A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement

• URL: http://arxiv.org/abs/2601.22723v1
• Date: Fri, 30 Jan 2026 08:55:46 GMT
• Title: A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement
• Authors: Chengchun Liu, Wendi Cai, Boxuan Zhao, Fanyang Mo,
• Abstract summary: GeoOpt-Net is a multi-branch SE(3)-equivariant geometry refinement network that predicts DFT-quality structures at the B3LYP/TZVP level of theory in a single forward pass.<n>GeoOpt-Net generates initial guesses intrinsically compatible with DFT convergence criteria, yielding nonzero All-YES'' convergence rates.<n>These results establish GeoOpt-Net as a scalable, physically consistent geometry refinement framework that enables efficient acceleration of DFT-based quantum-chemical predictions.
• Score: 0.47664901548798794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate molecular geometries are a prerequisite for reliable quantum-chemical predictions, yet density functional theory (DFT) optimization remains a major bottleneck for high-throughput molecular screening. Here we present GeoOpt-Net, a multi-branch SE(3)-equivariant geometry refinement network that predicts DFT-quality structures at the B3LYP/TZVP level of theory in a single forward pass starting from inexpensive initial conformers generated at a low-cost force-field level. GeoOpt-Net is trained using a two-stage strategy in which a broadly pretrained geometric representation is subsequently fine-tuned to approach B3LYP/TZVP-level accuracy, with theory- and basis-set-aware calibration enabled by a fidelity-aware feature modulation (FAFM) mechanism. Benchmarking against representative approaches spanning classical conformer generation (RDKit), semiempirical quantum methods (xTB), data-driven geometry refinement pipelines (Auto3D), and machine-learning interatomic potentials (UMA) on external drug-like molecules demonstrates that GeoOpt-Net achieves sub-milli-Å all-atom RMSD with near-zero B3LYP/TZVP single-point energy deviations, indicating DFT-ready geometries that closely reproduce both structural and energetic references. Beyond geometric metrics, GeoOpt-Net generates initial guesses intrinsically compatible with DFT convergence criteria, yielding nonzero ``All-YES'' convergence rates (65.0\% under loose and 33.4\% under default thresholds), and substantially reducing re-optimization steps and wall-clock time. GeoOpt-Net further exhibits smooth and predictable energy scaling with molecular complexity while preserving key electronic observables such as dipole moments. Collectively, these results establish GeoOpt-Net as a scalable, physically consistent geometry refinement framework that enables efficient acceleration of DFT-based quantum-chemical workflows.

Related papers

• Renormalization Group Guided Tensor Network Structure Search [58.0378300612202]
  Network structure search (TN-SS) aims to automatically discover optimal network topologies and rank robustness for efficient tensor decomposition in high-dimensional data representation.<n>We propose RGTN (Renormalization Group guided Network search), a physics-inspired framework transforming TN-SS via multi-scale renormalization group flows.
  arXiv  Detail & Related papers  (2025-12-31T06:31:43Z)
• GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters [61.51810815162003]
  We propose an SE(3)-equivariant adapter framework ( GeoAda) that enables flexible and parameter-efficient fine-tuning for controlled generative tasks.<n>GeoAda preserves the model's geometric consistency while mitigating overfitting and catastrophic forgetting.<n>We demonstrate the wide applicability of GeoAda across diverse geometric control types, including frame control, global control, subgraph control, and a broad range of application domains.
  arXiv  Detail & Related papers  (2025-07-02T18:44:03Z)
• EquiCPI: SE(3)-Equivariant Geometric Deep Learning for Structure-Aware Prediction of Compound-Protein Interactions [0.0]
  EquiCPI is an end-to-end geometric deep learning framework that synergizes first-principles structural modeling with SE(3)-equivariant neural networks.<n>At its core, EquiCPI employs SE(3)-equivariant message passing over atomic point clouds, preserving symmetry under rotations, translations, and reflections.<n>The proposed model is evaluated on BindingDB (affinity prediction) and DUD-E (virtual screening), EquiCPI performance on par with or exceeding the state-of-the-art deep learning competitors.
  arXiv  Detail & Related papers  (2025-04-07T00:57:08Z)
• Geometric Meta-Learning via Coupled Ricci Flow: Unifying Knowledge Representation and Quantum Entanglement [7.410691988131121]
  This paper establishes a unified framework integrating geometric flows with deep learning through three fundamental innovations.<n>First, we propose a thermodynamically coupled Ricci flow that dynamically adapts parameter space geometry to loss landscape topology.<n>Second, we derive explicit phase transition thresholds and critical learning rates through curvature blowup analysis.<n>Third, we establish an AdS/CFT-type holographic duality (Theoremrefthm:ads) between neural networks and conformal field theories.
  arXiv  Detail & Related papers  (2025-03-25T17:32:31Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• Bridging Geometric States via Geometric Diffusion Bridge [79.60212414973002]
  We introduce the Geometric Diffusion Bridge (GDB), a novel generative modeling framework that accurately bridges initial and target geometric states. GDB employs an equivariant diffusion bridge derived by a modified version of Doob's $h$-transform for connecting geometric states. We show that GDB surpasses existing state-of-the-art approaches, opening up a new pathway for accurately bridging geometric states.
  arXiv  Detail & Related papers  (2024-10-31T17:59:53Z)
• Orbital-free density functional theory with first-quantized quantum subroutines [0.0]
  We propose a quantum-classical hybrid scheme for performing orbital-free density functional theory (OFDFT) using probabilistic imaginary-time evolution (PITE) PITE is applied to the part of OFDFT that searches the ground state of the Hamiltonian in each self-consistent field (SCF) iteration. It is shown that obtaining the ground state energy of Hamiltonian requires a circuit depth of $O(log N_mathrmg)$.
  arXiv  Detail & Related papers  (2024-07-23T05:34:11Z)
• Force-free identification of minimum-energy pathways and transition states for stochastic electronic structure theories [0.18641315013048293]
  We present strategies that utilize the surrogate Hessian line-search method to efficiently identify MEP and TS structures. We show that it is possible to identify MEPs and TSs using a force-free Quantum Monte Carlo approach.
  arXiv  Detail & Related papers  (2024-02-20T17:58:43Z)
• GeoTMI:Predicting quantum chemical property with easy-to-obtain geometry via positional denoising [0.9192155794577584]
  We propose a new training framework, GeoTMI, that employs denoising process to predict properties accurately using easy-to-obtain geometries. Our results showed consistent improvements in accuracy across various tasks, demonstrating the effectiveness and robustness of GeoTMI.
  arXiv  Detail & Related papers  (2023-03-28T17:07:12Z)
• 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)
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming [71.82571553927619]
  We propose an end-to-end solution for molecular conformation prediction called ConfVAE. Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.
  arXiv  Detail & Related papers  (2021-05-15T15:22:29Z)

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.