Rapidly tailor metal–organic frameworks for arsenate removal using graph convolutional neural networks

Metal-organic frameworks (MOFs) are effective materials for the removal of highly toxic arsenates (As(V)). However, the intricate structure–activity relationships of MOFs for As(V) removal remain unclear, thus impeding its targeted fabrication. In this work, we used the graph convolutional neural network to integrate MOFs’ chemical composition, physical structure, and adsorption environment, thereby developing an end-to-end predictive model for As(V) adsorption by MOFs. The model's high coefficient of determination, low mean absolute error, and experimental verification of MOFs synthesized based on model predictions not previously used in the As (V) adsorption confirmed the precision and general applicability of the model. Our constructed model identified two key features for adsorption, i.e., metal nodes and pore features, and the modular blocks for constructing MOFs. The strategic design for MOFs to absorb As(V) informed by the model, emphasized integrating open single or binuclear metal nets with aromatic di- or tricarboxylic acid linkers within a robust three-dimensional topological net. This work highlights the integration of predictive modeling and structural refinement to enhance MOF design for As (V) adsorption, even in more other pollutants.