Polaris

So many stars in the sky, yet one is enough to guide you home.

Polaris establishes a novel, industry‑certified standard to foster the development of impactful methods in AI-based drug discovery.

This library is a Python client to interact with the Polaris Hub. It allows you to:

Download Polaris datasets and benchmarks.
Evaluate a custom method against a Polaris benchmark.
Create and upload new datasets and benchmarks.

[!WARNING] The Polaris Hub is currently released as a closed, private beta. We hope to officially release it early 2024.

Quick API Tour

import polaris as po

# Load the benchmark from the Hub
benchmark = po.load_benchmark("polaris/hello-world-benchmark")

# Get the train and test data-loaders
train, test = benchmark.get_train_test_split()

# Use the training data to train your model
# Get the input as an array with 'train.inputs' and 'train.targets'  
# Or simply iterate over the train object.
for x, y in train:
    ...

# Work your magic to accurately predict the test set
predictions = [0.0 for x in test]

# Evaluate your predictions
results = benchmark.evaluate(predictions)

# Submit your results
results.upload_to_hub(owner="dummy-user")

Documentation

Please refer to the documentation, which contains tutorials for getting started with polaris and detailed descriptions of the functions provided.

Installation

You can install polaris using conda/mamba/micromamba:

conda install -c conda-forge polaris

You can also use pip:

pip install polaris-lib

Development lifecycle

Setup dev environment

conda env create -n polaris -f env.yml
conda activate polaris

pip install --no-deps -e .

Other installation options

Alternatively, using [uv](https://github.com/astral-sh/uv): ```shell uv venv -p 3.12 polaris source .venv/polaris/bin/activate uv pip compile pyproject.toml -o requirements.txt --all-extras uv pip install -r requirements.txt ```

Tests

You can run tests locally with:

pytest

License

Under the Apache-2.0 license. See LICENSE.

polaris-hub / polaris

readme