Conformation-Guided Molecular Representation with Hamiltonian Neural NetworksDownload PDF

Published: 12 Jan 2021, Last Modified: 05 May 2023ICLR 2021 PosterReaders: Everyone
Keywords: Molecular Representation, Neural Physics Engines, Molecular Dynamics, Graph Neural Networks
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.
One-sentence Summary: We propose a molecular representation algorithm, which preserves molecular conformations with a neural physics engine and generates fingerprints with an MPNN.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Supplementary Material: zip
Data: [MoleculeNet](https://paperswithcode.com/dataset/moleculenet)
9 Replies

Loading