Search

Multivariate Time Series Anomaly Detection (MTS-AD) is crucial for the effective management and maintenance of devices in complex systems, such as server clusters, spacecrafts, and financial systems, and so on. However, upgrade or cross-platform deployment of these devices will introduce the issue of cross-domain distribution shift, which leads to the prototypical problem of domain adaptation for MTS-AD. Compared with general domain adaptation problems, MTS-AD domain adaptation presents two peculiar challenges: (1) the dimensions of data from the source domain and the target domain are usually different, so alignment without losing any information is necessary; and (2) the association between different variates plays a vital role in the MTS-AD task, which is overlooked by traditional domain adaptation approaches. Aiming at addressing the above issues, we propose a Variate Associated Domain Adaptation Method Combined with a Graph Deviation Network (VANDA) for MTS-AD, which includes two major contributions. First, we characterize the intra-domain variate associations of the source domain by a graph deviation network (GDN), which can share parameters across domains without dimension alignment. Second, we propose a sliding similarity to measure the inter-domain variate associations and perform joint training by minimizing the optimal transport distance between source and target data for transferring variate associations across domains. VANDA achieves domain adaptation by transferring both variate associations and GDN parameters from the source domain to the target domain. We construct two pairs of MTS-AD datasets from existing MTS-AD data and combine three domain adaptation strategies with six MTS-AD backbones as the benchmark methods for experimental evaluation and comparison. Extensive experiments demonstrate the effectiveness of our approach, which outperforms the benchmark methods, and significantly improves the AD performance of the target domain by effectively utilizing the source domain knowledge. [ABSTRACT FROM AUTHOR]

With the rapid growth of the data scale in data centers, the high reliability of storage is facing various challenges. Specifically, hardware failures such as disk faults occur frequently, causing serious system availability issues. In this context, hardware fault prediction based on AI and big data technologies has become a research hotspot, aiming to guide operation and maintenance personnel to implement preventive replacement through accurate prediction to reduce hardware failure rates. However, existing methods still have weaknesses in terms of accuracy due to the impacts of data quality issues such as the sample imbalance. This article proposes a disk fault prediction method based on classification intensity resampling, which fills the gap between the degree of data imbalance and the actual classification intensity of the task by introducing a base classifier to calculate the classification intensity, thus better preserving the data features of the original dataset. In addition, using ensemble learning methods such as random forests, combined with resampling, an integrated classifier for imbalanced data is developed to further improve the prediction accuracy. Experimental verification shows that compared with traditional methods, the F1-score of disk fault prediction is improved by 6%, and the model training time is also greatly reduced. The fault prediction method proposed in this paper has been applied to approximately 80 disk drives and nearly 40,000 disks in the production environment of a large bank's data center to guide preventive replacements. Compared to traditional methods, the number of preventive replacements based on our method has decreased by approximately 21%, while the overall disk failure rate remains unchanged, thus demonstrating the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Under a distributed information system, the scale of various operational components such as applications, operating systems, databases, servers, and networks is immense, with intricate access relationships. The silo effect of each professional is prominent, and the linkage mechanism is insufficient, making it difficult to locate the infrastructure components that cause exceptions under a particular application. Current research only plays a role in local scenarios, and its accuracy and generalization are still very limited. This paper proposes a novel fault location method based on dynamic operation maps and alarm common point analysis. During the fault period, various alarm entities are associated with dynamic operation maps, and alarm common points are obtained based on graph search addressing methods, covering deployment relationship common points, connection common points (physical and logical), and access flow common points. This method, compared with knowledge graph approaches, eliminates the complex process of knowledge graph construction, making it more concise and efficient. Furthermore, in contrast to indicator correlation analysis methods, this approach supplements with configuration correlation information, resulting in more precise positioning. Through practical validation, its fault hit rate exceeds 82%, which is significantly better than the existing main methods. [ABSTRACT FROM AUTHOR]

Motivation Molecular property prediction (MPP) is a fundamental but challenging task in the computer-aided drug discovery process. More and more recent works employ different graph-based models for MPP, which have achieved considerable progress in improving prediction performance. However, current models often ignore relationships between molecules, which could be also helpful for MPP. Results For this sake, in this article we propose a graph structure learning (GSL) based MPP approach, called GSL-MPP. Specifically, we first apply graph neural network (GNN) over molecular graphs to extract molecular representations. Then, with molecular fingerprints, we construct a molecule similarity graph (MSG). Following that, we conduct GSL on the MSG, i.e. molecule-level GSL, to get the final molecular embeddings, which are the results of fuzing both GNN encoded molecular representations and the relationships among molecules. That is, combining both intra-molecule and inter-molecule information. Finally, we use these molecular embeddings to perform MPP. Extensive experiments on 10 various benchmark datasets show that our method could achieve state-of-the-art performance in most cases, especially on classification tasks. Further visualization studies also demonstrate the good molecular representations of our method. Availability and implementation Source code is available at https://github.com/zby961104/GSL-MPP. [ABSTRACT FROM AUTHOR]

Background: The rapid devolvement of single cell RNA sequencing (scRNA-seq) technology leads to huge amounts of scRNA-seq data, which greatly advance the research of many biomedical fields involving tissue heterogeneity, pathogenesis of disease and drug resistance etc. One major task in scRNA-seq data analysis is to cluster cells in terms of their expression characteristics. Up to now, a number of methods have been proposed to infer cell clusters, yet there is still much space to improve their performance. Results: In this paper, we develop a new two-step clustering approach to effectively cluster scRNA-seq data, which is called TSC — the abbreviation of Two-Step Clustering. Particularly, by dividing all cells into two types: core cells (those possibly lying around the centers of clusters) and non-core cells (those locating in the boundary areas of clusters), we first clusters the core cells by hierarchical clustering (the first step) and then assigns the non-core cells to the corresponding nearest clusters (the second step). Extensive experiments on 12 real scRNA-seq datasets show that TSC outperforms the state of the art methods. Conclusion: TSC is an effective clustering method due to its two-steps clustering strategy, and it is a useful tool for scRNA-seq data analysis. [ABSTRACT FROM AUTHOR]

Anomalies (or outliers) indicate a minority of data items that are quite different from the majority (inliers) of a dataset in a certain aspect. Unsupervised anomaly detection (UAD) is an important but not yet extensively studied research topic. Recent deep learning based methods exploit the reconstruction gap between inliers and outliers to discriminate them. However, it is observed that the reconstruction gap often decreases rapidly as the training process goes. And there is no reasonable way to set the training stop point. To support effective UAD, we propose a new UAD framework by introducing a Latent Feature Reconstruction (LFR) layer that can be applied to recent UAD methods. The LFR layer acts as a regularizer to constrain the latent features in a low-rank subspace from which inliers can be reconstructed well while outliers cannot. We develop two new UAD methods by implementing the proposed framework with autoencoder architecture and geometric transformation scheme. Experiments on five benchmarks show that our proposed methods can achieve state-of-the-art performance in most cases. [ABSTRACT FROM AUTHOR]

Simple Summary: Both the lack of bird object detection datasets and the scarcity of technical references for evaluating the performance of object detection models and model lightweighting present challenges in the application of bird object detection technology. In this study, we have not only constructed the largest known bird object detection dataset, but also compared the performance of eight mainstream detection models on bird object detection tasks and proposed a feasible approach for model lightweighting in bird object detection. Our research results not only provide more accurate and comprehensive data for the field of bird detection, but also serve as a technical reference for users in selecting appropriate object detection models. The application of object detection technology has a positive auxiliary role in advancing the intelligence of bird recognition and enhancing the convenience of bird field surveys. However, challenges arise due to the absence of dedicated bird datasets and evaluation benchmarks. To address this, we have not only constructed the largest known bird object detection dataset, but also compared the performances of eight mainstream detection models on bird object detection tasks and proposed feasible approaches for model lightweighting in bird object detection. Our constructed bird detection dataset of GBDD1433-2023, includes 1433 globally common bird species and 148,000 manually annotated bird images. Based on this dataset, two-stage detection models like Faster R-CNN and Cascade R-CNN demonstrated superior performances, achieving a Mean Average Precision (mAP) of 73.7% compared to one-stage models. In addition, compared to one-stage object detection models, two-stage object detection models have a stronger robustness to variations in foreground image scaling and background interference in bird images. On bird counting tasks, the accuracy ranged between 60.8% to 77.2% for up to five birds in an image, but this decreased sharply beyond that count, suggesting limitations of object detection models in multi-bird counting tasks. Finally, we proposed an adaptive localization distillation method for one-stage lightweight object detection models that are suitable for offline deployment, which improved the performance of the relevant models. Overall, our work furnishes an enriched dataset and practice guidelines for selecting suitable bird detection models. [ABSTRACT FROM AUTHOR]

Sea Surface Temperature (SST) prediction is a hot topic that has received tremendous popularity in recent years. Existing methods for SST prediction usually select one sea area of interest and conduct SST prediction by learning the spatial and temporal dependencies and patterns in historical SST data. However, global SST is a unified system of high regionality, and the SST in different sea areas shows different changing patterns due to the influence of various factors, e.g., geographic location, ocean currents and sea depth. Without a good understanding of such regionality of SST, we cannot quantitatively integrate the regionality information of SST into SST prediction models to make them adaptive to different SST patterns around the world and improve the prediction accuracy. To address this issue, we proposed the Multi-Stage Spatio–Temporal Clustering (MuSTC) method to quantitatively identify sea areas with similar SST patterns. First, MuSTC sequentially learns the representation of long-term SST with a deep temporal encoder and calculates the spatial correlation scores between grid ocean regions with self-attention. Then, MuSTC clusters grid ocean regions based on the original SST data, encoded long-term SST representation and spatial correlation scores, respectively, to obtain the sea areas with similar SST patterns from different perspectives. According to the experiments in three ocean areas, i.e., the North Pacific Ocean (NPO), the South Atlantic Ocean (SAO) and the North Atlantic Ocean (NAO), the clustering results generally match the distribution of ocean currents, which demonstrates the effectiveness of our MuSTC method. In addition, we integrate the clustering results into two representative spatio–temporal prediction models, i.e., Spatio–Temporal Graph Convolutional Networks (STGCN) and Adaptive Graph Convolutional Recurrent Network (AGCRN), to conduct SST prediction. According to the results of experiments, the integration of regionality information leads to the reduction of Root Mean Square Error (RMSE) by 1.95%, 1.39% and 1.28% in NPO, SAO and NAO, respectively, using the STGCN model, and the reduction of RMSE by 4.94%, 0.74% and 1.43% by using the AGCRN model. Such results indicate that the integration of regionality information could notably improve the prediction accuracy of SST. [ABSTRACT FROM AUTHOR]

Molecular property prediction (MPP) is a crucial and fundamental task for AI-aided drug discovery (AIDD). Recent studies have shown great promise of applying self-supervised learning (SSL) to producing molecular representations to cope with the widely-concerned data scarcity problem in AIDD. As some specific substructures of molecules play important roles in determining molecular properties, molecular representations learned by deep learning models are expected to attach more importance to such substructures implicitly or explicitly to achieve better predictive performance. However, few SSL pre-trained models for MPP in the literature have ever focused on such substructures. To challenge this situation, this paper presents a C hemistry- A ware F ragmentation for E ffective MPP (CAFE-MPP in short) under the self-supervised contrastive learning framework. First, a novel fragment-based molecular graph (FMG) is designed to represent the topological relationship between chemistry-aware substructures that constitute a molecule. Then, with well-designed hard negative pairs, a is pre-trained on fragment-level by contrastive learning to extract representations for the nodes in FMGs. Finally, a Graphormer model is leveraged to produce molecular representations for MPP based on the embeddings of fragments. Experiments on 11 benchmark datasets show that the proposed CAFE-MPP method achieves state-of-the-art performance on 7 of the 11 datasets and the second-best performance on 3 datasets, compared with six remarkable self-supervised methods. Further investigations also demonstrate that CAFE-MPP can learn to embed molecules into representations implicitly containing the information of fragments highly correlated to molecular properties, and can alleviate the over-smoothing problem of graph neural networks. [ABSTRACT FROM AUTHOR]

Motivation Protein complexes are groups of polypeptide chains linked by non-covalent protein–protein interactions, which play important roles in biological systems and perform numerous functions, including DNA transcription, mRNA translation, and signal transduction. In the past decade, a number of computational methods have been developed to identify protein complexes from protein interaction networks by mining dense subnetworks or subgraphs. Results In this article, different from the existing works, we propose a novel approach for this task based on generative adversarial networks, which is called PCGAN , meaning identifying P rotein C omplexes by GAN. With the help of some real complexes as training samples, our method can learn a model to generate new complexes from a protein interaction network. To effectively support model training and testing, we construct two more comprehensive and reliable protein interaction networks and a larger gold standard complex set by merging existing ones of the same organism (including human and yeast). Extensive comparison studies indicate that our method is superior to existing protein complex identification methods in terms of various performance metrics. Furthermore, functional enrichment analysis shows that the identified complexes are of high biological significance, which indicates that these generated protein complexes are very possibly real complexes. Availability and implementation https://github.com/yul-pan/PCGAN. [ABSTRACT FROM AUTHOR]

Motivation Contrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may face the semantic inconsistency problem, which leads to false positive pairs and consequently poor prediction performance. Results To address this problem, in this article, we first propose a semantic-invariant view generation method by properly breaking molecular graphs into fragment pairs. Then, we develop a Fragment-based Semantic-Invariant Contrastive Learning (FraSICL) model based on this view generation method for molecular property prediction. The FraSICL model consists of two branches to generate representations of views for contrastive learning, meanwhile a multi-view fusion and an auxiliary similarity loss are introduced to make better use of the information contained in different fragment-pair views. Extensive experiments on various benchmark datasets show that with the least number of pre-training samples, FraSICL can achieve state-of-the-art performance, compared with major existing counterpart models. Availability and implementation The code is publicly available at https://github.com/ZiqiaoZhang/FraSICL. [ABSTRACT FROM AUTHOR]

Motivation Predicting molecular properties is one of the fundamental problems in drug design and discovery. In recent years, self-supervised learning (SSL) has shown its promising performance in image recognition, natural language processing, and single-cell data analysis. Contrastive learning (CL) is a typical SSL method used to learn the features of data so that the trained model can more effectively distinguish the data. One important issue of CL is how to select positive samples for each training example, which will significantly impact the performance of CL. Results In this article, we propose a new method for molecular property prediction (MPP) by C ontrastive   L earning with   A ttention-guided   P ositive-sample   S election (CLAPS). First, we generate positive samples for each training example based on an attention-guided selection scheme. Second, we employ a Transformer encoder to extract latent feature vectors and compute the contrastive loss aiming to distinguish positive and negative sample pairs. Finally, we use the trained encoder for predicting molecular properties. Experiments on various benchmark datasets show that our approach outperforms the state-of-the-art (SOTA) methods in most cases. Availability and implementation The code is publicly available at https://github.com/wangjx22/CLAPS. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) has important impacts on the global ecology, and having a good understanding of the predictability, i.e., the possibility of achieving accurate prediction, of SST can help us monitor the marine environment and climate change, and guide the selection and design of SST prediction methods. However, existing studies for analyzing SST mostly measure the rising or falling trends of SST. To address this issue, we introduce a temporal-correlated entropy to quantify the predictability of SST series from both global coarse-grained and local fine-grained aspects, and make SST prediction with multiple deep learning models to prove the effectiveness of such predictability evaluation method. In addition, we explore the dynamics of SST predictability by dividing the time range of interest into consecutive time periods, evaluating the corresponding predictability of SST for each time period, and analyzing the stability of the predictability of SST over time. According to the experiments, the SST predictability values near the poles and equator are really high. The average SST predictability values of the East China Sea, Bohai Sea, and Antarctic Ocean are 0.719, 0.706, and 0.886, respectively, and the size relationship of the SST predictability in the three local sea areas is consistent with our prediction results using multiple representative SST prediction methods, which corroborates the reliability of the predictability evaluation method. In addition, we found that the SST predictability in the Antarctic Ocean changes more dramatically over time than in the East China Sea and the Bohai Sea. The results of SST predictability and its dynamic analysis indicate that global warming, ocean currents, and human activities all have significant impacts on the predictability of SST. [ABSTRACT FROM AUTHOR]

Marine plankton classification is important for monitoring marine biological populations and understanding marine ecosystems. However, it is difficult to obtain abundant annotated image data of marine plankton to train classification models of high quality. To classify marine plankton with a small number of image samples, a cross‐domain few‐shot learning model (CDFM) is proposed. First, CDFM learns knowledge from existing labelled images and then transfers the knowledge to new images. In this process, there is an issue of domain differences between the new images and the existing datasets due to differences in data acquisition time and locations. To address this issue, the authors pre‐train a model in the source domain and then use fine‐tuning to adapt it to the target domain. Second, the graph neural network is used as a meta‐learning module to learn a feature distance metric for marine plankton classification with limited samples. Extensive experiments on four marine plankton image datasets are conducted, including Kaggle Plankton, miniPPlankton, ZooScan and WHOI, and CDFM outperforms existing methods for marine plankton classification. [ABSTRACT FROM AUTHOR]

Satellite data is of high importance for ocean environment monitoring and protection. However, due to the missing values in satellite data, caused by various force majeure factors such as cloud cover, bad weather and sensor failure, the quality of satellite data is reduced greatly, which hinders the applications of satellite data in practice. Therefore, a variety of methods have been proposed to conduct missing data imputation for satellite data to improve its quality. However, these methods cannot well learn the short-term temporal dependence and dynamic spatial dependence in satellite data, resulting in bad imputation performance when the data missing rate is large. To address this issue, we propose the Spatio-Temporal Attention Generative Adversarial Network (STA-GAN) for missing value imputation in satellite data. First, we develop the Spatio-Temporal Attention (STA) mechanism based on Graph Attention Network (GAT) to learn features for capturing both short-term temporal dependence and dynamic spatial dependence in satellite data. Then, the learned features from STA are fused to enrich the spatio-temporal information for training the generator and discriminator of STA-GAN. Finally, we use the generated imputation data by the trained generator of STA-GAN to fill the missing values in satellite data. Experimental results on real datasets show that STA-GAN largely outperforms the baseline data imputation methods, especially for filling satellite data with large missing rates. [ABSTRACT FROM AUTHOR]

Background: Essential proteins are indispensable to the development and survival of cells. The identification of essential proteins not only is helpful for the understanding of the minimal requirements for cell survival, but also has practical significance in disease diagnosis, drug design and medical treatment. With the rapidly amassing of protein–protein interaction (PPI) data, computationally identifying essential proteins from protein–protein interaction networks (PINs) becomes more and more popular. Up to now, a number of various approaches for essential protein identification based on PINs have been developed. Results: In this paper, we propose a new and effective approach called iMEPP to identify essential proteins from PINs by fusing multiple types of biological data and applying the influence maximization mechanism to the PINs. Concretely, we first integrate PPI data, gene expression data and Gene Ontology to construct weighted PINs, to alleviate the impact of high false-positives in the raw PPI data. Then, we define the influence scores of nodes in PINs with both orthological data and PIN topological information. Finally, we develop an influence discount algorithm to identify essential proteins based on the influence maximization mechanism. Conclusions: We applied our method to identifying essential proteins from saccharomyces cerevisiae PIN. Experiments show that our iMEPP method outperforms the existing methods, which validates its effectiveness and advantage. [ABSTRACT FROM AUTHOR]

Motivation Accurately predicting drug–target interaction (DTI) is a crucial step to drug discovery. Recently, deep learning techniques have been widely used for DTI prediction and achieved significant performance improvement. One challenge in building deep learning models for DTI prediction is how to appropriately represent drugs and targets. Target distance map and molecular graph are low dimensional and informative representations, which however have not been jointly used in DTI prediction. Another challenge is how to effectively model the mutual impact between drugs and targets. Though attention mechanism has been used to capture the one-way impact of targets on drugs or vice versa, the mutual impact between drugs and targets has not yet been explored, which is very important in predicting their interactions. Results Therefore, in this article we propose MINN-DTI, a new model for DTI prediction. MINN-DTI combines an interacting-transformer module (called Interformer) with an improved Communicative Message Passing Neural Network (CMPNN) (called Inter-CMPNN) to better capture the two-way impact between drugs and targets, which are represented by molecular graph and distance map, respectively. The proposed method obtains better performance than the state-of-the-art methods on three benchmark datasets: DUD-E, human and BindingDB. MINN-DTI also provides good interpretability by assigning larger weights to the amino acids and atoms that contribute more to the interactions between drugs and targets. Availability and implementation The data and code of this study are available at https://github.com/admislf/MINN-DTI. [ABSTRACT FROM AUTHOR]

Cellular programs often exhibit strong heterogeneity and asynchrony in the timing of program execution. Single-cell RNA-seq technology has provided an unprecedented opportunity for characterizing these cellular processes by simultaneously quantifying many parameters at single-cell resolution. Robust trajectory inference is a critical step in the analysis of dynamic temporal gene expression, which can shed light on the mechanisms of normal development and diseases. Here, we present TiC2D, a novel algorithm for cell trajectory inference from single-cell RNA-seq data, which adopts a consensus clustering strategy to precisely cluster cells. To evaluate the power of TiC2D, we compare it with three state-of-the-art methods on four independent single-cell RNA-seq datasets. The results show that TiC2D can accurately infer developmental trajectories from single-cell transcriptome. Furthermore, the reconstructed trajectories enable us to identify key genes involved in cell fate determination and to obtain new insights about their roles at different developmental stages. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) is a crucial factor that affects global climate and marine activities. Predicting SST at different temporal scales benefits various applications, from short-term SST prediction for weather forecasting to long-term SST prediction for analyzing El Niño–Southern Oscillation (ENSO). However, existing approaches for SST prediction train separate models for different temporal scales, which is inefficient and cannot take advantage of the correlations among the temperatures of different scales to improve the prediction performance. In this work, we propose a unified spatio-temporal model termed the Multi-In and Multi-Out (MIMO) model to predict SST at different scales. MIMO is an encoder–decoder model, where the encoder learns spatio-temporal features from the SST data of multiple scales, and fuses the learned features with a Cross Scale Fusion (CSF) operation. The decoder utilizes the learned features from the encoder to adaptively predict the SST of different scales. To our best knowledge, this is the first work to predict SST at different temporal scales simultaneously with a single model. According to the experimental evaluation on the Optimum Interpolation SST (OISST) dataset, MIMO achieves the state-of-the-art prediction performance. [ABSTRACT FROM AUTHOR]

Due to the increasing cost of data storage and computation, more and more graphs (e.g., web graphs, social networks) are outsourced and analyzed in the cloud. However, there is growing concern on the privacy of these outsourced graphs at the hands of untrusted cloud providers. Unfortunately, simple label anonymization cannot protect nodes from being re-identified by adversary who knows the graph structure. To address this issue, existing works adopt the k-automorphism model, which constructs (k - 1) symmetric vertices for each vertex. It has two disadvantages. First, it significantly enlarges the graphs, which makes graph mining tasks such as subgraph matching extremely inefficient and sometimes infeasible even in the cloud. Second, it cannot protect the privacy of attributes in each node. In this paper, we propose a new privacy model (k, t)-privacy that combines the k-automorphism model for graph structure with the t-closeness privacy model for node label generalization. Besides a stronger privacy guarantee, the paper also optimizes the matching efficiency by (1) an approximate label generalization algorithm TOGGLE with (1 + ϵ) approximation ratio and (2) a new subgraph matching algorithm PGP on succinct k-automorphic graphs without decomposing the query graph. [ABSTRACT FROM AUTHOR]

This article addresses two important issues of causal inference in the high-dimensional situation. One is how to reduce redundant conditional independence (CI) tests, which heavily impact the efficiency and accuracy of existing constraint-based methods. Another is how to construct the true causal graph from a set of Markov equivalence classes returned by these methods. For the first issue, we design a recursive decomposition approach where the original data (a set of variables) are first decomposed into two small subsets, each of which is then recursively decomposed into two smaller subsets until none of these subsets can be decomposed further. Redundant CI tests can be reduced by inferring causalities from these subsets. The advantage of this decomposition scheme lies in two aspects: 1) it requires only low-order CI tests and 2) it does not violate $d$ -separation. The complete causality can be reconstructed by merging all the partial results of the subsets. For the second issue, we employ regression-based CI tests to check CIs in linear non-Gaussian additive noise cases, which can identify more causal directions by $x - E(x|Z) \_{}\!\!\_{}\!\!\!\!\!\shortparallel z$ (or $y - E(y|Z) \_{}\!\!\_{}\!\!\!\!\!\shortparallel z$). Consequently, causal direction learning is no longer limited by the number of returned $V$ -structures and consistent propagation. Extensive experiments show that the proposed method can not only substantially reduce redundant CI tests but also effectively distinguish the equivalence classes. [ABSTRACT FROM AUTHOR]

Single-cell RNA sequencing (scRNA-seq) permits researchers to study the complex mechanisms of cell heterogeneity and diversity. Unsupervised clustering is of central importance for the analysis of the scRNA-seq data, as it can be used to identify putative cell types. However, due to noise impacts, high dimensionality and pervasive dropout events, clustering analysis of scRNA-seq data remains a computational challenge. Here, we propose a new d eep s tructural c lustering method for sc RNA-seq data, named scDSC, which integrate the structural information into deep clustering of single cells. The proposed scDSC consists of a Zero-Inflated Negative Binomial (ZINB) model-based autoencoder, a graph neural network (GNN) module and a mutual-supervised module. To learn the data representation from the sparse and zero-inflated scRNA-seq data, we add a ZINB model to the basic autoencoder. The GNN module is introduced to capture the structural information among cells. By joining the ZINB-based autoencoder with the GNN module, the model transfers the data representation learned by autoencoder to the corresponding GNN layer. Furthermore, we adopt a mutual supervised strategy to unify these two different deep neural architectures and to guide the clustering task. Extensive experimental results on six real scRNA-seq datasets demonstrate that scDSC outperforms state-of-the-art methods in terms of clustering accuracy and scalability. Our method scDSC is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/scDSC. [ABSTRACT FROM AUTHOR]

Link weight prediction is an important subject in network science and machine learning. Its applications to social network analysis, network modeling, and bioinformatics are ubiquitous. Although this subject has attracted considerable attention recently, the performance and interpretability of existing prediction models have not been well balanced. This article focuses on an unsupervised mixed strategy for link weight prediction. Here, the target attribute is the link weight, which represents the correlation or strength of the interaction between a pair of nodes. The input of the model is the weighted adjacency matrix without any preprocessing, as widely adopted in the existing models. Extensive observations on a large number of networks show that the new scheme is competitive to the state-of-the-art algorithms concerning both root-mean-square error and Pearson correlation coefficient metrics. Analytic and simulation results suggest that combining the weight consistency of the network and the link weight-associated latent factors of the nodes is a very effective way to solve the link weight prediction problem. [ABSTRACT FROM AUTHOR]

Over the past decades, massive amounts of protein-protein interaction (PPI) data have been accumulated due to the advancement of high-throughput technologies, and but data quality issues (noise or incompleteness) of PPI have been still affecting protein function prediction accuracy based on PPI networks. Although two main strategies of network reconstruction and edge enrichment have been reported on the effectiveness of boosting the prediction performance in numerous literature studies, there still lack comparative studies of the performance differences between network reconstruction and edge enrichment. Inspired by the question, this study first uses three protein similarity metrics (local, global and sequence) for network reconstruction and edge enrichment in PPI networks, and then evaluates the performance differences of network reconstruction, edge enrichment and the original networks on two real PPI datasets. The experimental results demonstrate that edge enrichment work better than both network reconstruction and original networks. Moreover, for the edge enrichment of PPI networks, the sequence similarity outperformes both local and global similarity. In summary, our study can help biologists select suitable pre-processing schemes and achieve better protein function prediction for PPI networks. [ABSTRACT FROM AUTHOR]

Background: Protein protein interactions (PPIs) are essential to most of the biological processes. The prediction of PPIs is beneficial to the understanding of protein functions and thus is helpful to pathological analysis, disease diagnosis and drug design etc. As the amount of protein data is growing fast in the post genomic era, high-throughput experimental methods are expensive and time-consuming for the prediction of PPIs. Thus, computational methods have attracted researcher's attention in recent years. A large number of computational methods have been proposed based on different protein sequence encoders. Results: Notably, the confidence score of a protein sequence pair could be regarded as a kind of measurement to PPIs. The higher the confidence score for one protein pair is, the more likely the protein pair interacts. Thus in this paper, a deep learning framework, called ordinal regression and recurrent convolutional neural network (OR-RCNN) method, is introduced to predict PPIs from the perspective of confidence score. It mainly contains two parts: the encoder part of protein sequence pair and the prediction part of PPIs by confidence score. In the first part, two recurrent convolutional neural networks (RCNNs) with shared parameters are applied to construct two protein sequence embedding vectors, which can automatically extract robust local features and sequential information from the protein pairs. Based on it, the two embedding vectors are encoded into one novel embedding vector by element-wise multiplication. By taking the ordinal information behind confidence score into consideration, ordinal regression is used to construct multiple sub-classifiers in the second part. The results of multiple sub-classifiers are aggregated to obtain the final confidence score. Following that, the existence of PPIs is determined by the confidence score. We set a threshold θ , and say the interaction exists between the protein pair if its confidence score is bigger than θ . Conclusions: We applied our method to predict PPIs on data sets S. cerevisiae and Homo sapiens. Through experimental verification, our method outperforms state-of-the-art PPI prediction models. [ABSTRACT FROM AUTHOR]

Motivation Molecular property prediction is a hot topic in recent years. Existing graph-based models ignore the hierarchical structures of molecules. According to the knowledge of chemistry and pharmacy, the functional groups of molecules are closely related to its physio-chemical properties and binding affinities. So, it should be helpful to represent molecular graphs by fragments that contain functional groups for molecular property prediction. Results In this article, to boost the performance of molecule property prediction, we first propose a definition of molecule graph fragments that may be or contain functional groups, which are relevant to molecular properties, then develop a fragment-oriented multi-scale graph attention network for molecular property prediction, which is called FraGAT. Experiments on several widely used benchmarks are conducted to evaluate FraGAT. Experimental results show that FraGAT achieves state-of-the-art predictive performance in most cases. Furthermore, our case studies show that when the fragments used to represent the molecule graphs contain functional groups, the model can make better predictions. This conforms to our expectation and demonstrates the interpretability of the proposed model. Availability and implementation The code and data underlying this work are available in GitHub, at https://github.com/ZiqiaoZhang/FraGAT. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

The current computer vision usually requires abundant training samples to classify target images, while it requires only a small number of samples if it is the same task for humans. This article attempts to address the few-shot marine plankton image classification problem. The model proposed in this paper uses transfer learning to train a classifier on base classes and fine-tunes on new classes to train a new classifier. Considering the small number of training samples, effective representation of each image is very important. We use the soft max loss function and center loss function to jointly train the model in order to minimize the intra-class distance of the depth features and obtain more robust and discriminative depth features. We conduct experiments on multiple marine plankton image data sets, and the outcomes have proved the effectiveness of the model. Our model is competitive with many existing few-shot image classification models in performance. [ABSTRACT FROM AUTHOR]

The mining missing links and predicting upcoming links are two important topics in the link prediction. In the past decades, a variety of algorithms have been developed, the majority of which apply similarity measures to estimate the bonding probability between nodes. And for these algorithms, it is still difficult to achieve a satisfactory tradeoff among precision, computational complexity, robustness to network types, and scalability to network size. In this article, we propose a chaotic ant colony optimized (CACO) link prediction algorithm, which integrates the chaotic perturbation model and ant colony optimization. The extensive experiments on a wide variety of unweighted and weighted networks show that the proposed algorithm CACO achieves significantly higher prediction accuracy and robustness than most of the state-of-the-art algorithms. The results demonstrate that the chaotic ant colony effectively takes advantage of the fact that most real networks possess the transmission capacity and provides a new perspective for future link prediction research. [ABSTRACT FROM AUTHOR]

Background: The rapid development of single-cell RNA sequencing (scRNA-seq) enables the exploration of cell heterogeneity, which is usually done by scRNA-seq data clustering. The essence of scRNA-seq data clustering is to group cells by measuring the similarities among genes/transcripts of cells. And the selection of features for cell similarity evaluation is of great importance, which will significantly impact clustering effectiveness and efficiency. Results: In this paper, we propose a novel method called CaFew to select genes based on cluster-aware feature weighting. By optimizing the clustering objective function, CaFew obtains a feature weight matrix, which is further used for feature selection. The genes have large weights in at least one cluster or the genes whose weights vary greatly in different clusters are selected. Experiments on 8 real scRNA-seq datasets show that CaFew can obviously improve the clustering performance of existing scRNA-seq data clustering methods. Particularly, the combination of CaFew with SC3 achieves the state-of-art performance. Furthermore, CaFew also benefits the visualization of scRNA-seq data. Conclusion: CaFew is an effective scRNA-seq data clustering method due to its gene selection mechanism based on cluster-aware feature weighting, and it is a useful tool for scRNA-seq data analysis. [ABSTRACT FROM AUTHOR]

Clustering analysis has been widely applied to single-cell RNA-sequencing (scRNA-seq) data to discover cell types and cell states. Algorithms developed in recent years have greatly helped the understanding of cellular heterogeneity and the underlying mechanisms of biological processes. However, these algorithms often use different techniques, were evaluated on different datasets and compared with some of their counterparts usually using different performance metrics. Consequently, there lacks an accurate and complete picture of their merits and demerits, which makes it difficult for users to select proper algorithms for analyzing their data. To fill this gap, we first do a review on the major existing scRNA-seq data clustering methods, and then conduct a comprehensive performance comparison among them from multiple perspectives. We consider 13 state of the art scRNA-seq data clustering algorithms, and collect 12 publicly available real scRNA-seq datasets from the existing works to evaluate and compare these algorithms. Our comparative study shows that the existing methods are very diverse in performance. Even the top-performance algorithms do not perform well on all datasets, especially those with complex structures. This suggests that further research is required to explore more stable, accurate, and efficient clustering algorithms for scRNA-seq data. [ABSTRACT FROM AUTHOR]

Identifying protein complexes is an important issue in computational biology, as it benefits the understanding of cellular functions and the design of drugs. In the past decades, many computational methods have been proposed by mining dense subgraphs in Protein–Protein Interaction Networks (PINs). However, the high rate of false positive/negative interactions in PINs prevents accurately detecting complexes directly from the raw PINs. In this paper, we propose a denoising approach for protein complex detection by using variational graph auto-encoder. First, we embed a PIN to vector space by a stacked graph convolutional network (GCN), then decide which interactions in the PIN are credible. If the probability of an interaction being credible is less than a threshold, we delete the interaction. In such a way, we reconstruct a reliable PIN. Following that, we detect protein complexes in the reconstructed PIN by using several typical detection methods, including CPM, Coach, DPClus, GraphEntropy, IPCA and MCODE, and compare the results with those obtained directly from the original PIN. We conduct the empirical evaluation on four yeast PPI datasets (Gavin, Krogan, DIP and Wiphi) and two human PPI datasets (Reactome and Reactomekb), against two yeast complex benchmarks (CYC2008 and MIPS) and three human complex benchmarks (REACT, REACT_uniprotkb and CORE_COMPLEX_human), respectively. Experimental results show that with the reconstructed PINs obtained by our denoising approach, complex detection performance can get obviously boosted, in most cases by over 5%, sometimes even by 200%. Furthermore, we compare our approach with two existing denoising methods (RWS and RedNemo) while varying different matching rates on separate complex distributions. Our results show that in most cases (over 2/3), the proposed approach outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Emerging on-demand transport services, such as Uber and GoGoVan, usually face the dilemma of demand supply imbalance, meaning that the spatial distributions of orders and drivers are imbalanced. Due to such imbalance, much supply resource is wasted while a considerable amount of order demand cannot be met in time. To address this dilemma, knowing the unmet demand in the near future is of high importance for service providers because they can dispatch their vehicles in advance to alleviate the impending demand supply imbalance, we develop a general framework for predicting the unmet demand in future time slots. Under this framework, we first evaluate the predictability of unmet demand in on-demand transport services and find that unmet demand is highly predictable. Then, we extract both static and dynamic urban features relevant to unmet demand from data sets in multiple domains. Finally, multiple prediction models are trained to predict unmet demand by using the extracted features. As demonstrated via experiments, the proposed framework can predict unmet demand in on-demand transport services effectively and flexibly. [ABSTRACT FROM AUTHOR]

Temporal networks are composed of individuals with on-and-off interactions. In the study of human dynamics, a typical interaction is interpreted as a coincidental or forced concurrence of two events. Since human beings’ rationality is bounded, the interaction between sentient individuals is normally investigated under the framework of game theory in the past half a century. In this brief, a game model on social networks is introduced, in which individuals play a $2\times2$ divide-and-conquer game with their neighbors, which is a specific symmetric game based on the type of their interactions. The individuals in a network play with the game with a certain strategy. The duration of a continuous interaction is defined to be the number of the continuous rounds in which at least one of them receives a non-zero payoff. On the contrary, the inter-event time is measured by the number of the continuous rounds in which both players do not receive any payoff. A detailed analytical and numerical study of the model’s dynamical properties is presented, showing that it reproduces the burstiness of the human coordinating system. The findings reveal that the burstiness is inducible by rational interactions of humans. The new model and analysis shed some new lights on the origin of the burstiness of human activities. [ABSTRACT FROM AUTHOR]

Essential proteins are critical to the development and survival of cells. Identification of essential proteins is helpful for understanding the minimal set of required genes in a living cell and for designing new drugs. To detect essential proteins, various computational methods have been proposed based on protein-protein interaction (PPI) networks. However, protein interaction data obtained by high-throughput experiments usually contain high false positives, which negatively impacts the accuracy of essential protein detection. Moreover, most existing studies focused on the local information of proteins in PPI networks, while ignoring the influence of indirect protein interactions on essentiality. In this paper, we propose a novel method, called Essentiality Ranking (EssRank in short), to boost the accuracy of essential protein detection. To deal with the inaccuracy of PPI data, confidence scores of interactions are evaluated by integrating various biological information. Weighted edge clustering coefficient (WECC), considering both interaction confidence scores and network topology, is proposed to calculate edge weights in PPI networks. The weight of each node is evaluated by the sum of WECC values of its linking edges. A random walk method, making use of both direct and indirect protein interactions, is then employed to calculate protein essentiality iteratively. Experimental results on the yeast PPI network show that EssRank outperforms most existing methods, including the most commonly-used centrality measures (SC, DC, BC, CC, IC, and EC), topology based methods (DMNC and NC) and the data integrating method IEW. [ABSTRACT FROM AUTHOR]

Background: The default mode network (DMN) in resting state has been increasingly used in disease diagnosis since it was found in 2001. Prior work has mainly focused on extracting a single DMN with various techniques. However, by using seeding-based analysis with more than one desirable seed, we can obtain multiple DMNs, which are likely to have complementary information, and thus are more promising for disease diagnosis. In the study, we used 18 early mild cognitive impairment (EMCI) participants and 18 late mild cognitive impairment (LMCI) participants of Alzheimer's disease (AD). First, we used seeding-based analysis with four seeds to extract four DMNs for each subject. Then, we conducted fusion analysis for all different combinations of the four DMNs. Finally, we carried out nonlinear support vector machine classification based on the mixing coefficients from the fusion analysis. Results: We found that (1) the four DMNs corresponding to the four different seeds indeed capture different functional regions of each subject; (2) Maps of the four DMNs in the most different joint source from fusion analysis are centered at the regions of the corresponding seeds; (3) Classification results reveal the effectiveness of using multiple seeds to extract DMNs. When using a single seed, the regions of posterior cingulate cortex (PCC) extractions of EMCI and LMCI show the largest difference. For multiple-seed cases, the regions of PCC extraction and right lateral parietal cortex (RLP) extraction provide complementary information for each other in fusion, which improves the classification accuracy. Furthermore, the regions of left lateral parietal cortex (LLP) extraction and RLP extraction also have complementary effect in fusion. In summary, AD diagnosis can be improved by exploiting complementary information of DMNs extracted with multiple seeds. Conclusions: In this study, we applied fusion analysis to the DMNs extracted by using different seeds for exploiting the complementary information hidden among the separately extracted DMNs, and the results supported our expectation that using the complementary information can improve classification accuracy. [ABSTRACT FROM AUTHOR]

Prediction of compound-protein interactions (CPIs) is to find new compound-protein pairs where a protein is targeted by at least a compound, which is a crucial step in new drug design. Currently, a number of machine learning based methods have been developed to predict new CPIs in the literature. However, as there is not yet any publicly available set of validated negative CPIs, most existing machine learning based approaches use the unknown interactions (not validated CPIs) selected randomly as the negative examples to train classifiers for predicting new CPIs. Obviously, this is not quite reasonable and unavoidably impacts the CPI prediction performance. In this paper, we simply take the unknown CPIs as unlabeled examples, and propose a new method called PUCPI (the abbreviation of PU learning for Compound-Protein Interaction identification) that employs biased-SVM (Support Vector Machine) to predict CPIs using only positive and unlabeled examples. PU learning is a class of learning methods that leans from positive and unlabeled (PU) samples. To the best of our knowledge, this is the first work that identifies CPIs using only positive and unlabeled examples. We first collect known CPIs as positive examples and then randomly select compound-protein pairs not in the positive set as unlabeled examples. For each CPI/compound-protein pair, we extract protein domains as protein features and compound substructures as chemical features, then take the tensor product of the corresponding compound features and protein features as the feature vector of the CPI/compound-protein pair. After that, biased-SVM is employed to train classifiers on different datasets of CPIs and compound-protein pairs. Experiments over various datasets show that our method outperforms six typical classifiers, including random forest, L1- and L2-regularized logistic regression, naive Bayes, SVM and $k$ -nearest neighbor (kNN), and three types of existing CPI prediction models. More information can be found at http://admis.fudan.edu.cn/projects/pucpi.html. [ABSTRACT FROM AUTHOR]

With the proliferation of positioning technologies and GPS-enabled mobile devices, it has become very important to search for optimal paths to cover required points of interest (POIs, e.g., banks and restaurants) over road networks in many location-based services. In practice, however, traffic conditions are inherently uncertain and dynamically changing over time, which makes it rather challenging to provide accurate results for path queries based on travelling time. Inspired by this, we consider the practical settings of road networks and model them by uncertain road networks (URNs) on which the travelling time of each road is uncertain and captured by a set of travelling time samples. Then, we formalize the probabilistic time-constrained path ( PTP) query over uncertain road networks to retrieve those paths that not only cover required POIs with constrained service time but also have the minimum travelling times in high confidence. We prove that PTP query problem is NP-hard. In order to answer PTP queries efficiently, we propose an efficient PTP query approach with effective pruning strategies regarding the time constraints on POIs and the probabilistic/rank requirements of queries. Extensive experiments on real road networks validate the efficiency and effectiveness of our PTP query approach. [ABSTRACT FROM PUBLISHER]

The widespread location-aware applications produce a vast amount of spatio-textual data that contains both spatial and textual attributes. To make use of this enriched information for users to describe their preferences for travel routes, we propose a Bounded-Cost Informative Route (BCIR) query to retrieve the routes that are the most textually relevant to the user-specified query keywords subject to a travel cost constraint. BCIR query is particularly helpful for tourists and city explorers to plan their travel routes. We will show that BCIR query is an NP-hard problem. To answer BCIR query efficiently, we propose an exact solution with effective pruning techniques and two approximate solutions with performance guarantees. Extensive experiments over real data sets demonstrate that the proposed solutions achieve the expected performance. [ABSTRACT FROM PUBLISHER]

Extracting the hierarchical organization of networks is currently a pressing task for understanding complex networked systems. The hierarchy of a network is essentially defined by the heterogeneity of link densities of communities at different scales. Here, we define a top-level partition (TLP) as a bipartition of the network (or a sub-network) such that no top-level community (TLC) runs across the two parts. It has been found that a TLP generally has a higher modularity than a non-top-level (TLP) partition when their TLCs have similar sizes and when the link densities of neighboring levels are well separated from each other. A spectral TLP procedure is proposed here to search for TLPs of a network (or sub-network). To extract the hierarchical organization of large complex networks, an algorithm called TLPA has been developed based on the TLP. Experiments have shown that the method developed in this research extract hierarchy accurately from network data. [ABSTRACT FROM AUTHOR]

Modern communication networks and social networks are the main tunnels of knowledge diffusion. Knowledge diffusion in complex networks is different from the epidemic-like information spreading, because individuals are willing to learn and spread knowledge to their friends and the learning process can hardly be achieved in a few conversations. In this paper, we investigate the important issue as what topological structure is suitable for knowledge diffusion. We propose a new knowledge diffusion model, where both learning and forgetting mechanisms are considered. In this model, individuals can play imparter and learner simultaneously. Comparing knowledge diffusion on a series of complex topologies, we observe that the individuals with a large degree can quickly learn more knowledge, who are beneficial to knowledge diffusion. Our results surprisingly reveal that the networks with high degree-heterogeneity are likely to be suitable for knowledge diffusion. Our finding suggests that enhancing the degree heterogeneity of existing social networks may help to improve the performance of knowledge diffusion. This result is well confirmed by our extensive simulation results. Our model therefore provides a theoretical framework for understanding knowledge diffusion in complex topologies. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Nucleosomes and the free linker DNA between them assemble the chromatin. Nucleosome positioning plays an important role in gene transcription regulation, DNA replication and repair, alternative splicing, and so on. With the rapid development of ChIP-seq, it is possible to computationally detect the positions of nucleosomes on chromosomes. However, existing methods cannot provide accurate and detailed information about the detected nucleosomes, especially for the nucleosomes with complex configurations where overlaps and noise exist. Meanwhile, they usually require some prior knowledge of nucleosomes as input, such as the size or the number of the unknown nucleosomes, which may significantly influence the detection results. In this paper, we propose a novel approach DPNuc for identifying nucleosome positions based on the Dirichlet process mixture model. In our method, Markov chain Monte Carlo (MCMC) simulations are employed to determine the mixture model with no need of prior knowledge about nucleosomes. Compared with three existing methods, our approach can provide more detailed information of the detected nucleosomes and can more reasonably reveal the real configurations of the chromosomes; especially, our approach performs better in the complex overlapping situations. By mapping the detected nucleosomes to a synthetic benchmark nucleosome map and two existing benchmark nucleosome maps, it is shown that our approach achieves a better performance in identifying nucleosome positions and gets a higher $F$ -score. Finally, we show that our approach can more reliably detect the size distribution of nucleosomes. [ABSTRACT FROM PUBLISHER]

Genomic science is now facing an explosive increase of data thanks to the fast development of sequencing technology. This situation poses serious challenges to genomic data storage and transferring. It is desirable to compress data to reduce storage and transferring cost, and thus to boost data distribution and utilization efficiency. Up to now, a number of algorithms / tools have been developed for compressing genomic sequences. Unlike the existing algorithms, most of which treat genomes as one-dimensional text strings and compress them based on dictionaries or probability models, this paper proposes a novel approach called CoGI (the abbreviation of Co mpressing Genomes as an I mage) for genome compression, which transforms the genomic sequences to a two-dimensional binary image (or bitmap), then applies a rectangular partition coding algorithm to compress the binary image. CoGI can be used as either a reference-based compressor or a reference-free compressor. For the former, we develop two entropy-based algorithms to select a proper reference genome. Performance evaluation is conducted on various genomes. Experimental results show that the reference-based CoGI significantly outperforms two state-of-the-art reference-based genome compressors GReEn and RLZ-opt in both compression ratio and compression efficiency. It also achieves comparable compression ratio but two orders of magnitude higher compression efficiency in comparison with XM—one state-of-the-art reference-free genome compressor. Furthermore, our approach performs much better than Gzip—a general-purpose and widely-used compressor, in both compression speed and compression ratio. So, CoGI can serve as an effective and practical genome compressor. The source code and other related documents of CoGI are available at: http://admis.fudan.edu.cn/projects/cogi.htm. [ABSTRACT FROM PUBLISHER]