Uni-Macro-FRPN：面向聚合物的全分辨率与跨尺度学习
Uni-Macro-FRPN: Full-Resolution and Cross-Scale Learning for Polymers
查看机构详情
- South China Advanced Institute for Soft Matter Science and Technology, School of Emergent Soft Matter, South China University of Technology（华南软物质科学与技术高等研究院， emergent soft matter 学院，华南理工大学）
- Guangdong Provincial Key Laboratory of Functional and Intelligent Hybrid Materials and Devices, South China University of Technology（广东省功能性与智能型杂化材料器件重点实验室，华南理工大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出Uni-Macro-FRPN全分辨率聚合物网络，联合建模原子级单体特征与链拓扑，在BCDB分类任务达86.4%准确率，超越单体中心方法，推动聚合物多尺度表示学习。
中文摘要 AI 辅助
聚合物的性质源于跨尺度的相互作用，然而现有的聚合物模型通常受限于计算资源（因为聚合物通常包含数万个原子），要么保留详细的单体化学信息但缺乏显式的聚合物图结构，要么保留聚合物连接性但简化单体表示。我们提出了Uni-Macro-FRPN（FRPN），一种全分辨率聚合物网络，在统一框架内同时保留详细的原子级和单体级特征以及显式的聚合物结构信息。两个Transformer从基于BigSMILES的表示中联合学习原子信息增强的单体语义、序列顺序和链拓扑。在嵌段共聚物数据库（BCDB）的层状与非层状分类任务中，FRPN达到了86.4%的准确率和90.6%的ROC-AUC，确立了最先进的性能。消融结果表明，性能提升不能仅由参数数量的增加来解释。在线性均聚物基准上，以单体为中心的学习仍具有竞争力，这突显了聚合物尺度组织简单时的边界情况。为了测试超越线性聚合物的泛化能力，我们进一步构建了一个包含1640个数据点的全原子分子动力学基准，涵盖多样的单体化学、序列顺序、链拓扑和物理性质。FRPN在这个富含拓扑结构的基准上取得了最强的整体性能，诊断结果支持联合建模单体化学和聚合物结构的益处。总的来说，FRPN为将聚合物表示学习超越单体中心表示提供了一条实用途径。FRPN的领先性能也为聚合物信息学指明了一个有前景的方向：未来的聚合物预测模型不仅应将聚合物视为单体描述符的集合，更应将其视为完整的多尺度化学和拓扑对象。
英文摘要
Polymer properties emerge from interactions across scales, yet existing polymer models typically preserve either detailed monomer chemistry without an explicit polymer graph or polymer connectivity with simplified monomer representations, due to computational constraints, as polymers typically contain tens of thousands of atoms. We present Uni-Macro-FRPN (FRPN), a Full-Resolution Polymer Network that retains both detailed atom-level and monomer-level features and explicit polymer structure information within a unified framework. Two Transformers jointly learn atom-informed monomer semantics, sequence order, and chain topology from BigSMILES-derived representations. On the Block Copolymer Database (BCDB) lamellar-versus-non-lamellar classification task, FRPN achieves 86.4% accuracy and 90.6% ROC-AUC, establishing state-of-the-art performance. Ablation results indicate that the gain is not explained solely by increased parameter count. On a linear homopolymer benchmark, monomer-centric learning remains competitive, highlighting a boundary case where polymer-scale organization is simple. To test generalization beyond linear polymers, we further construct an all-atom molecular-dynamics benchmark of 1640 datapoints spanning diverse monomer chemistries, sequence orderings, chain topologies, and physical properties. FRPN achieves the strongest overall performance on this topology-rich benchmark, with diagnostics supporting the benefit of jointly modeling monomer chemistry and polymer structure. Taken together, FRPN provides a practical route for moving polymer representation learning beyond monomer-centric representations. The leading performance of FRPN also suggests a promising direction for polymer informatics: future polymer prediction models should treat polymers not only as collections of monomer descriptors, but as complete multiscale chemical and topological objects.
