文献类型：期刊文献

英文题名：CIF2MOFNet: A deep learning model with multi-dimensional coordinate features to accelerate MOF screening for CO2 capture

作者：Chen, Shounian[1];Chen, Yan[2];Zhu, Zutao[1];Wang, Zihao[1];Zhang, Xiangping[3];Li, Zhongmei[4];Du, Wenli[4];Chang, Chenglin[1];Shen, Weifeng[1]

机构：[1]Chongqing Univ, Sch Chem & Chem Engn, Chongqing 400044, Peoples R China;[2]Univ Edinburgh, Inst Mat & Proc, Sch Engn, Edinburgh, Scotland;[3]China Univ Petr, Coll Chem Engn & Environm, Beijing, Peoples R China;[4]East China Univ Sci & Technol, State Key Lab Ind Control Technol, Minist Educ, Shanghai, Peoples R China

年份：2026

卷号：72

期号：4

外文期刊名：AICHE JOURNAL

收录：;EI(收录号：20255019682485);WOS:【SCI-EXPANDED(收录号:WOS:001632073800001)】；

基金：National Natural Science Foundation of China, Grant/Award Number: 22278044; Chongqing Science Fund for Distinguished Young Scholars, Grant/Award Number: CSTB2022NSCQ-JQX0021; Chongqing Innovation Support Key Program for Returned Overseas Chinese Scholars, Grant/Award Number: CX2023002; Key Project of Technical Innovation and Application Development, Grant/Award Number: CSTB2024TIAD-KPX0058; Science and Technology Innovation Key R&D Program of Chongqing, Grant/Award Number: CSTB2024TIAD-STX0032; Xinjiang Autonomous Region Regional Collaborative Innovation Special Science and Technology Assistance Plan Project, Grant/Award Number: 2024E02036; Open Research Project of the State Key Laboratory of Industrial Control Technology, Grant/Award Number: ICT2024B01

语种：英文

外文关键词：CIF-driven screening; CO2 capture; deep learning; end-to-end model; metal-organic framework

摘要：Metal-organic frameworks (MOFs) are promising adsorbents for carbon capture, while their structural complexity poses challenges for rapid screening. This study develops a novel deep learning model, CIF2MOFNet, which predicts CO2 working capacity and CO2/N2 selectivity of MOFs directly from their crystallographic information files (CIFs). In addition to the 2D structural projections used in previous methods, CIF2MOFNet incorporates an innovative 1D representation derived from atomic coordinates. This hybrid strategy effectively captures crucial spatial distributions and elemental compositions, which have often been overlooked in 2D simplifications. Thus, CIF2MOFNet achieves a significantly higher predictive accuracy, while circumventing the computational complexity associated with full 3D structural representations. Trained on 342,489 MOFs, CIF2MOFNet efficiently screens 7426 experimentally synthesized MOFs and identifies 321 high-performance candidates, reducing computation time per MOF from 7393 s to just 0.021 s while maintaining strong predictive performance. Structural analysis of top candidates highlights that key adsorption-related characteristics, including optimal pore size and functional group types, are linked to superior CO2 adsorption performance, demonstrating strong potential for accelerating MOF discovery and guiding rational MOF design for efficient CO2 capture. As an end-to-end model using CIF directly, CIF2MOFNet offers a universal strategy for rapid, high-throughput screening across any potential nanoporous material database with CIF data, providing valuable insights for the design of next-generation adsorbents.