通过几何约束与动态调制，提升分子属性预测的精度与鲁棒性。
SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction
- 引入余弦定律构建物理一致的3D空间先验，抑制几何噪声。
- 在FreeSolv、Lipophilicity等任务上相对误差降低5.3%~12.9%。
- 适合需要精细立体结构建模的药物发现场景。
有效的分子表示学习对精准预测分子属性至关重要。近年来，大量基于3D图神经网络的自监督学习方法被提出，以捕捉药物发现中的完整3D结构信息。然而，现有方法缺乏显式物理约束，在大规模预训练中易受粗粒度经验力场引入的几何噪声影响，且忽视下游适配过程中的动态特征调制，常导致灾难性遗忘与负迁移。为此，我们提出SenCos-GEM——一种显式解耦的几何增强型分子表示学习框架，融合SE网络校准与余弦定律约束。该框架基于余弦定律设计物理引导的几何一致性损失，生成高保真、数学不变的3D空间先验。同时，轻量级Squeeze-and-Excitation（SE）模块作为任务特定适配器嵌入主干网络，并采用结合FiLM与SE机制的双调制预测头，实现动态特征重校准。SenCos-GEM在MoleculeNet基准上多种分类与回归任务中表现优异，尤其在3D构象敏感回归任务（如FreeSolv、Lipophilicity、QM9）上达到新SOTA，相对误差分别降低12.9%（RMSE）、5.3%（RMSE）、8.2%（MAE）。此外，模型在区分立体异构体与识别构象扰动方面表现出色，凸显其强大的空间建模能力。总体而言，SenCos-GEM在准确分子属性预测方面取得显著突破。
原文摘要 · Abstract (English)
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.
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。