AI 中文总结
研究针对分子属性预测中现有方法的局限，提出SenCos-GEM框架。该框架结合SENet校准和余弦定律约束，采用物理引导几何一致性损失及轻量级SE模块等，在MoleculeNet基准测试中表现出色，降低多种任务误差，提升立体异构体辨别等能力。
AI 中文摘要
有效的分子表示学习对于准确的分子属性预测至关重要。最近，许多利用3D GNN的自监督学习（SSL）方法被开发用于药物发现以捕获全面的3D结构信息。然而，现有方法缺乏明确的物理约束，在大规模分子动力学模拟中极易受到粗略经验力场引起的几何噪声影响，并且在下游适应过程中忽略动态特征调制，常导致灾难性遗忘和负迁移。为解决这些限制，我们引入了SenCos-GEM，这是一个新颖的显式解耦几何增强分子表示学习框架，它结合了SENet校准和余弦定律约束的增强。SenCos-GEM采用基于余弦定律的物理引导几何一致性损失来推导高保真和数学不变的3D空间先验。此外，轻量级的挤压激励（SE）模块被集成到主干中作为特定任务的适配器，而双调制预测头结合了特征线性调制（FiLM）和SENet机制以实现动态特征重新校准。SenCos-GEM在MoleculeNet基准上的各种分类和回归任务中展示了极具竞争力的性能，在3D构象敏感回归任务上建立了新的最优结果，在FreeSolv、亲脂性和QM9任务中分别实现了12.9%（RMSE）、5.3%（RMSE）和8.2%（MAE）的相对误差降低。此外，我们的模型在区分立体异构体和辨别构象扰动方面表现出卓越能力，突出了其强大的空间建模性能。总体而言，SenCos-GEM在准确的分子属性预测方面代表了一个重大突破。
英文摘要
Effective molecular representation learning is crucial for accurate molecular property prediction. Recently, numerous self-supervised learning (SSL) approaches leveraging 3D GNNs have been developed to capture comprehensive 3D structural information for drug discovery. However, existing methods lack explicit physical constraints and are highly susceptible to geometric noise induced by coarse empirical force fields during large-scale pre-training.Furthermore, they overlook dynamic feature modulation during downstream adaptation, often resulting in catastrophic forgetting and negative transfer. To address these limitations, we introduce SenCos-GEM, a novel explicitly decoupled geometry-enhanced molecular representation learning framework that incorporates SENet-calibrated and law-of-cosines-constrained enhancements. SenCos-GEM employs a physics-guided geometric consistency loss based on the law of cosines to derive high-fidelity and mathematically invariant 3D spatial priors. In addition, lightweight Squeeze-and-Excitation (SE) modules are integrated into the backbone as task-specific adapters, while a dual-modulation prediction head combines Feature-wise Linear Modulation (FiLM) and SENet mechanisms to enable dynamic feature recalibration. SenCos-GEM demonstrates highly competitive performance across diverse classification and regression tasks on MoleculeNet benchmark, establishing new state-of-the-art results specifically on 3D conformation-sensitive regression tasks, such as FreeSolv, Lipophilicity, and QM9, achieving relative error reductions of 12.9% (RMSE), 5.3% (RMSE), and 8.2% (MAE), respectively. Moreover, our model exhibits superior capability in distinguishing stereoisomers and discriminating conformational perturbations, underscoring its robust spatial modeling performance. Collectively, SenCos-GEM represents a significant breakthrough in accurate molecular property prediction.
