COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy
This work addresses the inefficiency and labor-intensive nature of high-throughput screening for COFs in gas adsorption and separation, offering a deployable solution for researchers in materials science.
The authors tackled the problem of efficiently screening covalent organic frameworks (COFs) for gas adsorption by developing COFAP, a universal framework that uses deep learning to extract multi-modal features and cross-modal attention, achieving new state-of-the-art performance on the hypoCOFs dataset without relying on gas-specific features.
Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, while identifying the optimal structures among their vast design space requires efficient high-throughput screening. Conventional machine-learning predictors rely heavily on specific gas-related features. However, these features are time-consuming and limit scalability, leading to inefficiency and labor-intensive processes. Herein, a universal COFs adsorption prediction framework (COFAP) is proposed, which can extract multi-modal structural and chemical features through deep learning, and fuse these complementary features via cross-modal attention mechanism. Without Henry coefficients or adsorption heat, COFAP sets a new SOTA by outperforming previous approaches on hypoCOFs dataset. Based on COFAP, we also found that high-performing COFs for separation concentrate within a narrow range of pore size and surface area. A weight-adjustable prioritization scheme is also developed to enable flexible, application-specific ranking of candidate COFs for researchers. Superior efficiency and accuracy render COFAP directly deployable in crystalline porous materials.