Jingli Wu

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.

Essential proteins are a crucial component of living organisms, and their absence will lead to cell death or reproductive arrest. Discovering these proteins can propel advancements in synthetic biology and facilitate the development of novel antibiotics and therapies for various diseases. However, current computational methods suffer from two major drawbacks that hinder their discovery rate: one is the significant noise in protein-protein interaction (PPI) data, and the other is the inadequate consideration of feature relationships. To enhance identification capabilities, this study proposes a novel essential protein prediction method, Feature Synergy Method (FSM), which leverages a features synergy model and GO pure centrality. The FSM is described as folows:Firstly, based on the principle of co-expression, gene expression data are integrated with the original PPI network to construct a pure PPI network (PPIN). Subsequently, GO annotation data are employed to calculate GO_sim weights for the interactions within the original PPI network, forming a GS_PIN. The PPIN and GS_PIN are then fused to establish the GS_PPIN, which helps mitigate the impact of noise in PPI data. Secondly, a new centrality measure, GO pure centrality (GPC), is designed based on this GO similarity-weighted pure PPI network. Thirdly, an evolutionary conservation score (ECS) is extracted from subcellular localization and orthologous proteins data. Fourthly, after analyzing the relationship between GPC and ECS, a novel fusion model, the features synergy model, is developed to integrate GPC and ECS, ultimately leading to the proposal of the new essential protein prediction method, FSM. To validate the performance of FSM, six computational methods (PeC, WDC, ION, NCCO, E_POC, and JDC) and six centrality measures (NC, IC, EC, SC, CC, and DC) were evaluated on three distinct yeast datasets. The results demonstrate that FSM achieves a higher essential protein identification rate. Similarly, GPC identifies more essential proteins compared to the six centrality-based approaches (NC, IC, EC, SC, CC, and DC).

Essential proteins are fundamental to the reproduction and survival of cells, and if they are killed, the cells will stop reproducing or die. Many computational methods of identifying essential proteins are proposed which fuse a large number of features from multi-omics data. Some of them extract features from subcellular localization data by subjectively selecting certain subcellular locations. Meanwhile, there is still room to improve the identification rate of essential proteins. In this paper, a new deep learning framework for identifying essential proteins based on Vision Transformer is proposed, named EPViT. Firstly, topological features are extracted from the protein-protein interaction network. Secondly, a feature matrix is designed from the subcellular localization information without subjective factor. Then, the two classes of features are fused into a new feature matrix by outer product operation. Finally, the new feature matrix is input into the Vision Transformer model to discover essential proteins. The results show that EPViT has the highest recognition rate among the comparison experiments on yeast data.

Identifying cancer driver pathways is crucial for elucidating tumorigenesis and the progression of cancer. The vast accumulation of omics data now enables the use of computational approaches to infer these pathways. In the currently proposed identification methods, the gene set with "dominant" genes (mutating in most of the samples) may be captured. Although the "dominant" genes are usually driver genes, their absolute predominance of mutations in cancer samples may lead to the other genes within the set are not cancer driver genes at all. In this article, a parameter-free identification model MCMS (Maximizing Coverage, Mutual exclusivity, and Subnet importance) is proposed, which employs a novel mutual exclusivity metric to exclude the gene set with "dominant" genes (i.e., eliminating bias toward predominant mutations). A competitive coevolution algorithm CCA is devised to solve the model (CCA-MCMS), it implements an effective population fitness function that dynamically regulates inter-population competition to preserve population diversity. The gene sets derived from the proposed CCA-MCMS method demonstrate both superior enrichment in biological signaling pathways and increased connectivity in the HINT-HI2012 network, relative to sets identified by other prominent approaches. The demonstrated computational efficiency of CCA-MCMS further supports its use in practical biomarker discovery tasks.

With the scale of multiprocessor systems constantly increasing, the large number of interconnected processors (or nodes) makes faulty nodes inevitable. The fault diagnosis of multiprocessor systems therefore is a key technique for the system’s robustness. In this paper, we first propose a novel diagnostic metric, the $h$ -extra $r$ -component diagnosability, denoted $ECD^{h}_{r}(G)$ , which characterizes one special pattern of faults. We derive some theoretical results for the ECD of hypercube, denoted $ECD^{h}_{r}(Q_{n})$ , under the PMC model. Diagnostic algorithms is proposed and implemented to detect faulty nodes that will disconnect hypercube $Q_{n}$ into $r$ components each containing at least $h+1$ nodes. We also test the ECD-PMC algorithm to the hypercube network with different number of faulty processors satisfying the $h$ -extra $r$ -component condition. Extensive simulation results show that our proposed method achieves very good performance in terms of ACCR, TPR, FPR, and TNR.

The proliferation of interconnection networks has intensified the demand for robust fault diagnosis methodologies. Although existing research focuses predominantly on single-condition diagnosability metrics, these approaches often fail to capture hybrid failure scenarios in large-scale networks. To provide a more comprehensive and realistic resilience assessment, this article introduces a new diagnosability metric termed the $g$-good-neighbor $r$-component diagnosability, denoted by $D_{g,r}(G)$. This metric imposes two stringent constraints on the network after removing a faulty node set $F$: i) the residual network must contain at least $r$ connected components, and ii) every fault-free node must retain at least $g$ fault-free neighbors. We focus on the hypercube ($Q_{n}$), a prevalent interconnection architecture renowned for its high symmetry, scalability, and fault tolerance. Under the PMC and MM* diagnostic models, we establish the exact value $D_{2,2}(Q_{n}) = 8n - 21$ for $n \geq 24$. Leveraging the distinct characteristics of the PMC and MM* models, we propose two scalable fault localization algorithms tailored for hypercube architectures. Simulation experiments on $Q_{n}$ networks demonstrate that the proposed framework achieves approximately 100% true positive rate (TPR) when faulty nodes constitute $\leq 20\%$ of the network, maintaining TPR $> 98.7\%$ even as fault densities approach 50% .