COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy
Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, yet identifying optimal structures among their vast design space requires efficient high-throughput screening. Conventional machine-learning predictors rely heavily on specific gas-related features, which are time-consuming and limit scalability, leading to inefficiency and labor-intensive processes. Here, we propose COFAP, a universal COFs adsorption prediction framework that extracts multi-modal structural and chemical features via deep learning and fuses these complementary features through a cross-modal attention mechanism. Without relying on explicit gas-specific thermodynamic descriptors, COFAP achieves state-of-the-art prediction performance on the hypoCOFs dataset under the conditions investigated, outperforming existing approaches. Based on COFAP, we found that high-performing COFs for gas 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. Superior efficiency and accuracy render COFAP directly deployable in crystalline porous materials.