Dimer-structure Embedding: A Bridge Toward Accurate Performance Prediction of Covalent Organic Frameworks

Zi-yi Cheng; Xi-ni Chu; Qian-qian Yan; Liang Zhang

doi:10.11777/j.issn1000-3304.2026.26189

您当前的位置：

首页 >

文章列表页 >

Dimer-structure Embedding: A Bridge Toward Accurate Performance Prediction of Covalent Organic Frameworks

Review | 更新时间：2026-11-03

- Dimer-structure Embedding: A Bridge Toward Accurate Performance Prediction of Covalent Organic Frameworks
- Acta Polymerica Sinica Pages: 1-10(2026)
- 作者机构：
  
  中国科学技术大学化学物理系精准智能化学全国重点实验室合肥 230026
- 作者简介：
- 基金信息：
- DOI：10.11777/j.issn1000-3304.2026.26189
  CLC：
- Received：29 May 2026，
  
  Accepted：18 August 2026，
  
  Online First：03 November 2026，
- 稿件说明：
移动端阅览
程紫怡, 储悉尼, 闫欠欠, 张亮. 二聚体结构嵌入：实现共价有机框架性能精准预测的桥梁. 高分子学报, doi: 10.11777/j.issn1000-3304.2026.26189.

Cheng, Z. Y.; Chu, X. N.; Yan, Q. Q.; Zhang, L. Dimer-structure embedding: a bridge toward accurate performance prediction of covalent organic frameworks. Acta Polymerica Sinica (in Chinese), doi: 10.11777/j.issn1000-3304.2026.26189.
程紫怡, 储悉尼, 闫欠欠, 张亮. 二聚体结构嵌入：实现共价有机框架性能精准预测的桥梁. 高分子学报, doi: 10.11777/j.issn1000-3304.2026.26189. DOI： CSTR： 32057.14.GFZXB.2026.7718.

Cheng, Z. Y.; Chu, X. N.; Yan, Q. Q.; Zhang, L. Dimer-structure embedding: a bridge toward accurate performance prediction of covalent organic frameworks. Acta Polymerica Sinica (in Chinese), doi: 10.11777/j.issn1000-3304.2026.26189. DOI： CSTR： 32057.14.GFZXB.2026.7718.

摘要

共价有机框架(COFs)的光学与催化性能高度依赖于骨架组装过程中产生的电子结构协同效应，然而仅凭单体的本征性质难以准确预测框架的宏观性能，这一问题已成为制约COFs理性设计的核心瓶颈. 近年来，人工智能(AI)被广泛引入COFs性能预测，但现有模型多以单体分子描述符为输入，难以捕捉组装过程中的轨道重组与电荷转移等关键效应，导致预测精度和化学可解释性受限. 针对这一问题，本综述系统阐述一种基于二聚体电子结构嵌入的AI预测策略. 该策略以醛单体与胺单体通过亚胺键连接形成的二聚体作为中间表征，利用其所包含的局域成键、前线轨道耦合、激发态电荷分布等信息，有效桥接单体结构与框架性能之间的认知断层. 本综述首先剖析单体与框架预测偏差的物理本质，阐明二聚体作为中间表征的化学合理性；继而总结基于二聚体描述符的AI模型构建方法；随后以发光COFs与光催化COFs为例展示该策略的应用；最后讨论当前面临的挑战与发展方向.

Abstract

The optical and catalytic properties of covalent organic frameworks (COFs) are highly dependent on electronic-structure synergy arising during framework assembly. However

the intrinsic properties of isolated monomers alone are often insufficient for accurately predicting the macroscopic performance of the resulting frameworks

which has become a central bottleneck in the rational design of COFs. In recent years

artificial intelligent (AI) has been widely introduced into COF performance prediction. Nevertheless

most existing models use molecular descriptors of monomers as inputs and therefore struggle to capture key assembly-induced effects such as orbital reorganization and charge transfer

resulting in limited predictive accuracy and chemical interpretability. To address this issue

this article systematically describes an AI prediction strategy based on dimer electronic-structure embedding. In this strategy

the dimer formed by connecting aldehyde and amine monomers through an imine linkage is used as an intermediate representation. By incorporating information on local bonding

frontier-orbital coupling

excited-state charge distribution

and related electronic features

this representation effectively bridges the cognitive gap between monomer structures and framework-level properties. This article first analyzes the physical origin of the prediction discrepancy between monomers and frameworks and clarifies the chemical rationale for using dimers as intermediate representations. It then summarizes AI model construction based on dimer descriptors

illustrates the application of this strategy using luminescent COFs and photocatalytic COFs as examples

and finally discusses current challenges and future perspectives.

关键词

Keywords

references

Liu W. ; Zhang Y. N. ; Wang J. ; Shang X. B. ; Zhang C. X. ; Wang Q. L. Advances of functionalized bipyridine-based covalent-organic frameworks for boosting photocatalysis . Coord. Chem. Rev. , 2024 , 516 , 215997 . doi: 10.1016/j.ccr.2024.215997 http://dx.doi.org/10.1016/j.ccr.2024.215997

Huang Y. ; Hao X. Q. ; Ma S. L. ; Wang R. ; Wang Y. Z. Covalent organic framework-based porous materials for harmful gas purification . Chemosphere , 2022 , 291 , 132795 . doi: 10.1016/j.chemosphere.2021.132795 http://dx.doi.org/10.1016/j.chemosphere.2021.132795

Zhou W. ; Deng W. Q. ; Lu X. Metallosalen covalent organic frameworks for heterogeneous catalysis . Interdiscip. Mater. , 2024 , 3 ( 1 ), 87 - 112 . doi: 10.1002/idm2.12140 http://dx.doi.org/10.1002/idm2.12140

Zhan X. P. ; Guan S. Q. ; Wang Y. P. ; Shen J. ; Pan M. Luminescent hydrogen bonded frameworks (HOFs) and covalent organic frameworks (COFs) for biomedical applications . Coord. Chem. Rev. , 2026 , 551 , 217453 . doi: 10.1016/j.ccr.2025.217453 http://dx.doi.org/10.1016/j.ccr.2025.217453

Tan K. T. ; Ghosh S. ; Wang Z. Y. ; Wen F. X. ; Rodríguez-San-Miguel D. ; Feng J. ; Huang N. ; Wang W. ; Zamora F. ; Feng X. L. ; Thomas A. ; Jiang D. L. Covalent organic frameworks . Nat. Rev. Meth. Primers , 2023 , 3 , 1 . doi: 10.1038/s43586-022-00181-z http://dx.doi.org/10.1038/s43586-022-00181-z

Liu Y. K. ; Liu X. N. ; Su A. ; Gong C. T. ; Chen S. W. ; Xia L. W. ; Zhang C. W. ; Tao X. H. ; Li Y. ; Li Y. H. ; Sun T. L. ; Bu M. R. ; Shao W. ; Zhao J. ; Li X. N. ; Peng Y. W. ; Guo P. ; Han Y. ; Zhu Y. H. Revolutionizing the structural design and determination of covalent-organic frameworks: principles, methods, and techniques . Chem. Soc. Rev. , 2024 , 53 ( 1 ), 502 - 544 . doi: 10.1039/d3cs00287j http://dx.doi.org/10.1039/d3cs00287j

Jindal S. ; Wang J. X. ; Wang Y. ; Thomas S. ; Mallick A. ; Bonneau M. ; Bhatt P. M. ; Alkhazragi O. ; Nadinov I. ; Ng T. K. ; Shekhah O. ; Alshareef H. N. ; Ooi B. S. ; Mohammed O. F. ; Eddaoudi M. Aggregation induced emission-based covalent organic frameworks for high-performance optical wireless communication . J. Am. Chem. Soc. , 2024 , 146 ( 37 ), 25536 - 25543 . doi: 10.1021/jacs.4c05812 http://dx.doi.org/10.1021/jacs.4c05812

Yang M. J. ; Hanayama H. ; Fang L. ; Addicoat M. A. ; Guo Y. Y. ; Graf R. ; Harano K. ; Kikkawa J. ; Jin E. Q. ; Narita A. ; Müllen K. Saturated linkers in two-dimensional covalent organic frameworks boost their luminescence . J. Am. Chem. Soc. , 2023 , 145 ( 26 ), 14417 - 14426 . doi: 10.1021/jacs.3c03614 http://dx.doi.org/10.1021/jacs.3c03614

徐静 , 陈天泽 , 邵明超 , 郭云龙 , 张新瑞 , 王廷梅 . 具有鲁棒性机械性能和高弹性的超长室温磷光共价有机框架弹性体 . 高分子学报 , 2024 , 55 ( 6 ), 709 - 717 .

Cheng M. Y. ; Fu C. L. ; Okabe R. ; Chotrattanapituk A. ; Boonkird A. ; Hung N. T. ; Li M. D. Artificial intelligence-driven approaches for materials design and discovery . Nat. Mater. , 2026 , 25 ( 2 ), 174 - 190 . doi: 10.1038/s41563-025-02403-7 http://dx.doi.org/10.1038/s41563-025-02403-7

Szymanski N. J. ; Rendy B. ; Fei Y. X. ; Kumar R. E. ; He T. J. ; Milsted D. ; McDermott M. J. ; Gallant M. ; Cubuk E. D. ; Merchant A. ; Kim H. ; Jain A. ; Bartel C. J. ; Persson K. ; Zeng Y. ; Ceder G. An autonomous laboratory for the accelerated synthesis of inorganic materials . Nature , 2023 , 624 ( 7990 ), 86 - 91 . doi: 10.1038/s41586-023-06734-w http://dx.doi.org/10.1038/s41586-023-06734-w

Kang Y. ; Park H. ; Smit B. ; Kim J. A multi-modal pre-training transformer for universal transfer learning in metal-organic frameworks . Nat. Mach. Intell. , 2023 , 5 ( 3 ), 309 - 318 . doi: 10.1038/s42256-023-00628-2 http://dx.doi.org/10.1038/s42256-023-00628-2

Wang D. Y. ; Lv H. F. ; Wan Y. Y. ; Wu X. J. ; Yang J. L. Band-edge prediction of 2D covalent organic frameworks from molecular precursor via machine learning . J. Phys. Chem. Lett. , 2023 , 14 ( 30 ), 6757 - 6764 . doi: 10.1021/acs.jpclett.3c01419 http://dx.doi.org/10.1021/acs.jpclett.3c01419

Kumar S. ; Ignacz G. ; Szekely G. Synthesis of covalent organic frameworks using sustainable solvents and machine learning . Green Chem. , 2021 , 23 ( 22 ), 8932 - 8939 . doi: 10.1039/d1gc02796d http://dx.doi.org/10.1039/d1gc02796d

Zhang L. ; Du J. H. ; Xie Z. K. ; Chen L. J. ; Li W. L. ; Geng W. H. ; Zhou Y. ; Ou X. W. ; Gong C. T. ; Gao Y. J. ; He S. ; Yan C. X. ; Zhao C. B. ; Jiao Y. T. ; Yang S. Y. ; Huang B. ; Lam J. W. Y. ; Qian J. ; Jiang J. ; Tang B. Z. ; Deng H. X. Discovery of highly fluorescent covalent organic frameworks through AI-assisted iterative experiment-learning cycles . Nat. Chem. , 2025 , 17 ( 11 ), 1645 - 1654 . doi: 10.1038/s41557-025-01974-x http://dx.doi.org/10.1038/s41557-025-01974-x

Jia X. K. ; Chen L. ; Xiong K. ; Wang Y. J. ; Zhou L. J. ; Xu X. H. ; Li S. ; Wang M. ; Thomas A. ; Cheng C. Machine learning-accelerated discovery of covalent organic frameworks for hydrogen peroxide photosynthesis . Nat. Synth. , 2026 , 5 ( 8 ), 1242 - 1253 . doi: 10.1038/s44160-026-01037-0 http://dx.doi.org/10.1038/s44160-026-01037-0

Ding C. C. ; Xie X. Y. ; Chen L. J. ; Troisi A. Intuitive and efficient approach to determine the band structure of covalent organic frameworks from their chemical constituents . J. Chem. Theory Comput. , 2024 , 20 ( 3 ), 1252 - 1262 . doi: 10.1021/acs.jctc.3c01302 http://dx.doi.org/10.1021/acs.jctc.3c01302

Rawat K. S. ; Borgmans S. ; Braeckevelt T. ; Stevens C. V. ; Van Der Voort P. ; Van Speybroeck V. How the layer alignment in two-dimensional nanoporous covalent organic frameworks impacts its electronic properties . ACS Appl. Nano Mater. , 2022 , 5 ( 10 ), 14377 - 14387 . doi: 10.1021/acsanm.2c02647 http://dx.doi.org/10.1021/acsanm.2c02647

Winkler C. ; Kamencek T. ; Zojer E. Understanding the origin of serrated stacking motifs in planar two-dimensional covalent organic frameworks . Nanoscale , 2021 , 13 ( 20 ), 9339 - 9353 . doi: 10.1039/d1nr01047f http://dx.doi.org/10.1039/d1nr01047f

Zhan G. L. ; Koek B. ; Yuan Y. J. ; Liu Y. K. ; Mishra V. ; Lenzi V. ; Strutyński K. ; Li C. X. ; Zhang R. R. ; Zhou X. ; Choi H. S. ; Cai Z. F. ; Almarza J. ; Mali K. S. ; Mateo-Alonso A. ; Franco M. M. ; Zhu Y. H. ; De Feyter S. ; Loh K. P. Moiré two-dimensional covalent organic framework superlattices . Nat. Chem. , 2025 , 17 ( 4 ), 518 - 524 . doi: 10.1038/s41557-025-01748-5 http://dx.doi.org/10.1038/s41557-025-01748-5

Zhang L. ; Geng W. H. ; Ou X. W. ; He S. ; He X. H. ; Li W. L. ; Jiao Y. T. ; Cheng Z. Y. ; Jin Z. Y. ; Qian J. ; Tang B. Z. Boosting the brightness of aggregation-caused quenching chromophore-based covalent organic frameworks via energy level matching strategy . Nat. Commun. , 2025 , 16 , 9991 . doi: 10.1038/s41467-025-64952-4 http://dx.doi.org/10.1038/s41467-025-64952-4

Hayes S. C. ; Silva C. Analysis of the excited-state absorption spectral bandshape of oligofluorenes . J. Chem. Phys. , 2010 , 132 ( 21 ), 214510 . doi: 10.1063/1.3432602 http://dx.doi.org/10.1063/1.3432602

Sarkar R. ; Boggio-Pasqua M. ; Loos P. F. ; Jacquemin D. Benchmarking TD-DFT and wave function methods for oscillator strengths and excited-state dipole moments . J. Chem. Theory Comput. , 2021 , 17 ( 2 ), 1117 - 1132 . doi: 10.1021/acs.jctc.0c01228 http://dx.doi.org/10.1021/acs.jctc.0c01228

Herbert J. M. Visualizing and characterizing excited states from time-dependent density functional theory . Phys. Chem. Chem. Phys. , 2024 , 26 ( 5 ), 3755 - 3794 . doi: 10.1039/d3cp04226j http://dx.doi.org/10.1039/d3cp04226j

Grimme S. ; Ehrlich S. ; Goerigk L. Effect of the damping function in dispersion corrected density functional theory . J. Comput. Chem. , 2011 , 32 ( 7 ), 1456 - 1465 . doi: 10.1002/jcc.21759 http://dx.doi.org/10.1002/jcc.21759

Weigend F. ; Ahlrichs R. Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: design and assessment of accuracy . Phys. Chem. Chem. Phys. , 2005 , 7 ( 18 ), 3297 .

Yanai T. ; Tew D. P. ; Handy N. C. A new hybrid exchange-correlation functional using the Coulomb-attenuating method (CAM-B3LYP) . Chem. Phys. Lett. , 2004 , 393 ( 1-3 ), 51 - 57 . doi: 10.1016/j.cplett.2004.06.011 http://dx.doi.org/10.1016/j.cplett.2004.06.011

Chai J. D. ; Head-Gordon M. Long-range corrected hybrid density functionals with damped atom-atom dispersion corrections . Phys. Chem. Chem. Phys. , 2008 , 10 ( 44 ), 6615 - 6620 . doi: 10.1039/b810189b http://dx.doi.org/10.1039/b810189b

Tomasi J. ; Mennucci B. ; Cammi R. Quantum mechanical continuum solvation models . Chem. Rev. , 2005 , 105 ( 8 ), 2999 - 3094 . doi: 10.1021/cr9904009 http://dx.doi.org/10.1021/cr9904009

Marenich A. V. ; Cramer C. J. ; Truhlar D. G. Universal solvation model based on solute electron density and on a continuum model of the solvent defined by the bulk dielectric constant and atomic surface tensions . J. Phys. Chem. B , 2009 , 113 ( 18 ), 6378 - 6396 . doi: 10.1021/jp810292n http://dx.doi.org/10.1021/jp810292n

Pracht P. ; Bohle F. ; Grimme S. Automated exploration of the low-energy chemical space with fast quantum chemical methods . Phys. Chem. Chem. Phys. , 2020 , 22 ( 14 ), 7169 - 7192 . doi: 10.1039/c9cp06869d http://dx.doi.org/10.1039/c9cp06869d

Axelrod S. ; Gómez-Bombarelli R. GEOM, energy-annotated molecular conformations for property prediction and molecular generation . Sci. Data , 2022 , 9 , 185 . doi: 10.1038/s41597-022-01288-4 http://dx.doi.org/10.1038/s41597-022-01288-4

Dunn A. ; Wang Q. ; Ganose A. ; Dopp D. ; Jain A. Author Correction: Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm . npj Comput. Mater. , 2020 , 6 , 159 . doi: 10.1038/s41524-020-00433-0 http://dx.doi.org/10.1038/s41524-020-00433-0

Sardeshmukh A. ; Reddy S. ; Gautham B. P. ; Bhattacharyya P. Microstructure representation learning using Siamese networks . MRS Commun. , 2020 , 10 ( 4 ), 613 - 619 . doi: 10.1557/mrc.2020.55 http://dx.doi.org/10.1557/mrc.2020.55

Mandal N. ; Maniscalco J. ; Aindow M. ; Yang Q. Siamese graph neural networks for melting temperature prediction of molten salt eutectics . Digit. Discov. , 2026 , 5 ( 4 ), 1689 - 1699 . doi: 10.1039/d5dd00480b http://dx.doi.org/10.1039/d5dd00480b

Hadsell R. ; Chopra S. ; LeCun Y. Dimensionality reduction by learning an invariant mapping . Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Volume 2 . ACM , 2006, 1735 - 1742 . doi: 10.1109/cvpr.2006.100 http://dx.doi.org/10.1109/cvpr.2006.100

Schroff F. ; Kalenichenko D. ; Philbin J. FaceNet: a unified embedding for face recognition and clustering . 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston , MA, USA , 2015 : 815 - 823 . doi: 10.1109/cvpr.2015.7298682 http://dx.doi.org/10.1109/cvpr.2015.7298682

Kanarik K. J. ; Osowiecki W. T. ; Lu Y. J. ; Talukder D. ; Roschewsky N. ; Park S. N. ; Kamon M. ; Fried D. M. ; Gottscho R. A. Human-machine collaboration for improving semiconductor process development . Nature , 2023 , 616 ( 7958 ), 707 - 711 .

Snapp K. L. ; Verdier B. ; Gongora A. E. ; Silverman S. ; Adesiji A. D. ; Morgan E. F. ; Lawton T. J. ; Whiting E. ; Brown K. A. Superlative mechanical energy absorbing efficiency discovered through self-driving lab-human partnership . Nat. Commun. , 2024 , 15 , 4290 .

赵文凯 , 李升旭 , 付广恩 , 张涛 . 二维sp 2 -碳共轭聚合物的结构设计、可控制备与应用研究 . 高分子学报 , 2024 , 55 ( 5 ), 532 - 552 .

Evans A. M. ; Giri A. ; Sangwan V. K. ; Xun S. N. ; Bartnof M. ; Torres-Castanedo C. G. ; Balch H. B. ; Rahn M. S. ; Bradshaw N. P. ; Vitaku E. ; Burke D. W. ; Li H. ; Bedzyk M. J. ; Wang F. ; Brédas J. L. ; Malen J. A. ; McGaughey A. J. H. ; Hersam M. C. ; Dichtel W. R. ; Hopkins P. E. Thermally conductive ultra-low-k dielectric layers based on two-dimensional covalent organic frameworks . Nat. Mater. , 2021 , 20 ( 8 ), 1142 - 1148 . doi: 10.1038/s41563-021-00934-3 http://dx.doi.org/10.1038/s41563-021-00934-3

Oganov A. R. ; Glass C. W. Crystal structure prediction using ab initio evolutionary techniques: principles and applications . J. Chem. Phys. , 2006 , 124 ( 24 ), 244704 .

Unke O. T. ; Chmiela S. ; Sauceda H. E. ; Gastegger M. ; Poltavsky I. ; Schütt K. T. ; Tkatchenko A. ; Müller K. R. Machine learning force fields . Chem. Rev. , 2021 , 121 ( 16 ), 10142 - 10186 . doi: 10.1021/acs.chemrev.0c01111 http://dx.doi.org/10.1021/acs.chemrev.0c01111

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Liquid-phase Exfoliation of Pyridine-based Covalent Organic Framework Nanosheets for High-performance H2/CO2 Gas Separation Membrane Fabrication

Ultra-fast Supercritically-solvothermal Polymerization for Large-sized Covalent Organic Framework Single Crystals

Zinc Porphyrin-based Covalent Organic Framework and Conjugated Microporous Polymer as Heterogeneous Photocatalysts for Reversible Addition-fragmentation Chain Transfer Polymerization

Recent Progress of Aggregation-induced Emission Molecular Oligomers

Machine Learning Predictive Models for the Tensile Properties of Polyethylene and Polypropylene

Related Author

Yao-zu Liao

Wei-yi Zhang

Hong-yu Zuo

Da-cheng Wei

Lan Peng

Jiang Sun

Yao Wei

Yu-guo Ma

Related Institution

College of Materials Science and Engineering, Donghua University, State Key Laboratory for Modification of Chemical Fibers and Polymer Materials

State Key Laboratory of Molecular Engineering of Polymers, Department of Macromolecular Science, Fudan University

Beijing National Laboratory for Molecular Sciences, Key Laboratory of Polymer Chemistry and Physics of Ministry of Education, Center for Soft Matter Science and Engineering, College of Chemistry and Molecular Engineering, Peking University

Shanghai Institute of Applied Physics, Chinese Academy of Sciences

University of Chinese Academy of Sciences

Address：Zhongguancun North First Street 2, Haidian District, 100190 Beijing, PR China Postal code：100190
Tel：15652467851 Email：cjps@iccas.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05002796号-5 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰