Search

Saxitoxin (STX), an exceptionally potent marine toxin for which no antidote is currently available, is produced by methanogens and cyanobacteria. This poses a significant threat to both shellfish aquaculture and human health. Consequently, the development of a rapid, highly sensitive STX detection method is of great significance. The objective of this research is to create a novel approach for identifying STX. Therefore, amplified luminescent proximity homogeneous assay (AlphaLISA) was established using a direct competition method based on the principles of fluorescence resonance energy transfer and antigen–antibody specific binding. This method is sensitive, rapid, performed without washing, easy to operate, and can detect 8–128 ng/mL of STX in only 10 min. The limit of detection achieved by this method is as low as 4.29 ng/mL with coefficients of variation for the intra-batch and inter-batch analyses ranging from 2.61% to 3.63% and from 7.67% to 8.30%, respectively. In conclusion, our study successfully establishes a simple yet sensitive, rapid, and accurate AlphaLISA method for the detection of STX which holds great potential in advancing research on marine biotoxins. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNN), which extend deep neural networks to non-Euclidean data, have been proven to be powerful for numerous graph related tasks such as node classification, link prediction, and graph classification. On the task of graph classification, recent studies aim to learn graph-level representation through a hierarchical pooling procedure using the local and global structure information of the graph. After comparing and analyzing the current graph classification model, this paper proposes the structure and feature fusion pooling model (SAFPool) considering shortcomings of the current method and combining the advantages of different methods. SAFPool utilizes Graphtwo assignment matrix generation modules during the pooling process, which are structure-based cluster learning and feature- based cluster learning modules. Structure- based cluster learning module clusters nodes with similar structures based on graph structure information, and feature- based cluster learning clusters nodes with similar features based on graph node features. Then the two clustering assignment matrices are weighted and aggregated to obtain the clustering assignment matric which implements the clustering strategy to utilize graph structure and node feature information at the same time. Finally, comparative experiments and visualization on multiple graph classification datasets demonstrate the effectiveness of using graph node information and structure information to implement a clustering strategy in graph classification. [ABSTRACT FROM AUTHOR]