poli base (dev, conda, python 3.9) Link to documentation

poli is a library of discrete objective functions for benchmarking optimization algorithms.

• 🔲 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.arrays of strings, outputs are np.arrays of floats.
• SMILES and SELFIES support for small molecule manipulation.

To install poli, we recommend creating a fresh conda environment

conda create -n poli-base python=3.9
conda activate poli-base
pip install git+https://github.com/MachineLearningLifeScience/poli.git@dev

To check if everything went well, you can run

$ python -c "from poli import create"

Open the minimal example in Colab

In this next example, we estimate the docking score of the example provided in dockstring:

import numpy as np
from poli import objective_factory
problem = objective_factory.create(
 name="dockstring",
 target_name="drd2"
)
f, x0 = problem.black_box, problem.x0
y0 = f(x0)
# x0: [['C' 'C' '1' '=' 'C' '(' 'C', ...]] (i.e. Risperidone's SMILES)
# y0: 11.9
print(x0, y0)

If you use certain black boxes, we expect you to cite the relevant work. Check inside the documentation of each black box for the relevant references.

The main documentation site is hosted as a GitHub page here: https://machinelearninglifescience.github.io/poli-docs/

If you install the requirements-dev.txt via

pip install -r requirements-dev.txt

then you will have access to sphinx. You should be able to build the documentation by going to the docs folder and building it:

cd docs/
make html

Afterwards, you can enter the build folder and open index.html.