Tag

PennyLane is a cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. It enables building quantum circuits and hybrid quantum-classical models, provides hardware and simulator backends via plugins, and integrates with major ML frameworks for automatic differentiation and training.

Boltz is an open-source family of deep learning models and a GitHub project for biomolecular interaction prediction (Boltz-1, Boltz-2). It predicts complex structures and binding affinities, aiming to approach or exceed AlphaFold3 structural accuracy and deliver fast, practical affinity predictions comparable to physics-based methods at a fraction of the compute cost. Code and weights are released under the MIT license.

This paper introduces Message Passing Neural Networks (MPNNs), a unifying framework for graph-based deep learning, and applies it to quantum-chemistry property prediction, achieving state-of-the-art accuracy on the QM9 benchmark and approaching chemical accuracy on most targets. Its impact includes popularising graph neural networks, influencing subsequent work in cheminformatics, materials discovery, and the broader machine-learning community by demonstrating how learned message passing can replace hand-engineered molecular descriptors.