COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy

TL;DR

COFAP is a universal deep learning framework that predicts gas adsorption in covalent organic frameworks by extracting multi-modal features and using cross-modal attention, outperforming existing methods without relying on gas-specific descriptors.

Contribution

Introduces COFAP, a novel framework combining multi-modal feature extraction and cross-modal attention for efficient, scalable COFs adsorption prediction without gas-specific thermodynamic features.

Findings

Achieves state-of-the-art prediction accuracy on hypoCOFs dataset.

Identifies key pore size and surface area ranges for high-performing COFs.

Provides a flexible ranking scheme for application-specific COF selection.

Abstract

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 relying on explicit gas-specific thermodynamic descriptors, COFAP achieves state-of-the-art prediction performance on the hypoCOFs dataset under the conditions investigated in this study, outperforming existing approaches. Based on COFAP, we also 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 for researchers. Superior efficiency and accuracy render COFAP directly deployable in crystalline porous materials.