WIP cleaning up

datamol-io · Oct 27, 2023 · 2fcacd1 · 2fcacd1
1 parent 77a88be
commit 2fcacd1
Show file tree

Hide file tree

Showing 15 changed files with 119 additions and 215 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/.authors.yml b/.authors.yml
diff --git a/.mailmap b/.mailmap
diff --git a/AUTHORS.rst b/AUTHORS.rst
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
diff --git a/README.md b/README.md
@@ -1,4 +1,3 @@
-
 <h1 align="center">  :safety_vest: SAFE </h1>
 <h4 align="center"><b>S</b>equential <b>A</b>ttachment-based <b>F</b>ragment <b>E</b>mbedding (SAFE) is a novel molecular line notation that represents molecules as an unordered sequence of fragment blocks to improve molecule design using generative models.</h4>
 
@@ -9,13 +8,13 @@
 </br>
 
 <p align="center">
-    <a href="" target="_blank">
+    <a href="https://arxiv.org/pdf/2310.10773.pdf" target="_blank">
       Paper
   </a> |
-  <a href="https://maclandrol.github.io/safe/" target="_blank">
+  <a href="https://safe-docs.datamol.io/" target="_blank">
       Docs
   </a> |
-  <a href="#" target="_blank">
+  <a href="https://huggingface.co/datamol-io/safe" target="_blank">
     🤗 Model
   </a>
 </p>
@@ -24,28 +23,30 @@
 
 </br>
 
-[![PyPI](https://img.shields.io/pypi/v/safe)](https://pypi.org/project/safe/)
-[![Version](https://img.shields.io/pypi/pyversions/safe)](https://pypi.org/project/safe/)
-[![Code license](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/maclandrol/safe/blob/main/LICENSE)
-[![Data License](https://img.shields.io/badge/Data%20License-CC%20BY%204.0-red.svg)](https://github.com/maclandrol/safe/blob/main/DATA_LICENSE)
-[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-blue.svg)](https://github.com/maclandrol/safe/graphs/commit-activity)
-[![arXiv](https://img.shields.io/badge/arXiv-1234.56789-b31b1b.svg)](https://arxiv.org/abs/1234.56789)
-[![test](https://github.com/maclandrol/safe/actions/workflows/test.yml/badge.svg)](https://github.com/maclandrol/safe/actions/workflows/test.yml)
-
-## 🆕 News
-- \[**August 2023**\] We've released xxx
-
+[![PyPI](https://img.shields.io/pypi/v/safe-mol)](https://pypi.org/project/safe-mol/)
+[![Conda](https://img.shields.io/conda/v/conda-forge/safe-mol?label=conda&color=success)](https://anaconda.org/conda-forge/safe-mol)
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/safe-mol)](https://pypi.org/project/safe-mol/)
+[![Conda](https://img.shields.io/conda/dn/conda-forge/safe-mol)](https://anaconda.org/conda-forge/safe-mol)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/safe-mol)](https://pypi.org/project/safe-mol/)
+[![Code license](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)](https://github.com/datamol-io/safe/blob/main/LICENSE)
+[![Data License](https://img.shields.io/badge/Data%20License-CC%20BY%204.0-red.svg)](https://github.com/datamol-io/safe/blob/main/DATA_LICENSE)[![GitHub Repo stars](https://img.shields.io/github/stars/datamol-io/safe)](https://github.com/datamol-io/safe/stargazers)
+[![GitHub Repo stars](https://img.shields.io/github/forks/datamol-io/safe)](https://github.com/datamol-io/safe/network/members)
+[![test](https://github.com/datamol-io/safe/actions/workflows/test.yml/badge.svg)](https://github.com/datamol-io/safe/actions/workflows/test.yml)
+[![release](https://github.com/datamol-io/safe/actions/workflows/release.yml/badge.svg)](https://github.com/datamol-io/safe/actions/workflows/release.yml)
+[![code-check](https://github.com/datamol-io/safe/actions/workflows/code-check.yml/badge.svg)](https://github.com/datamol-io/safe/actions/workflows/code-check.yml)
+[![doc](https://github.com/datamol-io/safe/actions/workflows/doc.yml/badge.svg)](https://github.com/datamol-io/safe/actions/workflows/doc.yml)
+[![arXiv](https://img.shields.io/badge/arXiv-2310.10773-b31b1b.svg)](https://arxiv.org/pdf/2310.10773.pdf)
 
 ## Overview of SAFE
 
-SAFE *is the* deep learning molecular representation. It's an encoding leveraging a peculiarity in the decoding schemes of SMILES, to allow representation of molecules as contiguous sequence of connected fragment. SAFE strings are valid SMILES string, and thus are able to preserve the same amount of information.  The intuitive representation of molecules as unordered sequence of connected fragments gretly simplify the following tasks often encoutered in molecular design:
+SAFE _is the_ deep learning molecular representation. It's an encoding leveraging a peculiarity in the decoding schemes of SMILES, to allow representation of molecules as contiguous sequence of connected fragment. SAFE strings are valid SMILES string, and thus are able to preserve the same amount of information. The intuitive representation of molecules as unordered sequence of connected fragments gretly simplify the following tasks often encoutered in molecular design:
 
-- *de novo* design
+- _de novo_ design
 - superstructure generation
 - scaffold decoration
 - motif extension
 - linker generation
-- scaffold morphing. 
+- scaffold morphing.
 
 The construction of a SAFE strings requires definition a molecular fragmentation algorithm. By default, we use [BRICS], but any other fragmentation algorithm can be used. The image below illustrate the process of building a SAFE string. The resulting string is a valid SMILES that can be read by [datamol](https://github.com/datamol-io/datamol) or [RDKit](https://github.com/rdkit/rdkit).
 
@@ -54,63 +55,41 @@ The construction of a SAFE strings requires definition a molecular fragmentation
     <img src="docs/assets/safe-construction.svg" width="100%">
 </div>
 
-
-
 ### Installation
 
-You can install `safe` using pip, when the package is public
+You can install `safe` using pip:
 
 ```bash
-pip install safe-mol 
+pip install safe-mol
 ```
 
-
 You can use conda/mamba. Ask @maclandrol for credentials to the conda forge or for a token
 
 ```bash
-mamba install -c invivoai safe
-```
-
-
-Alternatively clone this repo, install the dependencies, install `safe` locally and you are good to go:
-
-
-```bash
-git clone https://github.com/maclandrol/safe.git
-cd safe
-mamba env create -f env.yml -n "safe-space" # :)
-pip install -e .
+mamba install -c conda-forge safe-mol
 ```
 
 `safe` mostly depends on [transformers](https://huggingface.co/docs/transformers/index) and [datasets](https://huggingface.co/docs/datasets/index). Please see the [env.yml](./env.yml) file for a complete list of dependencies.
 
-
 ### Datasets and Models
 
-We provided a pretained GPT2 model (XX M parameters) using the SAFE molecular representation that has been trained on 1.1 billion molecules from Unichem (0.1B) + Zinc (1B): 
-
-- *Safe-XXM* [maclandrol/safe-XXM]()
+We provided a pretained GPT2 model (XX M parameters) using the SAFE molecular representation that has been trained on 1.1 billion molecules from Unichem (0.1B) + Zinc (1B):
 
+- _Safe-XXM_ TODO
 
 ## Usage
 
-Please refer to the [documentation](), which contains a thorough tutorial for getting started with ``safe`` and detailed descriptions of the functions provided. 
-
-In particular, see the following tutorials:
-- xxx
-- xxx
-
+Please refer to the [documentation](https://safe-docs.datamol.io/), which contains tutorials for getting started with `safe` and detailed descriptions of the functions provided.
 
 ### API
 
 We summarize some key functions provided by the `safe` package below.
 
-| Function        | Description                                                                                                                                                                                             |
-| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ``safe.encode`` | Translates a SMILES string into its corresponding SAFE string.                                                                                                                                          |
-| ``safe.decode`` | Translates a SAFE string into its corresponding SMILES string. The SAFE decoder just augment RDKit's `Chem.MolFromSmiles` with an optional correction argument to take care of missing hydrogens bonds. |
-| ``safe.split``  | Tokenizes a SAFE string to build a generative model.                                                                                                                                                    |
-
+| Function      | Description                                                                                                                                                                                             |
+| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `safe.encode` | Translates a SMILES string into its corresponding SAFE string.                                                                                                                                          |
+| `safe.decode` | Translates a SAFE string into its corresponding SMILES string. The SAFE decoder just augment RDKit's `Chem.MolFromSmiles` with an optional correction argument to take care of missing hydrogens bonds. |
+| `safe.split`  | Tokenizes a SAFE string to build a generative model.                                                                                                                                                    |
 
 ### Examples
 
@@ -126,7 +105,7 @@ try:
     ibuprofen_sf = safe.encode(ibuprofen)  # [C][=C][C][=C][C][=C][Ring1][=Branch1]
     ibuprofen_smi = safe.decode(ibuprofen_sf, canonical=True)  # CC(Cc1ccc(cc1)C(C(=O)O)C)C
 except safe.EncoderError:
-    pass 
+    pass
 except safe.DecoderError:
     pass
 
@@ -136,7 +115,7 @@ ibuprofen_tokens = list(safe.split(ibuprofen_sf))
 
 ### Training a new models
 
-A command line interface is available to train a new model, please run ```safe-train --help```
+A command line interface is available to train a new model, please run `safe-train --help`
 
 For example:
 
@@ -155,28 +134,42 @@ safe-train --config <path to config> \
     --max_steps 5
 ```
 
-
-## Changelog
-See the latest changelogs at [CHANGELOG.rst](./CHANGELOG.rst).
-
 ## References
-If you use this repository, please cite the following related paper:
 
-```
-@article{,
-  title={Gotta be SAFE: a new framework for molecular design.},
-  author={},
-  journal={},
-  year={2023}
+If you use this repository, please cite the following related [paper](https://arxiv.org/abs/2310.10773#):
+
+```bib
+@misc{noutahi2023gotta,
+      title={Gotta be SAFE: A New Framework for Molecular Design},
+      author={Emmanuel Noutahi and Cristian Gabellini and Michael Craig and Jonathan S. C Lim and Prudencio Tossou},
+      year={2023},
+      eprint={2310.10773},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
 }
 ```
 
 ## License
 
-Please note that all data and model weights of **SAFE** are exclusively licensed for research purposes. The accompanying dataset is licensed under CC BY 4.0, which permits solely non-commercial usage. See [DATA_LICENSE](DATA_LICENSE) for details.
+Note that all data and model weights of **SAFE** are exclusively licensed for research purposes. The accompanying dataset is licensed under CC BY 4.0, which permits solely non-commercial usage. See [DATA_LICENSE](DATA_LICENSE) for details.
 
 This code base is licensed under the Apache-2.0 license. See [LICENSE](LICENSE) for details.
 
-## Maintainers
+## Development lifecycle
 
-- @maclandrol
+### Setup dev environment
+
+```bash
+mamba create -n safe -f env.yml
+mamba activate safe
+
+pip install --no-deps -e .
+```
+
+### Tests
+
+You can run tests locally with:
+
+```bash
+pytest
+```
diff --git a/docs/.DS_Store b/docs/.DS_Store
diff --git a/docs/index.md b/docs/index.md
@@ -10,7 +10,7 @@
     <a href="" target="_blank">
       Paper
   </a> |
-  <a href="https://github.com/valence-labs/safe/" target="_blank">
+  <a href="https://github.com/datamol-io/safe/" target="_blank">
       Github
   </a> |
   <a href="#" target="_blank">
@@ -34,7 +34,7 @@ SAFE *is the* deep learning molecular representation. It's an encoding leveragin
 - scaffold decoration
 - motif extension
 - linker generation
-- scaffold morphing. 
+- scaffold morphing.
 
 The construction of a SAFE strings requires definition a molecular fragmentation algorithm. By default, we use [BRICS], but any other fragmentation algorithm can be used. The image below illustrate the process of building a SAFE string. The resulting string is a valid SMILES that can be read by [datamol](https://github.com/datamol-io/datamol) or [RDKit](https://github.com/rdkit/rdkit).
 
@@ -67,14 +67,14 @@ pip install -e .
 
 ### Datasets and Models
 
-We provided a pretained GPT2 model (XXM parameters) using the SAFE molecular representation that has been trained on 1.1 billion molecules from Unichem (0.1B) + Zinc (1B): 
+We provided a pretained GPT2 model (XXM parameters) using the SAFE molecular representation that has been trained on 1.1 billion molecules from Unichem (0.1B) + Zinc (1B):
 
 - *Safe-XXM* [maclandrol/safe-XXM]()
 
 
 ### Usage
 
-To get started with SAFE, please see the tutorials: 
+To get started with SAFE, please see the tutorials:
 - xxx
 - xxx
 

diff --git a/env.yml b/env.yml
@@ -1,27 +1,29 @@
 channels:
   - conda-forge
+
 dependencies:
-  - python >=3.8
+  - python >=3.9
   - pip
   - tqdm
-  - joblib
   - loguru
+  - typer
+
+  # Scientific
   - datamol
   - numpy
   - pytorch >=2.0
   - transformers
-  - optimum
   - datasets
-  - typer
   - tokenizers
-  - sentencepiece
   - accelerate
   - evaluate
   - wandb
-  - universal_pathlib
   - huggingface_hub
   - deepspeed
 
+  # Optional
+  - deepspeed
+
   # dev
   - black >=23
   - ruff
@@ -31,13 +33,6 @@ dependencies:
   - nbconvert
   - ipywidgets
 
-  # Releasing tools
-  - twine
-  - build
-  - setuptools-scm
-  - rever >=0.4.5
-  - conda-smithy
-
   # Doc
   - mkdocs
   - mkdocs-material >=7.1.1

diff --git a/expts/README.md b/expts/README.md
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -1,8 +1,8 @@
 site_name: "SAFE"
 site_description: "Gotta be SAFE: a new framework for molecular design"
-site_url: "https://github.com/valence-labs/safe"
-repo_url: "https://github.com/valence-labs/safe"
-repo_name: "valence-labs/safe"
+site_url: "https://github.com/datamol-io/safe"
+repo_url: "https://github.com/datamol-io/safe"
+repo_name: "datamol-io/safe"
 copyright: Copyright 2023 Valence Labs
 
 remote_branch: "gh-pages"
@@ -87,8 +87,8 @@ extra:
 
   social:
     - icon: fontawesome/brands/github
-      link: https://github.com/valence-labs
+      link: https://github.com/datamol-io
     - icon: fontawesome/brands/twitter
-      link: https://twitter.com/ENoutahi
+      link: https://twitter.com/datamol_io
     - icon: fontawesome/brands/python
       link: https://pypi.org/project/safe-mol/
diff --git a/news/TEMPLATE.rst b/news/TEMPLATE.rst