Cloud block storage (CBS) serves as the fundamental infrastructure of modern cloud computing services like the cloud disk service. Large-scale cloud block storage usually adopts a layered architecture, including a forwarding layer with a cluster of proxy servers as proxies to provide cloud disk abstraction, and a unified distributed storage engine providing persisted data storage. However, as all I/O traffics go through the proxy servers in the forwarding layer, there may be a severe traffic imbalance between the proxy servers, which finally degrades the performance of cloud disks. To investigate the traffic imbalance problem in the forwarding layer, we first conduct an in-depth analysis on the workload traces of a large-scale cloud block storage system in production. We find that both the traffic of individual cloud disks and the consolidated traffic of cloud disks at proxy servers are highly skewed and fluctuate violently and frequently at a fine-grained time granularity, and thus causing severe traffic imbalance. To address the traffic imbalance issue, we then develop a low-cost migration algorithm, weighted partial migration (WPM), and conduct simulation analysis via trace replay to study its effectiveness. Experiments under real-world workloads show that for 84.3% of clusters, WPM can make the imbalance factor be smaller than 3 (i.e., the maximum traffic at a proxy server is within 3$\times$ of the median traffic), with a very small migration cost by migrating only 0.1% segments.

Outlier detection is an important task in many domains and is intensively studied in the past decade. Further, how to explain outliers, i.e., outlier interpretation, is more significant, which can provide valuable insights for analysts to better understand, solve, and prevent these detected outliers. However, only limited studies consider this problem. Most of the existing methods are based on the score-and-search manner. They select a feature subspace as interpretation per queried outlier by estimating outlying scores of the outlier in searched subspaces. Due to the tremendous searching space, they have to utilize pruning strategies and set a maximum subspace length, often resulting in suboptimal interpretation results. Accordingly, this paper proposes a novel Attention-guided Triplet deviation network for Outlier interpretatioN (ATON). Instead of searching a subspace, ATON directly learns an embedding space and learns how to attach attention to each embedding dimension (i.e., capturing the contribution of each dimension to the outlierness of the queried outlier). Specifically, ATON consists of a feature embedding module and a customized self-attention learning module, which are optimized by a triplet deviation-based loss function. We obtain an optimal attention-guided embedding space with expanded high-level information and rich semantics, and thus outlying behaviors of the queried outlier can be better unfolded. ATON finally distills a subspace of original features from the embedding module and the attention coefficient. With the good generality, ATON can be employed as an additional step of any black-box outlier detector. A comprehensive suite of experiments is conducted to evaluate the effectiveness and efficiency of ATON. The proposed ATON significantly outperforms state-of-the-art competitors on 12 real-world datasets and obtains good scalability w.r.t. both data dimensionality and data size.

Recent studies have demonstrated that the excessive inflammatory response is an important factor of death in coronavirus disease 2019 (COVID-19) patients. In this study, we propose a deep representation on heterogeneous drug networks, termed DeepR2cov, to discover potential agents for treating the excessive inflammatory response in COVID-19 patients. This work explores the multi-hub characteristic of a heterogeneous drug network integrating eight unique networks. Inspired by the multi-hub characteristic, we design 3 billion special meta paths to train a deep representation model for learning low-dimensional vectors that integrate long-range structure dependency and complex semantic relation among network nodes. Based on the representation vectors and transcriptomics data, we predict 22 drugs that bind to tumor necrosis factor-α or interleukin-6, whose therapeutic associations with the inflammation storm in COVID-19 patients, and molecular binding model are further validated via data from PubMed publications, ongoing clinical trials and a docking program. In addition, the results on five biomedical applications suggest that DeepR2cov significantly outperforms five existing representation approaches. In summary, DeepR2cov is a powerful network representation approach and holds the potential to accelerate treatment of the inflammatory responses in COVID-19 patients. The source code and data can be downloaded from https://github.com/pengsl-lab/DeepR2cov.git.

MOTIVATION: Predicting entity relationship can greatly benefit important biomedical problems. Recently, a large amount of biomedical heterogeneous networks (BioHNs) are generated and offer opportunities for developing network-based learning approaches to predict relationships among entities. However, current researches slightly explored BioHNs-based self-supervised representation learning methods, and are hard to simultaneously capturing local- and global-level association information among entities. RESULTS: In this study, we propose a BioHN-based self-supervised representation learning approach for entity relationship predictions, termed BioERP. A self-supervised meta path detection mechanism is proposed to train a deep Transformer encoder model that can capture the global structure and semantic feature in BioHNs. Meanwhile, a biomedical entity mask learning strategy is designed to reflect local associations of vertices. Finally, the representations from different task models are concatenated to generate two-level representation vectors for predicting relationships among entities. The results on eight datasets show BioERP outperforms 30 state-of-the-art methods. In particular, BioERP reveals great performance with results close to 1 in terms of AUC and AUPR on the drug-target interaction predictions. In summary, BioERP is a promising bio-entity relationship prediction approach. AVAILABILITY AND IMPLEMENTATION: Source code and data can be downloaded from https://github.com/pengsl-lab/BioERP.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

With a variety of tumor subtypes, personalized treatments need to identify the subtype of a tumor as accurately as possible. The development of DNA microarrays provides an opportunity to predict tumor classification. One strategy is to use gene expression profiling to extend current biological insights into the disease. However, overfitting problems exist in most machine learning methods when classifying tumor gene expression profile data characterized by high dimensional, small samples and nonlinearities. As a new machine learning methods, dictionary learning has become a more effective algorithm for gene expression profile classification. Here, a new method called discriminant projection shared dictionary learning (DPSDL) is proposed for classifying tumor subtypes using LINCS gene expression profile data. The method trains a shared dictionary, embeds Fisher discriminant criteria to obtain a class-specific sub-dictionary and coding coefficients. At the same time, a projection matrix is trained to widen the distance between different classes of samples. Experimental results show that our method performs better classification based on gene expression profile than the other dictionary learning methods and machine learning methods.

New drug development is an extremely time-consuming and high-risk process. [1]It has been widely valued by the biomedical industry to fully explore the new uses of existing drugs and reorientate them. [2]How to find drug disease with potential therapeutic relationship from a large number of unproven relationship pairs is the research focus of drug reorientation. With the help of machine learning model, we can improve the enrichment degree of potential drug disease relationship pairs, and reduce the false positive rate of prediction. In the past few years, a series of graph based convolutional network models have been developed to calculate the information latent feature representation of nodes and links. Researchers at home and abroad have done a lot of research on network embedding technology based on biomedical data, and have achieved a series of important research results. Among them, the research methods used can be divided into two categories: one is the traditional machine learning algorithm based on artificial feature extraction, the other is the method based on deep learning. For example, kipf and welling [3]proposed a new graph convolution network (GCN) with parts of existing models, DeepDR [4] and DTINet [5] based on node characteristics and their connections, which can be used for node classification. Aiming at the problem of imbalance of drug information data samples, the invention provides a drug relocation method based on deep learning multi-source heterogeneous network. In order to avoid the limitations of traditional feature extraction methods, such as highly dependent on the experience and knowledge of medical staff, strong subjectivity, consuming a lot of time and energy to complete, and extracting high-quality features with distinguishing features often exists In this paper, with the help of graph convolution encoder model and variational auto encoder neural network, we can automatically learn the characteristics of multi-source and heterogeneous drug low-dimensional network, and complete the drug relocation of drug disease association prediction.

Vaginal diseases caused by vaginal micro-ecological abnormalities mainly include Vulvovaginal Candidiasis (VVC), Aerobic Vaginitis (AV), and Bacterial Vaginosis (BV). Severe cases can lead to poor pregnancy outcomes and infertility. AI-based technologies are being deployed with an expectation to relieve doctors of routine, tedious work when implemented correctly in daily microscopy of vaginal micro-ecological abnormalities. In this paper, we built a clinical image dataset of the Gram stain of the vaginal discharge. By comparing the performance of state of art convolutional neural network models, we found the fine-tuning Inception ResNet V2 shows the best classification performance for vaginal diseases. It achieves 96%, 94%, 86% AUC in VVC, AV, BV classification respectively. The result shows that compared with human visual inspection, the method based on deep learning greatly improves the screening sensitivity. Besides, we found that transfer learning can reduce the required manual labeling by roughly 73% (about more than one thousand samples). But for BV, which is difficult to diagnose for both humans and AI. Unlike AV and VVC, it requires more labeled data and is insensitive to the transfer fine-tuning.

Clustering gene expression profiles is a fundamental task in the genome and biomedical research. With the development of RNA-seq and gene chip technology, mass gene expression profile data has been generated, which puts forward two requirements for related research of gene expression profile: i) accurate analysis of drug R&D requires high accuracy of similarity analysis, ii) large-scale analysis of data requires as little running time as possible. We propose a faster, more accurate method called DeepCDNet, which is based on the framework of the Siamese network. DeepCDNet uses the DenseNet structure and optimized loss function to achieve rapid convergence, and the similarity between expression spectra is calculated by a cosine function. The experiment results show that: i) our method breaks through the limitation of high dimensions of gene expression profile and can quickly and accurately learn the required gene characteristics, ii) The accuracy of our method in similarity analysis is greatly improved, iii) as the dimension of data increases, the advantage of our method on time cost gradually becomes more prominent, and time consumption is less.

Data analysis of electronic health record (EHRs) system using machine learning, statistical methods can predict relevant clinical tasks. However, there is no uniform standard for current electronic health record systems, and the clinical outcome prediction models trained on one EHR dataset cannot be applied well on other EHR datasets from different medical institutions. Data differences between different medical institutions pose a huge challenge to the study of electronic health records. In this study, we proposed a general transfer learning strategy which can enable models to make clinical prediction acrossing diverse EHRs datasets and validated its strong versatility on three deep learning models. Two different intensive care units (ICU) databases (MIMIC-III and eICU) and one clinical task (in-hospital mortality) are used to evaluate our method. At first, we trained the deep learning models on the source dataset and saved the model states after each epoch. Then, we selected the best performing model as the pre-training model, transferred it to the target dataset and fine-tuned the whole network on target dataset. Finally, we use the fine-tuned models to make predictions on the target dataset. Experiment results show that AUROC score increased by 3%-20% with transfer strategy, which indicated that the general strategy can provide more reliable predictions acrossing EHRs databases to predict clinical tasks.