Merge branch 'dev' into feature-blackbox-rosetta

.github/workflows/python-tox-testing-including-conda.yml → .github/workflows/python-tox-testing-base.yml

@@ -1,6 +1,9 @@
-name: Tests on poli (dev, conda, python 3.9)
+name: poli base (conda, py3.9)
 
-on: [push]
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
 
 jobs:
   build-linux:
@@ -24,6 +27,6 @@ jobs:
     - name: Test linting with tox
       run: |
         tox -c tox.ini -e lint
-    - name: Test poli-base with tox (ignoring RaSP)
+    - name: Test basic behaviors of poli with tox and pytest
       run: |
-        tox -c tox.ini -e poli-base-py39 -- --ignore=src/poli/tests/registry/proteins/test_rasp.py
+        tox -c tox.ini -e poli-base-py39

.github/workflows/python-tox-testing-dockstring-env.yml

@@ -0,0 +1,29 @@
+name: poli dockstring (conda, py3.9)
+
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test dockstring-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-dockstring-py39

.github/workflows/python-tox-testing-lambo-env.yml

@@ -0,0 +1,29 @@
+name: poli lambo (conda, py3.9)
+
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test lambo-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-lambo-py39

.github/workflows/python-tox-testing-protein-env.yml

@@ -0,0 +1,29 @@
+name: poli protein (conda, py3.9)
+
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test protein-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-protein-py39

.github/workflows/python-tox-testing-rmf-env.yml

@@ -0,0 +1,29 @@
+name: poli rmf (conda, py3.9)
+
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test rmf-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-rmf-py39

.github/workflows/python-tox-testing-tdc-env.yml

@@ -0,0 +1,29 @@
+name: poli tdc (conda, py3.9)
+
+on:
+  push:
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.9'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test PyTDC-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-tdc-py39

.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+        exclude: '.*\.pdb$'
+    -   id: check-yaml
+    -   id: check-added-large-files
+-   repo: https://github.com/psf/black
+    rev: 24.1.1
+    hooks:
+    -   id: black
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.13.2
+    hooks:
+    -   id: isort
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.5.5
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]

CITATION.cff

@@ -8,6 +8,6 @@ authors:
 - family-names: "Michael"
   given-names: "Richard"
 title: "poli: a libary of discrete sequence objectives"
-version: 0.1.0
+version: 0.2.1
 date-released: 2024-01-23
 url: "https://github.com/MachineLearningLifeScience/poli"

CONTRIBUTING.md

@@ -3,48 +3,65 @@
 ![Linting: black](https://img.shields.io/badge/Linting-black-black)
 ![Testing: pytest](https://img.shields.io/badge/Testing-pytest-blue)
 ![Testing: tox](https://img.shields.io/badge/Testing-tox-blue)
-![Main branch: black](https://img.shields.io/badge/Pull_request_to-dev-blue)
+![Main branch: dev](https://img.shields.io/badge/Pull_request_to-dev-blue)
 
 This note details how to contribute to `poli`.
 
 ## Forking and making pull requests
 
 The main development branch is called `dev`. To contribute, we recommend creating a fork of this repository and making changes on your version. Once you are ready to contribute, we expect you to document, lint and test.
 
-## Documentation standards
+## Installing dev dependencies and pre-commit hooks
 
-We follow [numpy's documentation standards](https://numpydoc.readthedocs.io/en/latest/format.html).
+We recommend you create a `poli-dev` environment in conda
 
-## Linting your changes
+```bash
+conda create -n poli-dev python=3.10
+conda activate poli-dev
+pip install -r requirements.txt
+pip install -r requirements-dev.txt
+```
 
-We expect you to lint the code you write or modify using `black`.
+The dev requirements include `pre-commit`. Install the hooks in our config by running
 
 ```bash
-pip install black
-black ./path/to/files
+pre-commit install
 ```
 
-## Testing your changes for `dev``
+Now every commit will run linting and isorting for you. You can also run it manually by saying
+
+```bash
+pre-commit run --all-files
+```
+
+## Documentation standards
+
+We follow [numpy's documentation standards](https://numpydoc.readthedocs.io/en/latest/format.html).
+
+## Creating a new environment? Mark your tests
+
+If you're contributing a black box in a new environment, remember to
+
+1. Mark all your tests with `@pyest.mark.poli__your_env`.
+2. Add a description of your marker to the `[tool.pytest.ini_options]`.
+
+## Testing your changes for `dev`
 
 Since we are testing multiple conda environments, we settled for using a combination of `tox` and `pytest`.
 
 ```bash
 pip install tox
 
 # To test linting (from the root of the project)
-tox -c tox.dev.ini -e lint
+tox -c tox.ini -e lint
 
 # To test in the base environment for poli
-tox -c tox.dev.ini -e poli-base-py39
+tox -c tox.ini -e poli-base-py39
 ```
 
-If you want to run tests in all environments, remove `-e poli-base-py39` and just run `tox`.
-
-## More thorough testing
-
-In many cases, testing with the instructions above should be enough. However, since we are dealing with creating conda environments, the definite test comes by building the Docker image specified in `Dockerfile.test`, and running it.
+There are several different environments (depending on the black boxes we test). Check `tox.ini` for more details.
 
-When contributing to the `@master` branch (i.e. to release), we will run these tests.
+If you want to run tests in all environments, remove `-e poli-base-py39` and just run `tox`. This might take a while, and several conda envs will be created.
 
 ## Create a pull request to dev
 

README.MD

@@ -1,14 +1,22 @@
-# poli 🧪, a library for discrete objective functions
+# `poli` 🧪, a library for discrete objective functions
 
-[![Testing (conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-including-conda.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-including-conda.yml)
-[![Link to documentation](https://img.shields.io/badge/docs-poli_docs-blue)](https://machinelearninglifescience.github.io/poli-docs/)
+[![poli base (dev, conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml)
+[![Link to documentation](https://img.shields.io/badge/documentation-poli_docs-blue)](https://machinelearninglifescience.github.io/poli-docs/)
 
-poli is a library of discrete objective functions for benchmarking optimization algorithms. Examples include:
-- 🔬 **stability** of mutations from a wildtype protein (using [foldx](https://foldxsuite.crg.eu/) or [rasp](https://github.com/KULL-Centre/_2022_ML-ddG-Blaabjerg)).
-- 🧪 **docking scores** of ligands to proteins (using [dockstring](https://github.com/dockstring/dockstring), [pyscreener](https://github.com/coleygroup/pyscreener) and [pytdc](https://tdcommons.ai/functions/oracles/)).
-- 💊 **druglikeness** or **synthetic acccesibility** of small molecules (using [rdkit](https://github.com/rdkit/rdkit) and [pytdc](https://tdcommons.ai/functions/oracles/)).
+`poli` is a library of discrete objective functions for benchmarking optimization algorithms.
 
-Some of `poli`'s features:
+## Black boxes
+
+| Black box | References | Tests
+|----------|----------|----------|
+|   [Toy continuous functions (e.g. Ackley, Hartmann...)](https://machinelearninglifescience.github.io/poli-docs/using_poli/objective_repository/toy_continuous_problems.html) |  [(Al-Roomi 2015)](https://www.al-roomi.org/benchmarks/unconstrained), [(Surjanovic & Bingham 2013)](https://www.sfu.ca/~ssurjano/optimization.html)  |   [![poli base (dev, conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml)  |
+|   Ehrlich functions  |    [(Stanton et al. 2024)](https://arxiv.org/abs/2407.00236)  | [![poli base (dev, conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-base.yml)
+|   [PMO/GuacaMol benchmark](https://machinelearninglifescience.github.io/poli-docs/#small-molecules)  |   [(Brown et al. 2019)](https://arxiv.org/abs/1811.09621), [(Gao et al. 2022)](https://openreview.net/forum?id=yCZRdI0Y7G), [(Huang et al. 2021)](https://openreview.net/pdf?id=8nvgnORnoWr)  | [![poli tdc (dev, conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-tdc-env.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-tdc-env.yml)
+|   [Dockstring](https://machinelearninglifescience.github.io/poli-docs/using_poli/objective_repository/dockstring.html) |  [(García-Ortegón et al. 2022)](https://pubs.acs.org/doi/full/10.1021/acs.jcim.1c01334)  | [![poli dockstring (dev, conda, python 3.9)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-dockstring-env.yml/badge.svg)](https://github.com/MachineLearningLifeScience/poli/actions/workflows/python-tox-testing-dockstring-env.yml)
+|   [FoldX stability and SASA](https://machinelearninglifescience.github.io/poli-docs/#proteins)  |   [(Schymkowitz et al. 2005)](https://academic.oup.com/nar/article/33/suppl_2/W382/2505499?login=true) |  -  |
+|   [RaSP](https://machinelearninglifescience.github.io/poli-docs/using_poli/objective_repository/RaSP.html)  |   [(Blaabjerg et al. 2023)](https://elifesciences.org/articles/82593)  | -
+
+## Features
 - 🔲 **isolation** of black box function calls inside conda environments. Don't worry about clashes w. black box requirements, poli will create the relevant conda environments for you.
 - 🗒️ **logging** each black box call using observers.
 -  A numpy interface. Inputs are `np.array`s of strings, outputs are `np.array`s of floats.
@@ -27,8 +35,7 @@ pip install git+https://github.com/MachineLearningLifeScience/poli.git@dev
 To check if everything went well, you can run
 
 ```bash
-$ python -c "from poli import get_problems ; print(get_problems())"
-['aloha', ..., 'white_noise']
+$ python -c "from poli import create"
 ```
 
 ### An example: dockstring

examples/minimal_working_example.py

@@ -6,6 +6,7 @@
 """
 
 import numpy as np
+
 from poli import objective_factory
 
 problem = objective_factory.create(name="white_noise")

examples/observers/adding_a_wandb_observer/example_logging_rdkit_qed_using_wandb.py

@@ -9,12 +9,10 @@
 from pathlib import Path
 
 import numpy as np
+from wandb_observer import WandbObserver
 
-from poli.core.problem import Problem
 from poli.objective_repository import QEDProblemFactory
 
-from wandb_observer import WandbObserver
-
 THIS_DIR = Path(__file__).parent.resolve()
 
 if __name__ == "__main__":

examples/observers/adding_a_wandb_observer/wandb_observer.py

@@ -6,8 +6,8 @@
 """
 
 import numpy as np
-import wandb
 
+import wandb
 from poli.core.black_box_information import BlackBoxInformation
 from poli.core.util.abstract_observer import AbstractObserver
 

examples/observers/adding_an_mlflow_observer/example_logging_rdkit_logp_using_mlflow.py

@@ -15,11 +15,10 @@
 from pathlib import Path
 
 import numpy as np
+from mlflow_observer import MlFlowObserver
 
 from poli import objective_factory
 
-from mlflow_observer import MlFlowObserver
-
 THIS_DIR = Path(__file__).parent.resolve()
 
 if __name__ == "__main__":

examples/observers/adding_an_mlflow_observer/mlflow_observer.py

@@ -11,6 +11,7 @@
 """
 
 from pathlib import Path
+
 import mlflow
 import numpy as np
 
@@ -60,8 +61,6 @@ def initialize_observer(
             }
         )
 
-        mlflow.log_param("x0", x0)
-        mlflow.log_param("y0", y0)
         mlflow.log_param("seed", seed)
 
     def observe(self, x: np.ndarray, y: np.ndarray, context=None) -> None: