用单次前向传播实现分子几何结构的高精度优化，大幅加速量子化学计算。
A Cross-Domain Graph Learning Protocol for Single-Step Molecular Geometry Refinement
- 基于SE(3)等变网络，从低成本构象直接预测B3LYP/TZVP级高质量结构。
- 在药物分子上实现亚毫埃级精度，能量偏差接近零，可直接用于DFT计算。
- 适合需要快速生成可靠分子结构的药物研发与高通量筛选场景。
精确的分子几何结构是可靠量子化学预测的前提，但密度泛函理论（DFT）优化仍是高通量分子筛选的主要瓶颈。本文提出GeoOpt-Net，一种多分支SE(3)-等变几何精修网络，仅需一次前向传播即可从低成本力场生成的初始构象出发，预测达到B3LYP/TZVP水平的高质量结构。该模型采用两阶段训练策略：先在广泛数据上预训练几何表示，再通过保真度感知特征调制（FAFM）机制微调至目标精度，实现理论与基组感知的校准。在外部药物样分子上的基准测试表明，GeoOpt-Net实现了亚毫埃级全原子均方根偏差（RMSD），且单点能量偏差接近零，生成的结构可直接作为DFT计算的起点。此外，其初始构象满足收敛条件，宽松与默认阈值下“全通过”收敛率分别达65.0%和33.4%，显著减少重优化步数与耗时。模型还表现出平滑的能量随分子复杂度增长趋势，并保持偶极矩等关键电子性质。结果表明，GeoOpt-Net是一种可扩展、物理一致的几何精修框架，能高效加速基于DFT的量子化学工作流。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。