Data-Driven Synthesis of Covalent Organic Frameworks via Machine Learning with Integrated Success–Failure Data
- 1Hainan University , , 58 Renmin Avenue , ,
- 2Shandong University , , ,
Abstract
Covalent organic frameworks (COFs) have emerged as a versatile class of porous materials with promising applications in catalysis, energy storage, and gas adsorption. However, their synthesis remains a major bottleneck primarily due to the widespread reliance on inefficient trial-and-error approaches that waste resources and delay discovery. Herein, we address this challenge by integrating success and failure data: we curated 1822 in-house failed synthesis records and extracted 2603 successful cases from the literature. A random forest machine learning (ML) model, selected for its robustness with complex experimental data sets, achieved 91% accuracy in solvent prediction and demonstrated strong predictive performance for reaction temperature (R2 = 0.9129) and reaction time (R2 = 0.9596), significantly outperforming models trained solely on success-only or trial-and-error data sets. Building on this model, we developed the ML-COF toolkit, which automates the retrieval of known COF synthesis routes and accurately predicts conditions for novel frameworks. Experimental validation, conducted across eight structurally complex and synthetically challenging COFs, including six M(salen)-COFs and two M(Rabson)-COFs, confirmed the toolkit’s high predictive accuracy, with all targets successfully synthesized under predicted conditions. This work establishes a data-driven paradigm for COF synthesis, offering a practical alternative to trial-and-error methods and paving the way for accelerated discovery and future robot-assisted synthesis.
Related
- Ionic Covalent Organic Frameworks for Solid-State Polymer Electrolytes: Synthesis, Ion-Transport Regulation, and Interfacial Stabilization
- Optimizing the synthesis of imine-linked covalent organic frameworks for high surface areas
- Optical-handedness-driven enantioselective synthesis and programmable chirality encoding of covalent organic frameworks
- 异孔共价有机框架气相色谱固定相的制备与应用 Preparation and application of heteroporous covalent organic frameworks as gas chromatography stationary phases
- Precise construction of antiparallel-stacked 2D imine covalent organic frameworks for atmospheric water harvesting
BibTeX
@article{ma2026datadriven,
title = {{Data-Driven Synthesis of Covalent Organic Frameworks via Machine Learning with Integrated Success–Failure Data}},
author = {Bing Ma and Qianqian Yan and Wei Zhou and Junhao Wu and Lipiao Bao and Xinhui Lu and Jixia Qiu and yuanyuan Zhu and Xiao Wang and Dong Zhai and Chengcheng Liu and Sheng Zhang and Wei Deng and Xing Lu},
journal = {JACS Au},
year = {2026},
month = may,
doi = {10.1021/jacsau.6c00493},
url = {https://doi.org/10.1021/jacsau.6c00493},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Data-Driven Synthesis of Covalent Organic Frameworks via Machine Learning with Integrated Success–Failure Data
AU - Bing Ma
AU - Qianqian Yan
AU - Wei Zhou
AU - Junhao Wu
AU - Lipiao Bao
AU - Xinhui Lu
AU - Jixia Qiu
AU - yuanyuan Zhu
AU - Xiao Wang
AU - Dong Zhai
AU - Chengcheng Liu
AU - Sheng Zhang
AU - Wei Deng
AU - Xing Lu
PY - 2026
DA - 2026/05/20
JO - JACS Au
DO - 10.1021/jacsau.6c00493
UR - https://doi.org/10.1021/jacsau.6c00493
AB - Covalent organic frameworks (COFs) have emerged as a versatile class of porous materials with promising applications in catalysis, energy storage, and gas adsorption. However, their synthesis remains a major bottleneck primarily due to the widespread reliance on inefficient trial-and-error approaches that waste resources and delay discovery. Herein, we address this challenge by integrating success and failure data: we curated 1822 in-house failed synthesis records and extracted 2603 successful cases from the literature. A random forest machine learning (ML) model, selected for its robustness with complex experimental data sets, achieved 91% accuracy in solvent prediction and demonstrated strong predictive performance for reaction temperature (R2 = 0.9129) and reaction time (R2 = 0.9596), significantly outperforming models trained solely on success-only or trial-and-error data sets. Building on this model, we developed the ML-COF toolkit, which automates the retrieval of known COF synthesis routes and accurately predicts conditions for novel frameworks. Experimental validation, conducted across eight structurally complex and synthetically challenging COFs, including six M(salen)-COFs and two M(Rabson)-COFs, confirmed the toolkit’s high predictive accuracy, with all targets successfully synthesized under predicted conditions. This work establishes a data-driven paradigm for COF synthesis, offering a practical alternative to trial-and-error methods and paving the way for accelerated discovery and future robot-assisted synthesis.
SN - 2691-3704
ER -