HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks
arXiv:2105.03688
Abstract
Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning. Whereas incorporating 3D geometry of molecules (i.e. conformations) in their representations seems beneficial, current 3D algorithms are still in infancy. In this paper, we propose a novel molecular representation algorithm which preserves 3D conformations of molecules with a Molecular Hamiltonian Network (HamNet). In HamNet, implicit positions and momentums of atoms in a molecule interact in the Hamiltonian Engine following the discretized Hamiltonian equations. These implicit coordinations are supervised with real conformations with translation- & rotation-invariant losses, and further used as inputs to the Fingerprint Generator, a message-passing neural network. Experiments show that the Hamiltonian Engine can well preserve molecular conformations, and that the fingerprints generated by HamNet achieve state-of-the-art performances on MoleculeNet, a standard molecular machine learning benchmark.
arXiv commentin ICLR-2021 (poster)
References in corpus (8)
- Neural Message Passing for Quantum Chemistry
- Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Hamiltonian Neural Networks
- Hamiltonian Graph Networks with ODE Integrators
- Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
- TF3P: Three-dimensional Force Fields Fingerprint Learned by Deep Capsular Network