Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning

• URL: http://arxiv.org/abs/2511.21900v1
• Date: Wed, 26 Nov 2025 20:42:31 GMT
• Title: Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning
• Authors: Patricia Suriana, Joshua A. Rackers, Ewa M. Nowara, Pedro O. Pinheiro, John M. Nicoloudis, Vishnu Sresht,
• Abstract summary: We compare three voxel-based input types for 3D convolutional neural networks (CNNs)<n>We focus on voxel-based CNNs because electron density is inherently volumetric, and voxel grids provide the most natural representation for both experimental and computed densities.
• Score: 3.554781859726123
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Machine learning models for 3D molecular property prediction typically rely on atom-based representations, which may overlook subtle physical information. Electron density maps -- the direct output of X-ray crystallography and cryo-electron microscopy -- offer a continuous, physically grounded alternative. We compare three voxel-based input types for 3D convolutional neural networks (CNNs): atom types, raw electron density, and density gradient magnitude, across two molecular tasks -- protein-ligand binding affinity prediction (PDBbind) and quantum property prediction (QM9). We focus on voxel-based CNNs because electron density is inherently volumetric, and voxel grids provide the most natural representation for both experimental and computed densities. On PDBbind, all representations perform similarly with full data, but in low-data regimes, density-based inputs outperform atom types, while a shape-based baseline performs comparably -- suggesting that spatial occupancy dominates this task. On QM9, where labels are derived from Density Functional Theory (DFT) but input densities from a lower-level method (XTB), density-based inputs still outperform atom-based ones at scale, reflecting the rich structural and electronic information encoded in density. Overall, these results highlight the task- and regime-dependent strengths of density-derived inputs, improving data efficiency in affinity prediction and accuracy in quantum property modeling.

Related papers

• Tokenizing Electron Cloud in Protein-Ligand Interaction Learning [51.74909649330779]
  ECBind is a method for tokenizing electron cloud signals into quantized embeddings.<n>It helps uncover binding modes that cannot be fully represented by atom-level models.<n>To extend its applicability to a wider range of scenarios, we utilize knowledge distillation to develop an electron-cloud-agnostic prediction model.
  arXiv  Detail & Related papers  (2025-05-25T07:36:50Z)
• A Recipe for Charge Density Prediction [4.017525264569417]
  Machine learning methods are promising in significantly accelerating charge density prediction. We propose a recipe that can achieve both accuracy and scalability. Our method achieves state-of-the-art accuracy while being more than an order of magnitude faster than existing methods.
  arXiv  Detail & Related papers  (2024-05-29T17:07:24Z)
• Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materials [3.7655047338409893]
  ChargE3Net is an E(3)-equivariant graph neural network for predicting electron density in atomic systems. We show that ChargE3Net exceeds the performance of prior work on diverse sets of molecules and materials.
  arXiv  Detail & Related papers  (2023-12-08T21:56:19Z)
• QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules [69.25826391912368]
  We generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 999 or 2998 molecular dynamics trajectories. We show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules.
  arXiv  Detail & Related papers  (2023-06-15T23:39:07Z)
• Automated 3D Pre-Training for Molecular Property Prediction [54.15788181794094]
  We propose a novel 3D pre-training framework (dubbed 3D PGT) It pre-trains a model on 3D molecular graphs, and then fine-tunes it on molecular graphs without 3D structures. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT.
  arXiv  Detail & Related papers  (2023-06-13T14:43:13Z)
• Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling [51.83761266429285]
  We propose a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them. Moleformer achieves state-of-the-art on the initial state to relaxed energy prediction of OC20 and is very competitive in QM9 on predicting quantum chemical properties.
  arXiv  Detail & Related papers  (2023-02-02T03:49:57Z)
• Electronic-structure properties from atom-centered predictions of the electron density [0.0]
  electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. We propose a gradient-based approach to minimize the loss function of the regression problem in an optimized and highly sparse feature space. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom.
  arXiv  Detail & Related papers  (2022-06-28T15:35:55Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning [7.106986689736826]
  Deep neural networks (DNNs) have been used to successfully predict molecular properties calculated based on the Kohn--Sham density functional theory (KS-DFT) This letter presents the quantum deep field (QDF), which provides the electron density with an unsupervised but end-to-end physics-informed modeling by learning the atomization energy on a large-scale dataset.
  arXiv  Detail & Related papers  (2020-11-16T13:15:16Z)
• DeepDFT: Neural Message Passing Network for Accurate Charge Density Prediction [0.0]
  DeepDFT is a deep learning model for predicting the electronic charge density around atoms. The accuracy and scalability of the model are demonstrated for molecules, solids and liquids.
  arXiv  Detail & Related papers  (2020-11-04T16:56:08Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)

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.