+artifact.meta["parameters"]         # canonical parameters, including defaults
+```
+
+Representation parameters are passed as keyword arguments and validated against the
+representation's config. `eris.list_representations()` lists the representations and
+`eris.get_representation_info(name)` shows one with its parameters and defaults. `output=` writes
+the artifact as a directory (`meta.json` plus `data.npz`) that
+`eris.core.artifacts.StructureArtifact.load(path)` reads back and validates.
+
+| Name                       | Type   | Granularity | Primary output                   |
+| -------------------------- | ------ | ----------- | -------------------------------- |
+| `atom_point_cloud`         | cloud  | atom        | atom coordinates and features    |
+| `residue_point_cloud`      | cloud  | residue     | residue coordinates and features |
+| `atom_knn_graph`           | graph  | atom        | atom k-nearest-neighbor graph    |
+| `residue_knn_graph`        | graph  | residue     | residue k-nearest-neighbor graph |
+| `residue_contact_graph`    | graph  | residue     | distance-cutoff residue graph    |
+| `residue_distogram`        | matrix | residue     | pairwise distances               |
+| `residue_distogram_bins`   | matrix | residue     | distance-bin classes             |
+| `residue_contact_map`      | matrix | residue     | binary contacts                  |
+| `residue_contact_map_bins` | matrix | residue     | distance-bin contact classes     |
+| `residue_voxel_grid`       | grid   | residue     | multi-channel 3D grid            |
+
+Residue coordinates can use the alpha carbon, the residue-atom mean or the center of mass. Residue
+features can combine amino-acid identity, physicochemical descriptors, AAIndex1 records, raw
+B-factor, explicitly interpreted pLDDT, backbone and side-chain torsions, local structural features,
+and aligned external values. Residue graphs can add chain relations, relative directions and
+interface annotations. `eris.pool(...)` turns residue features into one structure-level vector.
+
+## Learned embeddings
+
+```python
+artifact = eris.embed("protein.pdb", representation="gearnet_edge", output_mode="both")
+```
+
+`gearnet_edge` emits residue embeddings (`node`), one structure embedding (`global`), or both. It
+runs the official `mc_gearnet_edge.pth` checkpoint on CPU in fp32. The checkpoint isn't bundled: on
+first use, Eris downloads it over HTTPS, checks its registered SHA-256 and caches it. To work
+offline, pass a local copy with `checkpoint_path=` (`--checkpoint` in the CLI).
+
+## Batches, datasets and export
+
+```python
+import polars as pl
+import eris
+from eris.datasets import ErisFolderDataset
+
+manifest = pl.DataFrame({"id": ["p1", "p2"], "path": ["p1.pdb", "p2.cif"], "chain": ["A", None]})
+results = eris.batch_encode(manifest, representation="residue_knn_graph", artifact_root="artifacts")
+index = eris.pack("artifacts", "artifacts/index.csv")
+dataset = ErisFolderDataset("artifacts/index.csv")   # loads each artifact on access
+graph = eris.to_pyg(eris.encode("p1.pdb", representation="residue_knn_graph"))
+```
+
+A manifest is a CSV or JSONL file or a Polars DataFrame with `id` and `path` columns, and optional
+`chain` and `model` (default: all chains of the first model). `batch_encode` and `batch_embed`
+return one result row per input, record failures without stopping (unless `fail_fast=True`) and
+can resume an interrupted run. `pack` writes a CSV index over the artifact directories.
+`to_torch` converts any artifact to tensors; `to_pyg` only accepts graphs with an explicit
+`edge_index`.
+
+### Feature tables
+
+`feature_table` turns one structure-level vector per artifact into a Polars DataFrame with an `id`
+column and one column per feature, ready for tabular models such as
+[Saber](https://github.com/kren-ai-lab/saber):
+
+```python
+embeddings = eris.batch_embed(manifest, representation="gearnet_edge", artifact_root="emb", output_mode="global")
+eris.pack("emb", "emb/index.csv")
+features = eris.feature_table("emb/index.csv")   # id, p_0 ... p_3071
+
+dataset = saber.DatasetBundle(X=features.drop("id"), y=labels, sample_ids=features["id"])
+```
+
+It reads GearNet global embeddings (`p_0`, `p_1`, …) or `eris.pool(...)` vectors (named after
+their features), or graph statistics with `source="graph_attr"`. It also accepts a mapping from id
+to artifact. Every row must come from the same representation, parameters and model; mixing them
+is an error.
+
+## Command line
+
+```bash
+eris representations list
+eris encode protein.pdb --representation residue_knn_graph --params '{"k": 8}' --out artifact_knn
+eris embed protein.pdb --representation gearnet_edge --out embedding
+eris batch encode manifest.csv --representation residue_contact_map --out artifacts
+eris pack artifacts --out artifacts/index.csv
+eris features emb/index.csv --out features.csv
+eris info validate artifact_knn
+```
+
+Each command calls the matching Python function.
+
+`encode`, `embed` and the `batch` commands accept `--config PATH`, a YAML or JSON file whose keys are the option names (`representation`, `device`, ...). Representation parameters go under `params:`. Precedence is defaults < file < flags, and a `--params` flag replaces the file's `params` as a whole. Paths (input, `out`, `results`, `checkpoint`) stay on the command line.
+
+```yaml
+representation: residue_knn_graph
+params:
+  k: 8
+```
+
+`eris validate-config COMMAND CONFIG [--json]` checks such a file without reading structures (`COMMAND` is `encode`, `embed`, `batch-encode`, `batch-embed` or `batch-from-folder`). It prints one `path: message` line per problem to stderr, or with `--json` a JSON array of `{path, message}` on stdout, and exits `0` if valid or `2` if not.
+
+Validate a config from Python (no structures read, no model code imported):
+
+```python
+from eris import validate_config
+
+issues = validate_config("config.yaml", "encode")  # or a mapping; target as on the CLI
+for issue in issues:  # ConfigIssue(path, message); empty when valid
+    print(issue.path or "<root>", issue.message)
+```
+
+Every successful run also writes `<out>.provenance.json` next to the output (shared ecosystem CLI contract): tool version, effective parameters and their fingerprint, input and output hashes, and the environment. The artifact's own `meta.json` is unchanged in format.
+
+Exit codes:
+
+| Code | Meaning                                                                                                              |
+| ---- | -------------------------------------------------------------------------------------------------------------------- |
+| `0`  | Success (batch commands also exit `0` when some rows fail; see the results file)                                     |
+| `2`  | Invalid usage or configuration (missing argument or config file, unknown representation, invalid parameters)         |
+| `3`  | The operation failed (missing or unreadable structure, manifest or folder, invalid artifact, backend or cache error) |
+| `4`  | Unexpected internal error                                                                                            |
+
+## Design principles
+
+- Eris never silently pads, truncates, resizes, normalizes or clips values, and never invents
+  identifiers or drops failed samples. Graph edges come only from the documented neighbor or
+  cutoff rule, and exports never add topology that the artifact doesn't already contain.
+- Inputs that don't make scientific sense fail with a clear error instead of being coerced.
+- Sample identity, array order, feature order and keys are deterministic.
+- An artifact records the structure selection, canonical parameters and provenance, and is validated
+  every time it is saved or loaded.
+- The cache is keyed by the input file's content and the full configuration, so a changed input or
+  parameter never returns a stale result.
+- `import eris` doesn't load PyTorch, PyTorch Geometric or the GearNet runtime; they load only when
+  a feature needs them.
+- At runtime, the only network access is the download of the registered GearNet checkpoint.
+
+## Documentation and examples
+
+The [documentation index](https://github.com/kren-ai-lab/eris/blob/main/docs/README.md) links the
+technical references: representation defaults, structural features, artifact schema, external
+residue features and the GearNet-Edge backend. The
+[example notebooks](https://github.com/kren-ai-lab/eris/blob/main/examples/README.md) are written
+in marimo. To open one:
+
+```bash
+uv sync --all-extras --group examples
+uv run marimo edit examples/01_explicit_representations.py
+```
+
+## Citing and license
+
+If you use Eris in published work, please cite it using
+[`CITATION.cff`](https://github.com/kren-ai-lab/eris/blob/main/CITATION.cff), or the "Cite this
+repository" button on GitHub. Eris is released under the
+[MIT license](https://github.com/kren-ai-lab/eris/blob/main/LICENSE).
+
+GearNet-Edge uses the official Multiview Contrast checkpoint from
+[Zenodo record 10.5281/zenodo.7723075](https://doi.org/10.5281/zenodo.7723075). Eris provides a
+native runtime for that checkpoint and did not train it.