Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions

• URL: http://arxiv.org/abs/2603.00568v1
• Date: Sat, 28 Feb 2026 09:36:19 GMT
• Title: Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions
• Authors: Yunqing Liu, Yi Zhou, Wenqi Fan,
• Abstract summary: We introduce textbfDeMol, a dual-graph framework for atom-centric representation learning.<n>DeMol explicitly models molecules through parallel atom-centric and bond-centric channels.<n>It establishes a new state-of-the-art, outperforming existing methods.
• Score: 18.371474900925865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely as pairwise interactions, often overlook complex bond-level phenomena like resonance and stereoselectivity. This oversight limits their predictive accuracy for nuanced chemical behaviors. To address this limitation, we introduce \textbf{DeMol}, a dual-graph framework whose architecture is motivated by a rigorous information-theoretic analysis demonstrating the information gain from a bond-centric perspective. DeMol explicitly models molecules through parallel atom-centric and bond-centric channels. These are synergistically fused by multi-scale Double-Helix Blocks designed to learn intricate atom-atom, atom-bond, and bond-bond interactions. The framework's geometric consistency is further enhanced by a regularization term based on covalent radii to enforce chemically plausible structures. Comprehensive evaluations on diverse benchmarks, including PCQM4Mv2, OC20 IS2RE, QM9, and MoleculeNet, show that DeMol establishes a new state-of-the-art, outperforming existing methods. These results confirm the superiority of explicitly modelling bond information and interactions, paving the way for more robust and accurate molecular machine learning.

Related papers

• Mamba-driven multi-perspective structural understanding for molecular ground-state conformation prediction [69.32436472760712]
  We propose an approach of Mamba-driven multi-perspective structural understanding (MPSU-Mamba) to localize molecular ground-state conformation.<n>For complex and diverse molecules, three different kinds of dedicated scanning strategies are explored to construct a comprehensive perception of corresponding molecular structures.<n> Experimental results on QM9 and Molecule3D datasets indicate that MPSU-Mamba significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-10T11:18:32Z)
• Aligned Manifold Property and Topology Point Clouds for Learning Molecular Properties [55.2480439325792]
  This work introduces AMPTCR, a molecular surface representation that combines local quantum-derived scalar fields and custom topological descriptors within an aligned point cloud format.<n>For molecular weight, results confirm that AMPTCR encodes physically meaningful data, with a validation R2 of 0.87.<n>In the bacterial inhibition task, AMPTCR enables both classification and direct regression of E. coli inhibition values.
  arXiv  Detail & Related papers  (2025-07-22T04:35:50Z)
• Knowledge-aware contrastive heterogeneous molecular graph learning [77.94721384862699]
  We propose a paradigm shift by encoding molecular graphs into Heterogeneous Molecular Graph Learning (KCHML)<n>KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism.<n>This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction (DDI) prediction.
  arXiv  Detail & Related papers  (2025-02-17T11:53:58Z)
• FragNet: A Graph Neural Network for Molecular Property Prediction with Four Levels of Interpretability [0.7499722271664147]
  We present a graph neural network that matches leading models and provides insights on four levels of molecular substructures.<n>This model helps identify which atoms, bonds, molecular fragments, and connections between fragments are significant for predicting a specific molecular property.
  arXiv  Detail & Related papers  (2024-10-16T01:37:01Z)
• Response Matching for generating materials and molecules [0.0]
  We present a novel generative method called Response Matching (RM) RM exploits the locality of atomic interactions, and inherently respects permutation, translation, rotation, and periodic invariances. We demonstrate the efficiency and generalization of RM across three systems.
  arXiv  Detail & Related papers  (2024-05-15T03:08:21Z)
• Atom-Motif Contrastive Transformer for Molecular Property Prediction [68.85399466928976]
  Graph Transformer (GT) models have been widely used in the task of Molecular Property Prediction (MPP) We propose a novel Atom-Motif Contrastive Transformer (AMCT) which explores atom-level interactions and considers motif-level interactions. Our proposed AMCT is extensively evaluated on seven popular benchmark datasets, and both quantitative and qualitative results firmly demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2023-10-11T10:03:10Z)
• Cavity-Born-Oppenheimer Hartree-Fock Ansatz: Light-matter Properties of Strongly Coupled Molecular Ensembles [0.0]
  We present an ab-initio Hartree-Fock ansatz in the framework of the cavity Born-Oppenheimer approximation. We study the collective effects in ensembles of strongly coupled diatomic hydrogen fluoride molecules.
  arXiv  Detail & Related papers  (2023-07-05T11:20:24Z)
• Modeling Non-Covalent Interatomic Interactions on a Photonic Quantum Computer [50.24983453990065]
  We show that the cQDO model lends itself naturally to simulation on a photonic quantum computer. We calculate the binding energy curve of diatomic systems by leveraging Xanadu's Strawberry Fields photonics library. Remarkably, we find that two coupled bosonic QDOs exhibit a stable bond.
  arXiv  Detail & Related papers  (2023-06-14T14:44:12Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• GEM-2: Next Generation Molecular Property Prediction Network with Many-body and Full-range Interaction Modeling [24.94616336296936]
  GEM-2 is a novel method for solving the Schr"odinger equation for molecules. It considers both the long-range and many-body interactions in molecules.
  arXiv  Detail & Related papers  (2022-08-11T15:12:25Z)

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.