Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose

• URL: http://arxiv.org/abs/2405.13791v2
• Date: Tue, 23 Jul 2024 18:24:02 GMT
• Title: Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose
• Authors: Michael Kilgour, Mark Tuckerman, Jutta Rogal,
• Abstract summary: We develop, train, and evaluate a new type of autoencoder, molecular O(3) encoding net (Mo3ENet) for multi-type point clouds. Mo3ENet is end-to-end equivariant, meaning the learned representation can be manipulated on O(3), a practical bonus for downstream learning tasks.
• Score: 0.8886153850492464
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The point cloud is a flexible representation for a wide variety of data types, and is a particularly natural fit for the 3D conformations of molecules. Extant molecule embedding/representation schemes typically focus on internal degrees of freedom, ignoring the global 3D orientation. For tasks that depend on knowledge of both molecular conformation and 3D orientation, such as the generation of molecular dimers, clusters, or condensed phases, we require a representation which is provably complete in the types and positions of atomic nuclei and roto-inversion equivariant with respect to the input point cloud. We develop, train, and evaluate a new type of autoencoder, molecular O(3) encoding net (Mo3ENet), for multi-type point clouds, for which we propose a new reconstruction loss, capitalizing on a Gaussian mixture representation of the input and output point clouds. Mo3ENet is end-to-end equivariant, meaning the learned representation can be manipulated on O(3), a practical bonus for downstream learning tasks. An appropriately trained Mo3ENet latent space comprises a universal embedding for scalar and vector molecule property prediction tasks, as well as other downstream tasks incorporating the 3D molecular pose.

Related papers

• MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning [17.93173928602627]
  We propose a simple transformer-based baseline for multimodal molecular representation learning. We integrate three distinct modalities: SMILES strings, 2D graph representations, and 3D conformers of molecules. Despite its simplicity, our approach achieves state-of-the-art results across multiple datasets.
  arXiv  Detail & Related papers  (2024-10-10T14:36:58Z)
• SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning [27.713870291922333]
  We develop an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. SE3Set has shown performance on par with state-of-the-art (SOTA) models for small molecule datasets. It excels on the MD22 dataset, achieving a notable improvement of approximately 20% in accuracy across all molecules.
  arXiv  Detail & Related papers  (2024-05-26T10:43:16Z)
• MUDiff: Unified Diffusion for Complete Molecule Generation [104.7021929437504]
  We present a new model for generating a comprehensive representation of molecules, including atom features, 2D discrete molecule structures, and 3D continuous molecule coordinates. We propose a novel graph transformer architecture to denoise the diffusion process. Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.
  arXiv  Detail & Related papers  (2023-04-28T04:25:57Z)
• One Transformer Can Understand Both 2D & 3D Molecular Data [94.93514673086631]
  We develop a novel Transformer-based Molecular model called Transformer-M. It can take molecular data of 2D or 3D formats as input and generate meaningful semantic representations. All empirical results show that Transformer-M can simultaneously achieve strong performance on 2D and 3D tasks.
  arXiv  Detail & Related papers  (2022-10-04T17:30:31Z)
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations [2.17167311150369]
  We design an SE(3)-invariant model that processes torsion angles of a 3D molecular conformer. We test our model on four benchmarks: contrastive learning to distinguish conformers of different stereoisomers in a learned latent space, classification of chiral centers as R/S, prediction of how enantiomers rotate circularly polarized light, and ranking enantiomers by their docking scores in an enantiosensitive protein pocket.
  arXiv  Detail & Related papers  (2021-10-08T21:25:47Z)
• 3D-Transformer: Molecular Representation with Transformer in 3D Space [11.947499562836953]
  3D-Transformer is a variant of the Transformer for molecular representations that incorporates 3D spatial information. Our experiments show significant improvements over state-of-the-art models on the crystal property prediction task and the protein-ligand binding affinity prediction task.
  arXiv  Detail & Related papers  (2021-10-04T05:11:23Z)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)
• Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows [79.39092757515395]
  We propose Neural Mesh Flow (NMF) to generate two-manifold meshes for genus-0 shapes. NMF is a shape auto-encoder consisting of several Neural Ordinary Differential Equation (NODE) blocks that learn accurate mesh geometry by progressively deforming a spherical mesh. Our experiments demonstrate that NMF facilitates several applications such as single-view mesh reconstruction, global shape parameterization, texture mapping, shape deformation and correspondence.
  arXiv  Detail & Related papers  (2020-07-21T17:45:41Z)
• PointGMM: a Neural GMM Network for Point Clouds [83.9404865744028]
  Point clouds are popular representation for 3D shapes, but encode a particular sampling without accounting for shape priors or non-local information. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistents between existing shapes.
  arXiv  Detail & Related papers  (2020-03-30T10:34:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.