polaris-lib 0.2.1

Client for the Polaris Hub.

Polaris

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

🟆 Polaris Hub | 🛈 Client Doc

---

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

# Download a benchmark (the associated dataset will be transparently downloaded)
benchmark = po.load_benchmark("org_or_user/name")

# Retrieve the splits
train, test = benchmark.get_train_test_split()

# Work your magic!
y_pred = ...

# Run the evaluation procedure
results = benchmark.evaluate(y_pred)

# Upload your results to the hub
results.upload_to_hub()

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 .

Tests

You can run tests locally with:

pytest

License

Under the Apache-2.0 license. See LICENSE.