Matching molecular analogues is a computational chemistry and bioinformatics research issue which is used to identify molecules that are structurally or functionally similar to a target molecule. Recent studies on matching analogous molecules have predominantly concentrated on enhancing effectiveness, often sidelining computational efficiency, particularly in contexts of low computational resources. This oversight poses challenges in many real applications (e.g., drug discovery, catalyst generation and so forth). To tackle this issue, we propose a general strategy named MapLE, aiming to promptly match analogous molecules with low computational resources by multi-metrics evaluation. Experimental evaluation conducted on a public biomolecular dataset validates the excellent and efficient performance of the proposed strategy.

This invention discloses a prediction method for docking poses between proteins and ligands based on graph neural networks. Firstly, a dataset of biological information samples of protein-ligand complexes is obtained, including sample data and annotated data. Secondly, docking pose generation models based on graph neural networks and multi-perspective docking pose evaluation models are constructed. The model parameters are further adjusted, and the structural generation model obtained through training is used to process the sample data, obtaining actual outputs of protein-ligand docking poses. Finally, mainstream docking structure evaluation metrics are used to assess the stability of the output results. This invention directly utilizes the biological structural information of ligands and proteins to generate optimal docking pose structures and evaluates the generated results through a comprehensive evaluation model from multiple perspectives. This improves the accuracy of docking pose structure prediction for ligand-protein interactions and enhances the effectiveness of evaluating the prediction results of ligand-protein docking pose structures.