atomworks 2.2.0__tar.gz → 3.0.0__tar.gz

{atomworks-2.2.0 → atomworks-3.0.0}/.gitignore

@@ -5,6 +5,7 @@ biotite
 # github pages
 docs/_build/*
 docs/auto_examples/*
+docs/sg_execution_times.rst
 
 
 # Python files
@@ -109,15 +110,6 @@ celerybeat-schedule
 # SageMath parsed files
 *.sage.py
 
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
 # github pages
 docs/_build/*
 docs/auto_examples/*
@@ -155,6 +147,7 @@ cython_debug/
 *.pkl
 *.parquet
 *.csv
+*.ciflmdb-lock
 
 # Temporary test files
 tests/test_outputs
@@ -166,8 +159,10 @@ tinker/
 
 # Local scripts
 **/logs
+.ipd/
 
 # AI
 **/.claude
-CLAUDE.md
 .github/workflows/claude*.yml
+
+.devcontainer

{atomworks-2.2.0 → atomworks-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: atomworks
-Version: 2.2.0
+Version: 3.0.0
 Summary: A research-oriented data toolkit for training biomolecular deep-learning foundation models
 Project-URL: homepage, https://rosettacommons.github.io/atomworks/latest/index.html
 Project-URL: repository, https://github.com/RosettaCommons/atomworks
@@ -46,64 +46,88 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.11
-Requires-Dist: biotite==1.4.0
-Requires-Dist: cython<4,>=3.0.0
-Requires-Dist: cytoolz<1,>=0.12.3
-Requires-Dist: hydride<2,>=1.2.3
-Requires-Dist: numpy<3,>=1.25.0
-Requires-Dist: pandas<2.4,>=2.2
-Requires-Dist: py3dmol<3,>=2.2.1
-Requires-Dist: pyarrow==17.0.0
+Requires-Dist: biotite==1.6.0
+Requires-Dist: cython>=3.0.0
+Requires-Dist: cytoolz>=0.12.3
+Requires-Dist: idna>=3.15
+Requires-Dist: jaxtyping>=0.2.17
+Requires-Dist: numpy>=1.25.0
+Requires-Dist: pandas>=2.2
+Requires-Dist: pillow>=12.3.0
+Requires-Dist: py3dmol>=2.2.1
+Requires-Dist: pyarrow>=23.0.1
+Requires-Dist: pygments>=2.20.0
 Requires-Dist: pymol-remote>=0.0.5
-Requires-Dist: rdkit<2025.9,>=2024.3.5
-Requires-Dist: scipy<2,>=1.13.1
-Requires-Dist: tqdm<5,>=4.65.0
-Requires-Dist: typer<1,>=0.12.5
-Requires-Dist: zstandard<1,>=0.21.0
+Requires-Dist: python-dotenv>=1.2.2
+Requires-Dist: rdkit>=2024.3.5
+Requires-Dist: requests>=2.33.0
+Requires-Dist: scipy>=1.13.1
+Requires-Dist: tqdm>=4.66.3
+Requires-Dist: typer>=0.12.5
+Requires-Dist: urllib3>=2.8.0
+Requires-Dist: zstandard>=0.21.0
 Provides-Extra: ase
-Requires-Dist: ase-db-backends<1,>=0.10.0; extra == 'ase'
-Requires-Dist: ase<4,>=3.22.0; extra == 'ase'
-Requires-Dist: lmdb<2,>=1.5.0; extra == 'ase'
+Requires-Dist: ase-db-backends>=0.10.0; extra == 'ase'
+Requires-Dist: ase>=3.22.0; extra == 'ase'
+Requires-Dist: cryptography>=50.0.0; extra == 'ase'
+Requires-Dist: lmdb>=1.5.0; extra == 'ase'
+Provides-Extra: catcif
+Requires-Dist: catcif-tools; extra == 'catcif'
 Provides-Extra: dev
+Requires-Dist: fire>=0.5.0; extra == 'dev'
 Requires-Dist: ipykernel>=6.28.0; extra == 'dev'
-Requires-Dist: pytest-benchmark<6,>=5.0.0; extra == 'dev'
-Requires-Dist: pytest-cov<5,>=4.1.0; extra == 'dev'
-Requires-Dist: pytest-dotenv<1,>=0.5.2; extra == 'dev'
-Requires-Dist: pytest-testmon<3,>=2.1.1; extra == 'dev'
-Requires-Dist: pytest-xdist<4,>=3.6.1; extra == 'dev'
-Requires-Dist: pytest<9,>=8.2.0; extra == 'dev'
+Requires-Dist: pytest-benchmark>=5.0.0; extra == 'dev'
+Requires-Dist: pytest-cov>=4.1.0; extra == 'dev'
+Requires-Dist: pytest-dotenv>=0.5.2; extra == 'dev'
+Requires-Dist: pytest-testmon>=2.1.1; extra == 'dev'
+Requires-Dist: pytest-xdist>=3.6.1; extra == 'dev'
+Requires-Dist: pytest>=9.0.3; extra == 'dev'
 Requires-Dist: ruff==0.8.3; extra == 'dev'
+Requires-Dist: tornado>=6.5.9; extra == 'dev'
 Provides-Extra: docs
-Requires-Dist: matplotlib<4,>=3.10.0; extra == 'docs'
-Requires-Dist: pydata-sphinx-theme<1,>=0.16.1; extra == 'docs'
-Requires-Dist: sphinx-gallery<1,>=0.19.0; extra == 'docs'
-Requires-Dist: sphinx<9,>=8.0.0; extra == 'docs'
+Requires-Dist: matplotlib>=3.10.0; extra == 'docs'
+Requires-Dist: myst-parser>=4.0.0; extra == 'docs'
+Requires-Dist: pydata-sphinx-theme>=0.16.1; extra == 'docs'
+Requires-Dist: sphinx-design>=0.6.0; extra == 'docs'
+Requires-Dist: sphinx-gallery>=0.19.0; extra == 'docs'
+Requires-Dist: sphinx>=8.0.0; extra == 'docs'
+Requires-Dist: sphinxcontrib-typer<1,>=0.7.2; extra == 'docs'
 Provides-Extra: ml
-Requires-Dist: beartype<1,>=0.18.0; extra == 'ml'
-Requires-Dist: einops<1,>=0.7.0; extra == 'ml'
-Requires-Dist: jaxtyping<1,>=0.2.17; extra == 'ml'
-Requires-Dist: torch<2.8,>=2.2.0; extra == 'ml'
+Requires-Dist: beartype>=0.18.0; extra == 'ml'
+Requires-Dist: einops>=0.7.0; extra == 'ml'
+Requires-Dist: filelock>=3.20.3; extra == 'ml'
+Requires-Dist: numba>=0.60.0; extra == 'ml'
+Requires-Dist: requests>=2.33.0; extra == 'ml'
+Requires-Dist: torch>=2.2.0; extra == 'ml'
 Provides-Extra: openbabel
-Requires-Dist: openbabel-wheel==3.1.1.22; extra == 'openbabel'
+Requires-Dist: openbabel-wheel>=3.1.1.22; extra == 'openbabel'
+Provides-Extra: posebusters
+Requires-Dist: posebusters>=0.6.0; extra == 'posebusters'
+Provides-Extra: s3
+Requires-Dist: boto3; extra == 's3'
 Description-Content-Type: text/markdown
 
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![CI](https://github.com/RosettaCommons/atomworks/actions/workflows/release_and_docs.yaml/badge.svg?branch=release%2Fatomworks-3-0)](https://github.com/RosettaCommons/atomworks/actions/workflows/release_and_docs.yaml)
 [![PyPI version](https://img.shields.io/pypi/v/atomworks.svg)](https://pypi.org/project/atomworks/)
 [![Python versions](https://img.shields.io/pypi/pyversions/atomworks.svg)](https://pypi.org/project/atomworks/)
 [![Documentation Status](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://rosettacommons.github.io/atomworks/latest/)
 [![License: BSD 3-Clause](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)
 
 <div align="center">
-  <img src="docs/_static/atomworks_logo_color.svg" width="450" alt="atomworks logo">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/RosettaCommons/atomworks/release/atomworks-3-0/docs/_static/atomworks_logo_dark.svg">
+    <img src="https://raw.githubusercontent.com/RosettaCommons/atomworks/release/atomworks-3-0/docs/_static/atomworks_logo_color.svg" width="450" alt="AtomWorks logo">
+  </picture>
 </div>
 
 **atomworks** is an open-source platform that maximizes research velocity for biomolecular modeling tasks. Much like how [Torchvision](https://docs.pytorch.org/vision/stable/index.html) enables rapid prototyping within the vision domain, and [Torchaudio](https://docs.pytorch.org/audio/main/) within the audio domain, AtomWorks aims to accelerate development and experimentation within biomolecular modeling.
 
-> **⚠️ Notice:** We are currently finalizing some cleanup work within our repositories. Please expect the APIs (e.g., function and class names, inputs and outputs) to stabilize within the next one week. Thank you for your patience!
+Upgrading to 3.0? See the [migration guide](https://github.com/RosettaCommons/atomworks/blob/release/atomworks-3-0/docs/migration/migration-short.md).
 
-If you're looking for the models themselves (e.g., RF3, MPNN) that integrate with AtomWorks rather than the underlying framework, check out [ModelForge](https://github.com/RosettaCommons/modelforge)
+If you're looking for the models themselves (e.g., RF3, RFD3, MPNN) that integrate with AtomWorks rather than the underlying framework, check out [Foundry](https://github.com/RosettaCommons/foundry)
 
-> **💡 Note:** Not sure where to start? We've made some [examples in the AtomWorks documentation](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) that work through several helpful scenarios; a full tutorial is under construction!
+> **💡 Note:** Start with the [AtomWorks examples](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) or the [model-building tutorial](https://github.com/RosettaCommons/atomworks/blob/release/atomworks-3-0/docs/how_to_build_a_model/index.rst).
 
 AtomWorks is composed of two symbiotic libraries:
 
@@ -118,7 +142,7 @@ AtomWorks is built atop [biotite](https://www.biotite-python.org/): We are grate
 
 ## atomworks.io
 
-> *A general-purpose Python toolkit for cleaning, standardizing, and manipulating with biomolecular structure files - built atop [biotite](https://www.biotite-python.org/):
+> *A general-purpose Python toolkit for cleaning, standardizing, and manipulating biomolecular structure files, built on [Biotite](https://www.biotite-python.org/).*
 
 **atomworks.io** lets you:
 
@@ -140,7 +164,7 @@ We have found `atomworks.io` to be generally useful to a broad bioinformatics an
 - An extensible framework, integrated with `atomworks.io`, to write `Transforms` for arbitrary use cases
 - Pre-built datasets and samplers suitable for most model training scenarios
 
-Within the AtomWorks paradigm, the output of each `Transform` is not an opaque dictionary with model-specific tensors but instead an updated version of our atom-level structural representation (Biotite's `AtomArray`). Operations within – and between – pipelines thus maintain a common vocabulary of inputs and outputs.
+Transforms consume and return dictionaries containing structural data, annotations and features. Biotite's `AtomArray` provides their shared atom-level representation.
 
 We have found that `atomworks.ml` **dramatically** reduces the overhead of starting, and completing, many ML projects; research topics that once took months now achieve signal within weeks if not days, accelerating the pace of innovation.
 
@@ -161,14 +185,14 @@ We have found that `atomworks.ml` **dramatically** reduces the overhead of start
 ---
 
 ## Installation
-> Note: AtomWorks requires Python >= 3.11 and [`dotenv`](https://pypi.org/project/python-dotenv/#file-format)
+AtomWorks requires Python 3.11 or newer. Pip installs its dependencies automatically.
 
 ```shell
 pip install atomworks # base installation version without torch (for only atomworks.io)
 pip install "atomworks[ml]" # with torch and ML dependencies (for atomworks.io plus atomworks.ml)
 pip install "atomworks[dev]" # with development dependencies
 pip install "atomworks[openbabel]" # with [Open Babel](https://openbabel.org/) and its dependencies
-pip install "atomworks[ml,openbabel,dev]" # with all dependencies
+pip install "atomworks[ml,openbabel,dev]" # ML, Open Babel, and development tools
 ```
 *Running multiple of these installations will just add to the installed dependencies and will not install multiple installations of atomworks.*
 
@@ -178,6 +202,12 @@ If you are using [uv](https://docs.astral.sh/uv/reference/policies/versioning/)
 uv pip install "atomworks[ml,openbabel,dev]"
 ```
 
+To install the AtomWorks 3.0 release branch before it is published on PyPI:
+
+```shell
+pip install "atomworks[ml] @ git+https://github.com/RosettaCommons/atomworks.git@release/atomworks-3-0"
+```
+
 For more advanced setup options (including how to run workflows via apptainers) see the [full documentation](https://rosettacommons.github.io/atomworks/latest/index.html).
 
 ---
@@ -192,10 +222,11 @@ To parse a pdb file (parse = load, clean, annotate relevant metadata such as ent
 
 ```python
 
-from atomworks.io.parser import parse
+from atomworks.io import parse
+from atomworks.io.config import ParseConfig
 from biotite.structure import AtomArrayStack
 
-result = parse(filename="3nez.cif.gz")
+result = parse("3nez.cif.gz", config=ParseConfig.from_preset("rcsb"))
 
 asym_unit: AtomArrayStack = result["asym_unit"]
 assemblies: dict[str, AtomArrayStack] = result["assemblies"]
@@ -216,13 +247,13 @@ The output of `parse` includes:
 See [usage examples](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) for more examples of the use of `parse()`. All of the provided examples make use of this method. 
 See [API reference documentation](https://rosettacommons.github.io/atomworks/latest/io/parser.html) for more information on this method.
 
-If you just want to load a file, you can use the `load_any` function:
+For minimal processing, use the same parser with the `minimal` preset:
 
 ```python
-from atomworks.io.utils.io_utils import load_any
+from atomworks.io import parse
 from biotite.structure import AtomArray
 
-atom_array: AtomArray = load_any("3nez.cif.gz", model=1)  # model=1 means that we want to load the model 1 (i.e. the first model) rather than a stack of all models in the file
+atom_array: AtomArray = parse("3nez.cif.gz", config="minimal")["asym_unit"][0]
 ```
 
 ---

{atomworks-2.2.0 → atomworks-3.0.0}/README.md

@@ -1,20 +1,24 @@
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![CI](https://github.com/RosettaCommons/atomworks/actions/workflows/release_and_docs.yaml/badge.svg?branch=release%2Fatomworks-3-0)](https://github.com/RosettaCommons/atomworks/actions/workflows/release_and_docs.yaml)
 [![PyPI version](https://img.shields.io/pypi/v/atomworks.svg)](https://pypi.org/project/atomworks/)
 [![Python versions](https://img.shields.io/pypi/pyversions/atomworks.svg)](https://pypi.org/project/atomworks/)
 [![Documentation Status](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://rosettacommons.github.io/atomworks/latest/)
 [![License: BSD 3-Clause](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)
 
 <div align="center">
-  <img src="docs/_static/atomworks_logo_color.svg" width="450" alt="atomworks logo">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/RosettaCommons/atomworks/release/atomworks-3-0/docs/_static/atomworks_logo_dark.svg">
+    <img src="https://raw.githubusercontent.com/RosettaCommons/atomworks/release/atomworks-3-0/docs/_static/atomworks_logo_color.svg" width="450" alt="AtomWorks logo">
+  </picture>
 </div>
 
 **atomworks** is an open-source platform that maximizes research velocity for biomolecular modeling tasks. Much like how [Torchvision](https://docs.pytorch.org/vision/stable/index.html) enables rapid prototyping within the vision domain, and [Torchaudio](https://docs.pytorch.org/audio/main/) within the audio domain, AtomWorks aims to accelerate development and experimentation within biomolecular modeling.
 
-> **⚠️ Notice:** We are currently finalizing some cleanup work within our repositories. Please expect the APIs (e.g., function and class names, inputs and outputs) to stabilize within the next one week. Thank you for your patience!
+Upgrading to 3.0? See the [migration guide](https://github.com/RosettaCommons/atomworks/blob/release/atomworks-3-0/docs/migration/migration-short.md).
 
-If you're looking for the models themselves (e.g., RF3, MPNN) that integrate with AtomWorks rather than the underlying framework, check out [ModelForge](https://github.com/RosettaCommons/modelforge)
+If you're looking for the models themselves (e.g., RF3, RFD3, MPNN) that integrate with AtomWorks rather than the underlying framework, check out [Foundry](https://github.com/RosettaCommons/foundry)
 
-> **💡 Note:** Not sure where to start? We've made some [examples in the AtomWorks documentation](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) that work through several helpful scenarios; a full tutorial is under construction!
+> **💡 Note:** Start with the [AtomWorks examples](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) or the [model-building tutorial](https://github.com/RosettaCommons/atomworks/blob/release/atomworks-3-0/docs/how_to_build_a_model/index.rst).
 
 AtomWorks is composed of two symbiotic libraries:
 
@@ -29,7 +33,7 @@ AtomWorks is built atop [biotite](https://www.biotite-python.org/): We are grate
 
 ## atomworks.io
 
-> *A general-purpose Python toolkit for cleaning, standardizing, and manipulating with biomolecular structure files - built atop [biotite](https://www.biotite-python.org/):
+> *A general-purpose Python toolkit for cleaning, standardizing, and manipulating biomolecular structure files, built on [Biotite](https://www.biotite-python.org/).*
 
 **atomworks.io** lets you:
 
@@ -51,7 +55,7 @@ We have found `atomworks.io` to be generally useful to a broad bioinformatics an
 - An extensible framework, integrated with `atomworks.io`, to write `Transforms` for arbitrary use cases
 - Pre-built datasets and samplers suitable for most model training scenarios
 
-Within the AtomWorks paradigm, the output of each `Transform` is not an opaque dictionary with model-specific tensors but instead an updated version of our atom-level structural representation (Biotite's `AtomArray`). Operations within – and between – pipelines thus maintain a common vocabulary of inputs and outputs.
+Transforms consume and return dictionaries containing structural data, annotations and features. Biotite's `AtomArray` provides their shared atom-level representation.
 
 We have found that `atomworks.ml` **dramatically** reduces the overhead of starting, and completing, many ML projects; research topics that once took months now achieve signal within weeks if not days, accelerating the pace of innovation.
 
@@ -72,14 +76,14 @@ We have found that `atomworks.ml` **dramatically** reduces the overhead of start
 ---
 
 ## Installation
-> Note: AtomWorks requires Python >= 3.11 and [`dotenv`](https://pypi.org/project/python-dotenv/#file-format)
+AtomWorks requires Python 3.11 or newer. Pip installs its dependencies automatically.
 
 ```shell
 pip install atomworks # base installation version without torch (for only atomworks.io)
 pip install "atomworks[ml]" # with torch and ML dependencies (for atomworks.io plus atomworks.ml)
 pip install "atomworks[dev]" # with development dependencies
 pip install "atomworks[openbabel]" # with [Open Babel](https://openbabel.org/) and its dependencies
-pip install "atomworks[ml,openbabel,dev]" # with all dependencies
+pip install "atomworks[ml,openbabel,dev]" # ML, Open Babel, and development tools
 ```
 *Running multiple of these installations will just add to the installed dependencies and will not install multiple installations of atomworks.*
 
@@ -89,6 +93,12 @@ If you are using [uv](https://docs.astral.sh/uv/reference/policies/versioning/)
 uv pip install "atomworks[ml,openbabel,dev]"
 ```
 
+To install the AtomWorks 3.0 release branch before it is published on PyPI:
+
+```shell
+pip install "atomworks[ml] @ git+https://github.com/RosettaCommons/atomworks.git@release/atomworks-3-0"
+```
+
 For more advanced setup options (including how to run workflows via apptainers) see the [full documentation](https://rosettacommons.github.io/atomworks/latest/index.html).
 
 ---
@@ -103,10 +113,11 @@ To parse a pdb file (parse = load, clean, annotate relevant metadata such as ent
 
 ```python
 
-from atomworks.io.parser import parse
+from atomworks.io import parse
+from atomworks.io.config import ParseConfig
 from biotite.structure import AtomArrayStack
 
-result = parse(filename="3nez.cif.gz")
+result = parse("3nez.cif.gz", config=ParseConfig.from_preset("rcsb"))
 
 asym_unit: AtomArrayStack = result["asym_unit"]
 assemblies: dict[str, AtomArrayStack] = result["assemblies"]
@@ -127,13 +138,13 @@ The output of `parse` includes:
 See [usage examples](https://rosettacommons.github.io/atomworks/latest/auto_examples/index.html) for more examples of the use of `parse()`. All of the provided examples make use of this method. 
 See [API reference documentation](https://rosettacommons.github.io/atomworks/latest/io/parser.html) for more information on this method.
 
-If you just want to load a file, you can use the `load_any` function:
+For minimal processing, use the same parser with the `minimal` preset:
 
 ```python
-from atomworks.io.utils.io_utils import load_any
+from atomworks.io import parse
 from biotite.structure import AtomArray
 
-atom_array: AtomArray = load_any("3nez.cif.gz", model=1)  # model=1 means that we want to load the model 1 (i.e. the first model) rather than a stack of all models in the file
+atom_array: AtomArray = parse("3nez.cif.gz", config="minimal")["asym_unit"][0]
 ```
 
 ---

{atomworks-2.2.0 → atomworks-3.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "atomworks"
-version = "2.2.0"
+version = "3.0.0"
 description = "A research-oriented data toolkit for training biomolecular deep-learning foundation models"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -23,76 +23,111 @@ classifiers = [
 
 dependencies = [
     # ... generic tools
-    "cython>=3.0.0,<4", # Cython compiler for C extensions
-    "cytoolz>=0.12.3,<1", # Cython-optimized tools for itertools and functional programming
-    "tqdm>=4.65.0,<5", # Fast, extensible progress bar for loops and more
+    "cython>=3.0.0", # Cython compiler for C extensions
+    "cytoolz>=0.12.3", # Cython-optimized tools for itertools and functional programming
+    "tqdm>=4.66.3", # Fast, extensible progress bar for loops and more
     # ... CLI & config management
-    "typer>=0.12.5,<1", # Modern CLI framework
+    "typer>=0.12.5", # Modern CLI framework
+    "python-dotenv>=1.2.2", # Environment loading for the CLI
+    "pygments>=2.20.0", # Traceback formatting in core IO
     # ... linear algebra, maths & ml
-    "numpy>=1.25.0,<3",
-    "scipy>=1.13.1,<2",
+    "numpy>=1.25.0",
+    "jaxtyping>=0.2.17", # Array annotations used by core IO
+    "scipy>=1.13.1",
     # ... data tools
-    "pandas>=2.2,<2.4", # Data manipulation and analysis
-    "pyarrow==17.0.0", # Columnar data format for efficient data storage and processing  # TODO: Test later versions
+    "pandas>=2.2", # Data manipulation and analysis
+    "pyarrow>=23.0.1", # Columnar data format for efficient data storage and processing
     # ... compression
-    "zstandard>=0.21.0,<1", # Zstandard compression for MSA files and other data
+    "zstandard>=0.21.0", # Zstandard compression for MSA files and other data
     # ... bioinformatics
-    "py3Dmol>=2.2.1,<3", # Python wrapper for 3Dmol.js
+    "py3Dmol>=2.2.1", # Python wrapper for 3Dmol.js
     "pymol-remote>=0.0.5", # Remote access to PyMOL from Python (has no dependencies)
-    "biotite==1.4.0", # Biotite is a Python library for bioinformatics  # TODO: Test newer versions
-    "hydride>=1.2.3,<2", # Biotite-supported tool for hydrogen addition
+    # Pinned exactly: atomworks monkey-patches biotite internals and ``atomworks/__init__.py``
+    # refuses to import against any other version. A ``>=`` floor here silently resolves to a
+    # newer biotite that then fails at import time.
+    "biotite==1.6.0", # Biotite is a Python library for bioinformatics
     # ... small molecule libraries
-    "rdkit>=2024.3.5,<2025.9",
+    "rdkit>=2024.3.5",
+    "urllib3>=2.8.0",
+    "pillow>=12.3.0",
+    "idna>=3.15",
+    "requests>=2.33.0",
 ]
 
 [project.optional-dependencies]
 ml = [
     # atomworks-ml dependencies
-    "torch>=2.2.0,<2.8",
-    "einops>=0.7.0,<1",
-    "jaxtyping>=0.2.17,<1",
-    "beartype>=0.18.0,<1",
+    "torch>=2.2.0",
+    "requests>=2.33.0", # Remote MMseqs2 server client
+    "einops>=0.7.0",
+    "beartype>=0.18.0",
+    "numba>=0.60.0",
+    "filelock>=3.20.3",
+]
+
+s3 = [
+    # Reading blob stores / parquet directly from ``s3://`` URLs
+    "boto3",
 ]
 
 ase = [
     # ASE (Atomic Simulation Environment) dataset support
-    "ase>=3.22.0,<4",  # Atomic Simulation Environment
-    "ase-db-backends>=0.10.0,<1",  # Database backends for ASE (PostgreSQL, MySQL, LMDB)
-    "lmdb>=1.5.0,<2",  # LMDB backend for ASE database support (required for .aselmdb files)
+    "ase>=3.22.0",  # Atomic Simulation Environment
+    "ase-db-backends>=0.10.0",  # Database backends for ASE (PostgreSQL, MySQL, LMDB)
+    "lmdb>=1.5.0",  # LMDB backend for ASE database support (required for .aselmdb files)
+    "cryptography>=50.0.0",
 ]
 
 openbabel = [
     # Optional openbabel dependency
-    "openbabel-wheel==3.1.1.22",
+    "openbabel-wheel>=3.1.1.22",
+]
+
+posebusters = [
+    # PoseBusters: structural validity checks for docked/predicted poses
+    "posebusters>=0.6.0",
+]
+
+catcif = [
+    # catcif: concatenated CIF archive format support
+    "catcif-tools",
 ]
 
 dev = [
     # Linters & formatters
     "ruff==0.8.3",
     # Testing tools
-    "pytest>=8.2.0,<9", # testing framework
-    "pytest-testmon>=2.1.1,<3", # run only tests related to changed code
-    "pytest-xdist>=3.6.1,<4", # run tests in parallel
-    "pytest-dotenv>=0.5.2,<1", # load environment variables from .env file
-    "pytest-cov>=4.1.0,<5", # generate coverage report
-    "pytest-benchmark>=5.0.0,<6", # benchmark tests for speed
+    "pytest>=9.0.3", # testing framework
+    "pytest-testmon>=2.1.1", # run only tests related to changed code
+    "pytest-xdist>=3.6.1", # run tests in parallel
+    "pytest-dotenv>=0.5.2", # load environment variables from .env file
+    "pytest-cov>=4.1.0", # generate coverage report
+    "pytest-benchmark>=5.0.0", # benchmark tests for speed
     # Jupyter notebooks
     "ipykernel>=6.28.0", # IPython kernel for Jupyter
+    "tornado>=6.5.9",
+    # CLI
+    "fire>=0.5.0", # CLI generation library
 ]
 
 docs = [
-    "sphinx>=8.0.0,<9",
-    "sphinx-gallery>=0.19.0,<1",
-    "pydata-sphinx-theme>=0.16.1,<1",
-    "matplotlib>=3.10.0,<4",
+    "sphinxcontrib-typer>=0.7.2,<1",
+    "sphinx>=8.0.0",
+    "sphinx-gallery>=0.19.0",
+    "pydata-sphinx-theme>=0.16.1",
+    "matplotlib>=3.10.0",
+    "myst-parser>=4.0.0", # Support Markdown tutorial pages
+    "sphinx-design>=0.6.0", # Render collapsible tutorial code examples
 ]
 
 [dependency-groups]
 # Reference optional dependencies for native uv compatability (in addition to the pip compatability)
 dev = ["atomworks[dev]"]
-ml = ["atomworks[ml]"] 
+ml = ["atomworks[ml]"]
 docs = ["atomworks[docs]"]
 openbabel = ["atomworks[openbabel]"]
+posebusters = ["atomworks[posebusters]"]
+catcif = ["atomworks[catcif]"]
 
 [project.urls]
 homepage = "https://rosettacommons.github.io/atomworks/latest/index.html"
@@ -105,13 +140,15 @@ aw = "atomworks_cli.__main__:main"
 
 # Build settings ----------------------------------------------------------------------
 [build-system]
-requires = ["hatchling", "hatch-vcs"]
+requires = ["hatchling"]
 build-backend = "hatchling.build"
 
-[tool.hatch.build]
-sources = ["src"]
+[tool.hatch.build.targets.wheel]
 packages = ["src/atomworks", "src/atomworks_cli"]
 
+[tool.hatch.build.targets.sdist]
+include = ["/src", "/README.md", "/LICENSE.md", "/pyproject.toml"]
+
 [tool.hatch.metadata]
 allow-direct-references = true
 dynamic = false  # optional – this disables dynamic metadata guessing
@@ -220,6 +257,7 @@ convention = "google"
 "docs/**/*.py" = ["E402"]               # Ignore forcing imports to be at the top of the file
 "docs/**/*.ipynb" = ["E402"]            # Ignore forcing imports to be at the top of the file
 "src/atomworks_cli/*" = ["B008"]        # Ignore function calls in argument defaults for Typer CLI
+"src/atomworks/ml/preprocessing/msa/colabfold_server.py" = ["N803", "N806"]  # Keep ColabFold's upstream variable names (ID, REDO, TIME, ...) for easy diffing
 
 # Allow one-letter variable names commonly used in scientific code.
 [tool.ruff.lint.pep8-naming]
@@ -238,6 +276,7 @@ testpaths = "tests"  # Only run tests in the tests directory (speeds up collecti
 norecursedirs = "docs *.egg-info .git .tox htmlcov"
 addopts = "--import-mode=importlib"
 pythonpath = ["src/atomworks", "tests"]
+env_files = ".env"  # Automatically load .env file before running tests (via pytest-dotenv)
 markers = [
     "requires_internet: marks tests that require an internet connection",
     "requires_pymol_remote: marks tests that require a PyMOL remote connection to run",

atomworks-3.0.0/src/atomworks/__init__.py

@@ -0,0 +1,88 @@
+"""Unified package for biological data I/O and machine learning.
+
+This package combines functionality from :mod:`atomworks.io` (I/O operations) and
+:mod:`atomworks.ml` (ML utilities) into a unified interface for biological data
+processing and machine learning.
+"""
+
+import importlib
+import importlib.metadata
+import logging
+import os
+import warnings
+
+try:
+    __version__ = importlib.metadata.version("atomworks")
+except ImportError:
+    __version__ = "unknown"
+
+
+# Hard-enforce biotite version compatibility by importing biotite directly.
+# Atomworks monkey-patches several private biotite internals that are sensitive to exact version alignment
+_REQUIRED_BIOTITE_VERSION = "1.6.0"
+try:
+    import biotite as _biotite_check
+except ImportError:
+    raise ImportError(
+        f"atomworks requires biotite=={_REQUIRED_BIOTITE_VERSION}, but biotite is not installed.\n"
+        f"    pip install 'biotite=={_REQUIRED_BIOTITE_VERSION}'"
+    ) from None
+if _biotite_check.__version__ != _REQUIRED_BIOTITE_VERSION:
+    raise ImportError(
+        f"atomworks requires biotite=={_REQUIRED_BIOTITE_VERSION}, "
+        f"but biotite {_biotite_check.__version__!r} is installed.\n"
+        f"    pip install 'biotite=={_REQUIRED_BIOTITE_VERSION}'"
+    )
+del _biotite_check
+
+# Global logging configuration
+logger = logging.getLogger("atomworks")
+_log_level = os.environ.get("ATOMWORKS_LOG_LEVEL", "WARNING").upper()
+logger.setLevel(_log_level)
+
+# Ensure that deprecation warnings are not repeated
+warnings.filterwarnings("once", category=DeprecationWarning)
+
+# Enforce strict biotite version — atomworks patches biotite internals
+import biotite  # noqa: E402
+
+_REQUIRED_BIOTITE_VERSION = "1.6.0"
+if biotite.__version__ != _REQUIRED_BIOTITE_VERSION:
+    raise RuntimeError(
+        f"atomworks requires biotite=={_REQUIRED_BIOTITE_VERSION}, "
+        f"but found biotite=={biotite.__version__}. "
+        f"Install the correct version: pip install biotite=={_REQUIRED_BIOTITE_VERSION}"
+    )
+
+# Apply monkey patching to extend AtomArray functionality
+from atomworks.biotite_patch import monkey_patch_biotite  # noqa: E402
+
+monkey_patch_biotite()
+
+
+# Import subpackages; also import annotators and Conditions to ensure they're registered
+from atomworks.io.utils import annotator as _annotator_io  # noqa: E402
+from atomworks.io.utils.standard_annotations import definitions as _standard_annotation_definitions  # noqa: E402
+
+from . import io  # noqa: E402
+
+# Make atomworks.ml an optional import
+try:
+    from atomworks.ml.conditions import definitions as _condition_definitions
+    from atomworks.ml.utils import annotator as _annotator_ml
+
+    from . import ml
+except ImportError:
+    pass
+
+# Re-export key functionality from subpackages for convenience
+# This maintains backward compatibility and provides a clean top-level API
+# Key I/O functionality
+from .io.parser import parse  # noqa: E402
+
+__all__ = [
+    "__version__",
+    "io",
+    "ml",
+    "parse",
+]