MicroRNA (miRNA) is a class of non-coding single-stranded RNA molecules encoded by endogenous genes with a length of about 22 nucleotides. MiRNAs have been successfully identified as differentially expressed in various cancers. There is evidence that disorders of miRNAs are associated with a variety of complex diseases. Therefore, inferring potential miRNA-disease associations (MDAs) is very important for understanding the aetiology and pathogenesis of many diseases and is useful to disease diagnosis, prognosis and treatment. First, We creatively fused multiple similarity subnetworks from multi-sources for miRNAs, genes and diseases by multiplexing technology, respectively. Then, three multiplexed biological subnetworks are connected through the extended binary association to form a tripartite complete heterogeneous multiplexed network (Tri-HM). Finally, because the constructed Tri-HM network can retain the original topology and biological functions of subnetworks and expands the binary association and dependence between the three biological entities, rich neighbourhood information is obtained iteratively from neighbours by a non-equilibrium random walk. Through cross-validation, our tri-HM-RWR model obtained an AUC value of 0.8657, and an AUPR value of 0.2139 in the global 5-fold cross-validation, which shows that our model can more fully speculate disease-related miRNAs.

Identifying the microbe-disease associations is conducive to understanding the pathogenesis of disease from the perspective of microbe. In this paper, we propose a deep matrix factorization prediction model (DMFMDA) based on deep neural network. First, the disease one-hot encoding is fed into neural network, which is transformed into a low-dimensional dense vector in implicit semantic space via embedding layer, and so is microbe. Then, matrix factorization is realized by neural network with embedding layer. Furthermore, our model synthesizes the non-linear modeling advantages of multi-layer perceptron based on the linear modeling advantages of matrix factorization. Finally, different from other methods using square error loss function, Bayesian Personalized Ranking optimizes the model from a ranking perspective to obtain the optimal model parameters, which makes full use of the unobserved data. Experiments show that DMFMDA reaches average AUCs of 0.9091 and 0.9103 in the framework of 5-fold cross validation and Leave-one-out cross validation, which is superior to three the-state-of-art methods. In case studies, 10, 9 and 9 out of top-10 candidate microbes are verified by recently published literature for asthma, inflammatory bowel disease and colon cancer, respectively. In conclusion, DMFMDA is successful application of deep learning in the prediction of microbe-disease association.

Numerous experiments have demonstrated that long non-coding RNA (lncRNA) play an important role in various systems of the human body. LncRNA deletions or mutations can cause human disease. The prediction of lncRNA-disease associations is conducive to the diagnosis and prevention of complex diseases. As we all know, it is a time-consuming and expensive process to predict lncRNA-disease associations via biological experiments. However, the computation methods can effectively discover lncRNA-disease associations with less human and material resources. In this paper, we propose a neural network-based matrix factorization model to predict lncRNA-disease associations, which is called NeuMFLDA. NeuMFLDA first converts the one-hot encoding of disease or lncRNA into word vector via the embedding layer. Then combined with the memorization of the conventional matrix factorization and the generalization of the multi-layer perceptron, the lncRNA-disease associations can be predicted more accurately. In addition, as opposed to conventional pointwise loss function, a new pairwise loss function is proposed to update our model parameters. Our new loss function optimizes the model from the perspective of ranking priority, which is more in line with the solution to the lncRNA-disease associations prediction task. Experiments show that NeuMFLDA reaches average AUCs of 0.904 ± 0.003 and 0.918 ± 0.002 in the framework of 5-fold cross validation and Leave-one-out cross validation, which is superior to three the-stateof- art methods. In case studies, 9, 9 and 8 out of top-10 candidate lncRNAs are verified by recently published literatures for hepatocelluar carcinoma, kidney cancer and ovarian cancer, respectively. In short, NeuMFLDA is an effective tool for predicting lncRNA-disease associations.

Persistent and infrequent (PI) flows refer to packet flows that last for a long time at low packet arrival rates in network traffic. It is crucial to accurately find these flows for uncovering stealthy network threats, such as advanced persistent threats (APTs) and low-rate denial-of-service attacks (LDoS). To this end, we propose a low-overhead and accurate method for detecting persistent and infrequent flows called PIF-Detector, which separates the monitoring and identification functions of PI flows. Specifically, we design a monitoring table composed of bucket arrays to store and monitor potential PI flows, and an identifier composed of compact bit vectors to recognize potential PI flows. For the monitoring table, we design an adjacent-bucket relocation strategy to improve bucket utilization and thereby enhance PI-flow detection accuracy. For the identifier, we track flow arrivals across consecutive time windows using compact bit vectors to detect PI flows with low memory overhead. Finally, we perform theoretical derivations on the false positive rate and the false negative rate of PIF-Detector, and evaluate its performance through experiments on three datasets. Experimental results show that PIF-Detector achieves up to 99.57% precision and 99.93% recall, outperforming state-of-the-art solutions under the same memory overhead.

Periodic flows are characterized by repeated appearances at regular time intervals in network traffic. These flows may conceal low-rate DoS attacks that gradually exhaust server resources while evading network traffic detection. Therefore, it is crucial to accurately detect periodic flows for network security. However, existing work on periodic-flow detection often struggles to achieve high detection accuracy, due to the resource constraints of its typically deployed devices such as switches. To resolve this issue, this paper proposes an accurate low-overhead detection method of periodic flows called PFDetector, which consists of two components: new-flow detector and periodic-flow identifier. The first component adopts a Bloom filter to rapidly detect first-appearing flows and skip repeated flows within each time window, significantly reducing computational and memory overhead of subsequent periodic-flow detection. The second component records potential periodic flows and tracks their periodicity for reporting real periodic flows. For the second component, we design a stable flow replacement strategy, which prioritizes flows with higher arrival frequencies and smaller inter-arrival time standard deviations under memory constraints. We further derive the false positive rate of the new-flow detector and the error bound of the periodic-flow identifier by theoretical analysis. Finally, we verify the performance of our proposed method PFDetector by experiments on real network traffic traces. Experimental results indicate that the PFDetector improves detection precision by approximately 4.5%, increases recall by approximately 8%, and reduces the average relative error by more than two times, compared to the state-of-the-art methods.