Jiafei Liu

Cancer is a global public health problem that poses a huge threat to human life and health. The identification of cancer driver genes helps to discover the intrinsic mechanisms of cancer occurrence and development. Existing deep learning-based methods for identifying cancer driver genes are mainly biased towards local structure reconstruction, limiting the global learning. In order to increase the identification capacity of cancer driver genes, in this study, a new cancer driver genes prediction method VGDriver using Vision Transformer(ViT) and hierarchical feature fusion module is proposed. Its steps are as follows: firstly, the gene expression, copy number aberrations, and single nucleotide variations data are used to construct a gene property feature matrix; secondly, a new hierarchical feature fusion module is designed, which can perform a two-pipeline fusion of multi-omics features to obtain a multi-source feature matrix by co-designing the graph convolutional networks block and the multilayer perceptron block; finally, the multi-source feature matrix is input into ViT to train and perform the task of predicting cancer driver genes. The results of comparative experiments on five different protein-protein interaction datasets for pan-cancer and eight single cancer types show that the VGDriver method is better compared to seven representative methods in the evaluation metrics AUC and AUPR.

As critical reliability metrics for multiprocessor systems, connectivity and diagnosability respectively determine network robustness against node failures and the capability to accurately identify faulty units. This article presents a comprehensive reliability analysis of bubble-sort networks (B_n), a class of Cayley graphs that implement adjacent-node swap operations, offering inherent advantages for distributed sorting systems. First, we investigate the h-extra r-component connectivity and diagnosability of B_n under the Preparata-Metze-Chien (PMC) diagnostic model through rigorous topological analysis. Then, we characterize the g-good-neighbor r-component connectivity and diagnosability of B_n under the PMC model by establishing tight bounds through fault pattern analysis. In addition, we develop a three-round fault identification algorithm, TRFI-PMC, that achieves robust diagnostic performance in simulated experiments. Specifically, for the network B₈ with 40320 nodes, the algorithm maintains superior performance (fault density achieving 25%) across five metrics: accuracy (98.81%), true negative rate (97.81%), false positive rate (2.18%), true positive rate (99.3%), and precision (98.98%). The theoretical results establish fundamental reliability limits for B_n architectures, while the practical algorithm provides an efficient fault diagnosis solution for n-dimensional bubble-sort network.