papyrus-scripts 2.1.2__tar.gz → 3.0.0__tar.gz

{papyrus_scripts-2.1.2 → papyrus_scripts-3.0.0}/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2021 OlivierBeq
-
-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.
+MIT License
+
+Copyright (c) 2021-2026 OlivierBeq
+
+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.

papyrus_scripts-3.0.0/PKG-INFO

@@ -0,0 +1,245 @@
+Metadata-Version: 2.4
+Name: papyrus_scripts
+Version: 3.0.0
+Summary: A collection of scripts to handle the Papyrus bioactivity dataset
+Author: Brandon J. Bongers, Willem Jespers
+Author-email: "Olivier J. M. Béquignon" <olivier.bequignon.maintainer@gmail.com>
+Maintainer-email: "Olivier J. M. Béquignon" <olivier.bequignon.maintainer@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/OlivierBeq/Papyrus-scripts
+Keywords: bioactivity data,QSAR,proteochemometrics,cheminformatics,modelling,machine learning
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: pandas
+Requires-Dist: polars
+Requires-Dist: pyarrow
+Requires-Dist: rdkit
+Requires-Dist: requests
+Requires-Dist: fake-useragent
+Requires-Dist: tqdm
+Requires-Dist: ipywidgets
+Requires-Dist: colorama; platform_system == "Windows"
+Requires-Dist: mordred
+Requires-Dist: scikit-learn
+Requires-Dist: xgboost
+Requires-Dist: pystow
+Requires-Dist: prodec
+Requires-Dist: defusedxml
+Provides-Extra: testing
+Requires-Dist: pytest; extra == "testing"
+Requires-Dist: parameterized; extra == "testing"
+Provides-Extra: dnn
+Requires-Dist: torch; extra == "dnn"
+Requires-Dist: skorch; extra == "dnn"
+Provides-Extra: subsim
+Requires-Dist: tables; extra == "subsim"
+Requires-Dist: FPSim2; extra == "subsim"
+Provides-Extra: gpu
+Requires-Dist: cupy-cuda12x[ctk]; extra == "gpu"
+Provides-Extra: simgpu
+Requires-Dist: papyrus_scripts[gpu,subsim]; extra == "simgpu"
+Provides-Extra: all
+Requires-Dist: papyrus_scripts[dnn,simgpu]; extra == "all"
+Dynamic: license-file
+
+<div align="center">
+  <img src="https://raw.githubusercontent.com/OlivierBeq/Papyrus-scripts/refs/heads/master/figures/logo/Papyrus_trnsp-bg.svg" alt="Papyrus logo" width="200">
+
+  # 📜 Papyrus-scripts
+
+  [![PyPI version](https://img.shields.io/pypi/v/papyrus-scripts.svg)](https://pypi.org/project/papyrus-scripts/)
+  [![Supported Python versions](https://img.shields.io/pypi/pyversions/papyrus-scripts.svg)](https://pypi.org/project/papyrus-scripts/)
+  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+  [![Tests](https://github.com/OlivierBeq/Papyrus-scripts/actions/workflows/ci.yml/badge.svg)](https://github.com/OlivierBeq/Papyrus-scripts/actions/workflows/ci.yml)
+  [![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)
+  [![DOI](https://img.shields.io/badge/DOI-10.1186/s13321--022--00672--x-blue)](https://doi.org/10.1186/s13321-022-00672-x)
+</div>
+
+A Python library for working with **Papyrus**, a large-scale curated dataset of bioactivity data aimed at machine learning applications. It handles downloading, versioning, and caching the dataset, and provides a fluent API to filter, search, and export exactly the subset you need — without ever loading the full dataset into memory.
+
+## ✨ Features
+
+- 🗂️ **Versioned dataset access** — download and cache specific Papyrus releases from Zenodo or 4TU, with automatic integrity checks.
+- 🔗 **Fluent filtering API** — chain quality, source, organism, protein-class and molecular filters over a lazy Polars pipeline; only what you keep gets materialized.
+- 🧬 **Proteins, structures & descriptors** — retrieve matching UniProt targets, 2D/3D compound structures, and precomputed molecular/protein descriptors in one call.
+- 🔍 **Similarity & substructure search** — build an indexed FPSim2/RDKit search database over the dataset, with CPU, GPU (CUDA), or auto-fallback search engines.
+- 🧠 **DNN-ready** — train PyTorch-based QSAR/PCM models on curated subsets, with y-scrambling and repeated seeds built in.
+- 💻 **CLI included** — download, convert and clean up dataset files without writing any Python.
+- 🔄 **Format-friendly** — transparent LZMA ↔ Gzip conversion and Parquet caching for tools that don't handle `.xz`.
+
+## 📦 Installation
+
+```bash
+pip install papyrus-scripts
+```
+
+<details>
+<summary><strong>⚠️ Troubleshooting <code>pip</code> installation</strong></summary>
+
+If you see `Defaulting to user installation because normal site-packages is not writeable` followed by import errors, reinstall with:
+```bash
+pip uninstall -y papyrus-scripts
+python -m pip install papyrus-scripts
+```
+</details>
+
+Optional extras enable additional functionality:
+
+| Extra | Enables |
+|---|---|
+| `papyrus-scripts[subsim]` | CPU similarity & substructure search (`tables`, `FPSim2`) |
+| `papyrus-scripts[gpu]` | GPU-accelerated similarity search (`cupy-cuda12x[ctk]`, bundles the CUDA 12.x toolkit) |
+| `papyrus-scripts[simgpu]` | CPU + GPU-accelerated similarity search (`subsim` + `gpu`) |
+| `papyrus-scripts[dnn]` | DNN model training (`torch`, `skorch`) |
+| `papyrus-scripts[all]` | Everything above |
+
+> **Note:** `openbabel` (needed only for FP2/FP3/FP4 fingerprints) must be installed via conda-forge, not pip, when used alongside RDKit/FPSim2/cupy in the same environment: `conda install -c conda-forge openbabel`.
+>
+> **Note:** the `gpu` extra pins `cupy-cuda12x[ctk]`, whose `ctk` extra pulls in the CUDA 12.x toolkit as a pip package — no separate toolkit install needed, only an NVIDIA driver compatible with CUDA 12.x.
+
+## 🛠️ Requirements
+
+- Python 3.11+
+- [RDKit](https://www.rdkit.org/docs/Install.html)
+
+## 💡 Usage
+
+### Quickstart: the object-oriented API
+
+The recommended way to interact with the dataset. It downloads and caches data automatically as needed.
+
+```python
+from papyrus_scripts import PapyrusDataset
+
+dataset = PapyrusDataset(version='2024.09.2', plusplus=True)
+
+filtered = (dataset
+            .keep_source(['chembl', 'sharma'])
+            .keep_quality('high'))
+
+df = filtered.to_dataframe()
+proteins = filtered.proteins().to_dataframe()
+```
+
+### Downloading data: the CLI
+
+```bash
+# Download Papyrus++ bioactivities & targets for the latest version
+papyrus download -V latest
+
+# Download the full (all-quality) dataset with all precomputed descriptors for a specific revision
+papyrus download -V 2022.11.3 --more -d all
+
+# Download Papyrus++ data & compound structures for two versions
+papyrus download -V 2022.11.3 -V 2022.04.2 -S
+
+papyrus download --help
+```
+
+By default, data is downloaded to [pystow](https://github.com/cthoyt/pystow)'s home directory; override it with `-o`.
+
+<details>
+<summary><strong>Legacy functional API</strong></summary>
+
+```python
+from papyrus_scripts import (read_papyrus, read_protein_set,
+                              keep_quality, keep_source, consume_chunks)
+
+chunks = read_papyrus(version='2024.09.2', plusplus=True, chunksize=1_000_000)
+proteins = read_protein_set(version='2024.09.2')
+
+filtered = keep_quality(keep_source(chunks, source=['chembl', 'sharma']), min_quality='high')
+df = consume_chunks(filtered)
+```
+</details>
+
+<details>
+<summary><strong>Similarity & substructure search</strong></summary>
+
+```python
+from papyrus_scripts.subsim_search import FPSubSim2
+
+fpss = FPSubSim2()
+fpss.create_from_papyrus(version='2024.09.2', njobs=-1)  # builds a search database using all CPU cores
+
+# cuda=False (default, CPU) | True (GPU, raises if unavailable) | 'auto' (GPU with CPU fallback)
+engine = fpss.get_similarity_lib(cuda='auto')
+hits = engine.similarity('CCO', threshold=0.7)
+
+sub_lib = fpss.get_substructure_lib()
+matches = sub_lib.substructure('c1ccccc1')
+```
+</details>
+
+## 📊 Dataset versions
+
+Papyrus releases are hosted on Zenodo:
+
+| Papyrus version | Revisions | Legacy alias | ChEMBL version | Zenodo |
+|:---:|:---:|:---:|:---:|:---:|
+| **2022.04** | 2 | 05.4 | 29 | [link](https://zenodo.org/records/10943992) |
+| **2022.08** | 3 | 05.5 | 30 | [link](https://zenodo.org/records/7019873) |
+| **2022.11** | 4 | 05.6 | 31 | [link](https://zenodo.org/records/7373213) |
+| **2024.09** | 2 | 05.7 | 34 | [link](https://zenodo.org/records/13787633) |
+
+> **Note:** for machine learning use cases, we recommend the datasets without stereochemistry (files marked "2D" and/or "without_stereochemistry").
+
+## ⚙️ Advanced utilities
+
+<details>
+<summary><strong>Compression conversion</strong></summary>
+
+Data is distributed as LZMA-compressed files (`.xz`), which some tools (e.g. Pipeline Pilot) don't support. Convert to Gzip (or back) without manually decompressing:
+
+```bash
+papyrus convert -v latest
+```
+</details>
+
+<details>
+<summary><strong>Removing downloaded data</strong></summary>
+
+```bash
+papyrus clean --remove_root
+```
+```python
+from papyrus_scripts import remove_papyrus
+
+remove_papyrus(papyrus_root=True)
+```
+</details>
+
+## 📚 Learn more
+
+- [`simple_examples.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/simple_examples.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/simple_examples.ipynb)
+- [`matchRCSB.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/matchRCSB.ipynb) — matching Papyrus data against the Protein Data Bank [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/matchRCSB.ipynb)
+- [`advanced_querying.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/advanced_querying.ipynb)
+- To reproduce the models, extraction pipeline and visualizations from the original publication, see [Papyrus-modelling](https://github.com/OlivierBeq/Papyrus-modelling).
+
+## 🖋️ Citation
+
+If you use `papyrus-scripts` or the Papyrus dataset in your research, please cite:
+
+```bibtex
+@article{Bequignon2023Papyrus,
+  title={Papyrus - A large scale curated dataset aimed at bioactivity predictions},
+  author={B{\'e}quignon, Olivier J.M. and Bongers, Bart J. and Jespers, Willem and IJzerman, Adriaan P. and van de Water, Bob and van Westen, Gerard J.P.},
+  journal={Journal of Cheminformatics},
+  volume={15},
+  number={3},
+  year={2023},
+  doi={10.1186/s13321-022-00672-x}
+}
+```
+
+## 📄 License
+
+This project is licensed under the [MIT License](LICENSE).

papyrus_scripts-3.0.0/README.md

@@ -0,0 +1,193 @@
+<div align="center">
+  <img src="https://raw.githubusercontent.com/OlivierBeq/Papyrus-scripts/refs/heads/master/figures/logo/Papyrus_trnsp-bg.svg" alt="Papyrus logo" width="200">
+
+  # 📜 Papyrus-scripts
+
+  [![PyPI version](https://img.shields.io/pypi/v/papyrus-scripts.svg)](https://pypi.org/project/papyrus-scripts/)
+  [![Supported Python versions](https://img.shields.io/pypi/pyversions/papyrus-scripts.svg)](https://pypi.org/project/papyrus-scripts/)
+  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+  [![Tests](https://github.com/OlivierBeq/Papyrus-scripts/actions/workflows/ci.yml/badge.svg)](https://github.com/OlivierBeq/Papyrus-scripts/actions/workflows/ci.yml)
+  [![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)
+  [![DOI](https://img.shields.io/badge/DOI-10.1186/s13321--022--00672--x-blue)](https://doi.org/10.1186/s13321-022-00672-x)
+</div>
+
+A Python library for working with **Papyrus**, a large-scale curated dataset of bioactivity data aimed at machine learning applications. It handles downloading, versioning, and caching the dataset, and provides a fluent API to filter, search, and export exactly the subset you need — without ever loading the full dataset into memory.
+
+## ✨ Features
+
+- 🗂️ **Versioned dataset access** — download and cache specific Papyrus releases from Zenodo or 4TU, with automatic integrity checks.
+- 🔗 **Fluent filtering API** — chain quality, source, organism, protein-class and molecular filters over a lazy Polars pipeline; only what you keep gets materialized.
+- 🧬 **Proteins, structures & descriptors** — retrieve matching UniProt targets, 2D/3D compound structures, and precomputed molecular/protein descriptors in one call.
+- 🔍 **Similarity & substructure search** — build an indexed FPSim2/RDKit search database over the dataset, with CPU, GPU (CUDA), or auto-fallback search engines.
+- 🧠 **DNN-ready** — train PyTorch-based QSAR/PCM models on curated subsets, with y-scrambling and repeated seeds built in.
+- 💻 **CLI included** — download, convert and clean up dataset files without writing any Python.
+- 🔄 **Format-friendly** — transparent LZMA ↔ Gzip conversion and Parquet caching for tools that don't handle `.xz`.
+
+## 📦 Installation
+
+```bash
+pip install papyrus-scripts
+```
+
+<details>
+<summary><strong>⚠️ Troubleshooting <code>pip</code> installation</strong></summary>
+
+If you see `Defaulting to user installation because normal site-packages is not writeable` followed by import errors, reinstall with:
+```bash
+pip uninstall -y papyrus-scripts
+python -m pip install papyrus-scripts
+```
+</details>
+
+Optional extras enable additional functionality:
+
+| Extra | Enables |
+|---|---|
+| `papyrus-scripts[subsim]` | CPU similarity & substructure search (`tables`, `FPSim2`) |
+| `papyrus-scripts[gpu]` | GPU-accelerated similarity search (`cupy-cuda12x[ctk]`, bundles the CUDA 12.x toolkit) |
+| `papyrus-scripts[simgpu]` | CPU + GPU-accelerated similarity search (`subsim` + `gpu`) |
+| `papyrus-scripts[dnn]` | DNN model training (`torch`, `skorch`) |
+| `papyrus-scripts[all]` | Everything above |
+
+> **Note:** `openbabel` (needed only for FP2/FP3/FP4 fingerprints) must be installed via conda-forge, not pip, when used alongside RDKit/FPSim2/cupy in the same environment: `conda install -c conda-forge openbabel`.
+>
+> **Note:** the `gpu` extra pins `cupy-cuda12x[ctk]`, whose `ctk` extra pulls in the CUDA 12.x toolkit as a pip package — no separate toolkit install needed, only an NVIDIA driver compatible with CUDA 12.x.
+
+## 🛠️ Requirements
+
+- Python 3.11+
+- [RDKit](https://www.rdkit.org/docs/Install.html)
+
+## 💡 Usage
+
+### Quickstart: the object-oriented API
+
+The recommended way to interact with the dataset. It downloads and caches data automatically as needed.
+
+```python
+from papyrus_scripts import PapyrusDataset
+
+dataset = PapyrusDataset(version='2024.09.2', plusplus=True)
+
+filtered = (dataset
+            .keep_source(['chembl', 'sharma'])
+            .keep_quality('high'))
+
+df = filtered.to_dataframe()
+proteins = filtered.proteins().to_dataframe()
+```
+
+### Downloading data: the CLI
+
+```bash
+# Download Papyrus++ bioactivities & targets for the latest version
+papyrus download -V latest
+
+# Download the full (all-quality) dataset with all precomputed descriptors for a specific revision
+papyrus download -V 2022.11.3 --more -d all
+
+# Download Papyrus++ data & compound structures for two versions
+papyrus download -V 2022.11.3 -V 2022.04.2 -S
+
+papyrus download --help
+```
+
+By default, data is downloaded to [pystow](https://github.com/cthoyt/pystow)'s home directory; override it with `-o`.
+
+<details>
+<summary><strong>Legacy functional API</strong></summary>
+
+```python
+from papyrus_scripts import (read_papyrus, read_protein_set,
+                              keep_quality, keep_source, consume_chunks)
+
+chunks = read_papyrus(version='2024.09.2', plusplus=True, chunksize=1_000_000)
+proteins = read_protein_set(version='2024.09.2')
+
+filtered = keep_quality(keep_source(chunks, source=['chembl', 'sharma']), min_quality='high')
+df = consume_chunks(filtered)
+```
+</details>
+
+<details>
+<summary><strong>Similarity & substructure search</strong></summary>
+
+```python
+from papyrus_scripts.subsim_search import FPSubSim2
+
+fpss = FPSubSim2()
+fpss.create_from_papyrus(version='2024.09.2', njobs=-1)  # builds a search database using all CPU cores
+
+# cuda=False (default, CPU) | True (GPU, raises if unavailable) | 'auto' (GPU with CPU fallback)
+engine = fpss.get_similarity_lib(cuda='auto')
+hits = engine.similarity('CCO', threshold=0.7)
+
+sub_lib = fpss.get_substructure_lib()
+matches = sub_lib.substructure('c1ccccc1')
+```
+</details>
+
+## 📊 Dataset versions
+
+Papyrus releases are hosted on Zenodo:
+
+| Papyrus version | Revisions | Legacy alias | ChEMBL version | Zenodo |
+|:---:|:---:|:---:|:---:|:---:|
+| **2022.04** | 2 | 05.4 | 29 | [link](https://zenodo.org/records/10943992) |
+| **2022.08** | 3 | 05.5 | 30 | [link](https://zenodo.org/records/7019873) |
+| **2022.11** | 4 | 05.6 | 31 | [link](https://zenodo.org/records/7373213) |
+| **2024.09** | 2 | 05.7 | 34 | [link](https://zenodo.org/records/13787633) |
+
+> **Note:** for machine learning use cases, we recommend the datasets without stereochemistry (files marked "2D" and/or "without_stereochemistry").
+
+## ⚙️ Advanced utilities
+
+<details>
+<summary><strong>Compression conversion</strong></summary>
+
+Data is distributed as LZMA-compressed files (`.xz`), which some tools (e.g. Pipeline Pilot) don't support. Convert to Gzip (or back) without manually decompressing:
+
+```bash
+papyrus convert -v latest
+```
+</details>
+
+<details>
+<summary><strong>Removing downloaded data</strong></summary>
+
+```bash
+papyrus clean --remove_root
+```
+```python
+from papyrus_scripts import remove_papyrus
+
+remove_papyrus(papyrus_root=True)
+```
+</details>
+
+## 📚 Learn more
+
+- [`simple_examples.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/simple_examples.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/simple_examples.ipynb)
+- [`matchRCSB.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/matchRCSB.ipynb) — matching Papyrus data against the Protein Data Bank [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/matchRCSB.ipynb)
+- [`advanced_querying.ipynb`](https://github.com/OlivierBeq/Papyrus-scripts/blob/master/notebook_examples/advanced_querying.ipynb)
+- To reproduce the models, extraction pipeline and visualizations from the original publication, see [Papyrus-modelling](https://github.com/OlivierBeq/Papyrus-modelling).
+
+## 🖋️ Citation
+
+If you use `papyrus-scripts` or the Papyrus dataset in your research, please cite:
+
+```bibtex
+@article{Bequignon2023Papyrus,
+  title={Papyrus - A large scale curated dataset aimed at bioactivity predictions},
+  author={B{\'e}quignon, Olivier J.M. and Bongers, Bart J. and Jespers, Willem and IJzerman, Adriaan P. and van de Water, Bob and van Westen, Gerard J.P.},
+  journal={Journal of Cheminformatics},
+  volume={15},
+  number={3},
+  year={2023},
+  doi={10.1186/s13321-022-00672-x}
+}
+```
+
+## 📄 License
+
+This project is licensed under the [MIT License](LICENSE).

papyrus_scripts-3.0.0/pyproject.toml

@@ -0,0 +1,173 @@
+[build-system]
+requires = ["setuptools>=77.0.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "papyrus_scripts"
+dynamic = ["version"]
+description = "A collection of scripts to handle the Papyrus bioactivity dataset"
+requires-python = ">=3.11"
+readme = { file = "README.md", content-type = "text/markdown" }
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Olivier J. M. Béquignon", email = "olivier.bequignon.maintainer@gmail.com" },
+    { name = "Brandon J. Bongers"},
+    { name = "Willem Jespers"},
+
+]
+maintainers = [
+    { name = "Olivier J. M. Béquignon", email = "olivier.bequignon.maintainer@gmail.com" },
+]
+classifiers = [
+    "Development Status :: 2 - Pre-Alpha",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+keywords = [
+    "bioactivity data",
+    "QSAR",
+    "proteochemometrics",
+    "cheminformatics",
+    "modelling",
+    "machine learning",
+]
+dependencies = [
+    "click",
+    "numpy>=2.0.0",
+    "pandas",
+    "polars",
+    "pyarrow",
+    "rdkit",
+    "requests",
+    "fake-useragent",
+    "tqdm",
+    "ipywidgets",
+    "colorama; platform_system == 'Windows'",
+    "mordred",
+    "scikit-learn",
+    "xgboost",
+    "pystow",
+    "prodec",
+    "defusedxml",
+]
+
+[project.urls]
+Homepage = "https://github.com/OlivierBeq/Papyrus-scripts"
+
+[project.scripts]
+papyrus = "papyrus_scripts.cli:main"
+
+[project.optional-dependencies]
+testing = [
+    "pytest",
+    "parameterized",
+]
+dnn = [
+    "torch",
+    "skorch",
+]
+subsim = [
+    "tables",
+    "FPSim2",
+]
+gpu = [
+    "cupy-cuda12x[ctk]",
+]
+simgpu = [
+    "papyrus_scripts[subsim,gpu]"
+]
+all = [
+    "papyrus_scripts[dnn,simgpu]"
+]
+
+[tool.coverage.run]
+source = ["src/papyrus_scripts"]
+omit = ["*/__main__.py"]
+
+[tool.coverage.report]
+fail_under = 95
+exclude_also = [
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]
+
+[tool.setuptools.dynamic]
+version = { attr = "papyrus_scripts.__version__" }
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"*" = ["*.json"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py311"
+extend-exclude = ["tests/fixtures"]
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle errors (flake8)
+    "W",    # pycodestyle warnings (flake8)
+    "F",    # pyflakes (flake8)
+    "I",    # import sorting (isort, flake8-isort)
+    "N",    # naming conventions (pep8-naming)
+    "D",    # docstring conventions (pydocstyle, flake8-docstrings)
+    "UP",   # pyupgrade
+    "B",    # bugbear (flake8-bugbear)
+    "A",    # shadowed builtins (flake8-builtins)
+    "COM",  # trailing commas (flake8-commas)
+    "C4",   # comprehensions (flake8-comprehensions)
+    "T20",  # print statements (flake8-print)
+    "S",    # security (flake8-bandit)
+]
+ignore = [
+    "S310",  # URL open with a variable scheme (blanket-ignored under flake8 too)
+    "UP009", # UTF-8 coding declaration: kept deliberately in every file, do not strip
+    "N999",  # module naming: renaming existing public modules (IO.py, matchRCSB.py, ...) would break imports
+    "N802",  # function/method naming: mirrors external APIs (torch.autograd.Variable,
+             # RDKit's GetMatches, unittest's assertX convention), not a mistake
+    "N803",  # argument naming: mirrors sklearn/RDKit conventions (X, y, nBits, isQuery, is3D, ...)
+    "N806",  # in-function variable naming: CHUNKSIZE/_ROOT_FTYPES-style caps used for local constants
+    "N812",  # import aliasing: torch's own convention (`import torch as T`, `functional as F`)
+    "T201",  # print(): this is a CLI tool and training loop that deliberately prints progress/output
+    "A001",  # builtin-shadowing variables: descriptive local names (format, input, id) used harmlessly
+    "A002",  # same, for function arguments
+    "C408",  # dict(...) calls: used deliberately for readability when building keyword-style dicts
+    "E701",  # multiple statements on one line: used for compact optional-dependency stub classes
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = [
+    "S101",  # assert usage is expected in tests
+    "D",     # tests are not held to docstring conventions
+]
+"src/papyrus_scripts/__init__.py" = [
+    "F401",  # this is a barrel file: imports are re-exports of the public API, not unused
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["papyrus_scripts", "tests"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "pep257"
+
+[tool.mypy]
+python_version = "3.11"
+exclude = ["tests/fixtures", "build", "dist"]
+
+[[tool.mypy.overrides]]
+module = ["rdkit", "rdkit.*"]
+follow_imports = "skip"
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = [
+    "pandas.*", "requests.*", "tqdm.*", "sklearn.*", "prodec.*", "skorch.*",
+    "defusedxml.*", "scipy.*", "mordred.*", "xgboost.*", "pystow.*",
+    "fake_useragent.*", "FPSim2.*", "cupy.*", "tables.*", "openbabel.*",
+]
+ignore_missing_imports = true

papyrus_scripts-3.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+