Scholarlink

<p>Metal–organic frameworks (MOFs) are porous crystalline materials with strong potential for CO₂ capture because their structures and chemistries are highly tunable. However, their vast compositional and structural search space hampers efficient prediction of adsorption performance. Here we introduce MMAGNN, a multimodal MOF adsorption graph neural network that integrates graph representations and three-dimensional atomic coordinates. MMAGNN employs graph neural networks (GNNs) with attention mechanisms to extract and fuse molecular and spatial features, and incorporates a Transformer-based interpreter to quantify the contribution of individual atoms to adsorption. We find that the multimodal design reduces redundant information and feature interference, improving prediction accuracy and stability. Validation against adsorption density distributions confirms that MMAGNN learns interatomic interactions and pore-structure information and accurately predicts CO₂ adsorption sites. This interpretable framework provides high-throughput screening and rational design of high-performance&#xa0;MOFs for carbon-capture applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Atomic-level interpretable multimodal graph neural network for predicting carbon dioxide adsorption in metal-organic frameworks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月11日

查看全文
  • Yukun Teng,
  • Haoyi Tan,
  • Wei Huang,
  • Guangcun Shan

摘要

Metal–organic frameworks (MOFs) are porous crystalline materials with strong potential for CO₂ capture because their structures and chemistries are highly tunable. However, their vast compositional and structural search space hampers efficient prediction of adsorption performance. Here we introduce MMAGNN, a multimodal MOF adsorption graph neural network that integrates graph representations and three-dimensional atomic coordinates. MMAGNN employs graph neural networks (GNNs) with attention mechanisms to extract and fuse molecular and spatial features, and incorporates a Transformer-based interpreter to quantify the contribution of individual atoms to adsorption. We find that the multimodal design reduces redundant information and feature interference, improving prediction accuracy and stability. Validation against adsorption density distributions confirms that MMAGNN learns interatomic interactions and pore-structure information and accurately predicts CO₂ adsorption sites. This interpretable framework provides high-throughput screening and rational design of high-performance MOFs for carbon-capture applications.