Quantum-enabled machine learning
Our core technologies use physics-based machine learning features, derived from efficient quantum mechanical calculations, to map chemical space with unprecedented fidelity and transferability.
Learn More
OrbNet
The OrbNet technology uses features from quantum mechanics to produce machine-learning models with unprecedented transferability and learning efficiency. For computational chemistry, OrbNet provides thousandfold improvements in efficiency relative to DFT quantum mechanics, without loss of accuracy. For ML predictions based on experimental datasets, OrbNet compactly represents chemical space for the efficient machine-learning of high-value molecular properties including ADMET.
Qcore quantum simulation engine
Qcore has state-of-the-art implementations of efficient mean-field theories that power generation of quantum features forour machine-learning featurization and prediction engines and a suite of unique features for quantum embedding.
Core methods are available such as Hartree-Fock theory, density functional theory, and modern semiempirical methods, all wrapped in an efficiently parallelized application, developed by a team of dedicated software engineers. Tools for chemistry (such as constrained and unconstrained geometry optimization, transition-state search, ab initio dynamics, frequencies, etc) are available for all methods.
Publications
OrbNet: 1000x speedups
Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
Fluoride ion batteries
Room-temperature cycling of metal fluoride electrodes: Liquid electrolytes for high-energy fluoride ion cells
Graphene scattering
Imaging covalent bond formation by H atom scattering from graphene
Polyolefin catalysis
Embedded Mean-Field Theory for Solution-Phase Transition-Metal Polyolefin Catalysis