Graph Neural Networks are powerful tools for modeling graph-structured data but their interpretability remains a significant challenge. Existing model-agnostic GNN explainers aim to identify critical subgraphs or node features relevant to task predictions but often rely on GNN predictions for supervision, lacking ground-truth explanations. This limitation can introduce biases, causing explanations to fail in accurately reflecting the GNN's decision-making processes. To address this, we propose a novel explainer for GNNs with graph segmentation and contrastive learning. Our model introduces a graph segmentation learning module to divide the input graph into explanatory and redundant subgraphs. Next, we implement edge perturbation to augment these subgraphs, generating multiple positive and negative pairs for contrastive learning between explanatory and redundant subgraphs. Finally, we develop a contrastive learning module to guide the learning of explanatory and redundant subgraphs by pulling positive pairs with the same explanatory subgraphs closer while pushing negative pairs with different explanatory subgraphs far away. This approach allows for a clearer distinction of critical subgraphs, enhancing the fidelity of the explanations. We conducted extensive experiments on graph classification and node classification tasks, demonstrating the effectiveness of the proposed method.

Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.

Short-tandem repeats (STRs) are the type of genetic markers extensively utilized in biomedical and forensic applications. Due to sequencing noise in nanopore sequencing, accurate analysis methods are lacking. We developed NASTRA, an innovative tool for Nanopore Autosomal Short Tandem Repeat Analysis, which overcomes traditional database-based methods' limitations and provides a precise germline analysis of STR genetic markers without the need for allele sequence reference. Demonstrating high accuracy in cell line authentication testing and paternity testing, NASTRA significantly surpasses existing methods in both speed and accuracy. This advancement makes it a promising solution for rapid cell line authentication and kinship testing, highlighting the potential of nanopore sequencing for in-field applications.

The magnetotelluric (MT) inversion technology is crucial for quantitatively interpreting deep mineral resources, especially when combined with rock physics information, enhancing accuracy in assessing underground structural parameters and spatial distribution. However, the traditional fuzzy c-means (FCMs) clustering-constrained inversion method requires prior rock physics information for each geological unit, limiting their application scope. We propose a guided FCMs (GFCMs) clustering-constrained inversion method based on adaptive virtual rock physics information, referred to as XG-FCM-constrained MT inversion. This method breaks free from the constraints of traditional methods by not relying on prior rock physics information. In terms of extracting virtual rock physics information, we employ a local density clustering algorithm to dynamically extract resistivity model information from MT inversion iterations, automatically determining the number of clusters and cluster centers. Regarding the inversion strategy, we construct an integrated objective function that combines data fitting, smoothing constraint, and GFCM constraint, implementing a two-stage iterative solution strategy of “smoothing first, clustering second.” Model testing demonstrates that compared to traditional smoothing-constrained MT inversion, the XG-FCM-constrained method achieves a significant improvement in the resolution of resistivity model reconstruction, clearly delineating the boundaries of underground anomalies. Even in situations where rock physics information is insufficient or absent, this method can effectively reconstruct high-quality underground resistivity models, reducing the dependence on complete prior information. The application of actual field data further highlights the advantages of the XG-FCM-constrained MT inversion method, providing robust support for accurately delineating geological unit boundaries and precisely identifying potential ore deposit target areas.

Wireless sensor network (WSN) has the characteristics of large-scale, low cost, low power consumption and high network invulnerability, which can meet the needs of large-scale and fast networking of intelligent distribution communication system. Because the sensor nodes in WSN of intelligent distribution network have great differences in computing power, storage space, energy and so on, in order to achieve efficient and reliable communication links, it is more appropriate to use heterogeneous nodes for WSN networking of intelligent distribution network. In this paper, the node design method, node deployment method and network routing protocol of intelligent distribution network WSN based on heterogeneous nodes are systematically studied. The transmission success rate basically meets the demand of more than 80%.