Search

Background: Clinical studies have demonstrated that microbes play a crucial role in human health and disease. The identification of microbe-disease interactions can provide insights into the pathogenesis and promote the diagnosis, treatment, and prevention of disease. Although a large number of computational methods are designed to screen novel microbe-disease associations, the accurate and efficient methods are still lacking due to data inconsistence, underutilization of prior information, and model performance. Methods: In this study, we proposed an improved deep learning-based framework, named GIMMDA, to identify latent microbe-disease associations, which is based on graph autoencoder and inductive matrix completion. By co-training the information from microbe and disease space, the new representations of microbes and diseases are used to reconstruct microbe-disease association in the end-to-end framework. In particular, a similarity fusion strategy is conducted to improve prediction performance. Results: The experimental results show that the performance of GIMMDA is competitive with that of existing state-of-the-art methods on 3 datasets (i.e., HMDAD, Disbiome, and multiMDA). In particular, it performs best with the area under the receiver operating characteristic curve (AUC) of 0.9735, 0.9156, 0.9396 on abovementioned 3 datasets, respectively. And the result also confirms that different similarity fusions can improve the prediction performance. Furthermore, case studies on two diseases, i.e., asthma and obesity, validate the effectiveness and reliability of our proposed model. Conclusion: The proposed GIMMDA model show a strong capability in predicting microbe-disease associations. We expect that GPUDMDA will help identify potential microbe-related diseases in the future. [ABSTRACT FROM AUTHOR]

Study tours for adolescent users are somewhat contemporary and traditional methods, such as questionnaires cannot meet their psychological expectations. To bring a better experience to teenagers' study tour, a Latent Dirichlet Allocation (LDA) theme model was used to mine teenage users and their interest points, and then the similarity between LDA and the check-in matrix was calculated and fused. Based on this, an RT-CNN model was built for deep feature extraction of review information, and point-of-interest recommendation was performed by fusing similarity, check-in behavior, and geographic location. The RT-CNN model had an accuracy of 92.7%, a recall of 87.1%, a Mean Absolute Error (MAE) value of 4.2%, a Root Mean Square Error (RMSE) of 4.8%, and F1 values of 89.2% and 88.7% in the two datasets. The new model in this experiment has high accuracy in making interest point recommendations and has a good overall performance. [ABSTRACT FROM AUTHOR]

Computational approaches employed for predicting potential microbe-disease associations often rely on similarity information between microbes and diseases. Therefore, it is important to obtain reliable similarity information by integrating multiple types of similarity information. However, existing similarity fusion methods do not consider multi-order fusion of similarity networks. To address this problem, a novel method of linear neighborhood label propagation with multi-order similarity fusion learning (MOSFL-LNP) is proposed to predict potential microbe-disease associations. Multi-order fusion learning comprises two parts: low-order global learning and high-order feature learning. Low-order global learning is used to obtain common latent features from multiple similarity sources. High-order feature learning relies on the interactions between neighboring nodes to identify high-order similarities and learn deeper interactive network structures. Coefficients are assigned to different high-order feature learning modules to balance the similarities learned from different orders and enhance the robustness of the fusion network. Overall, by combining low-order global learning with high-order feature learning, multi-order fusion learning can capture both the shared and unique features of different similarity networks, leading to more accurate predictions of microbe-disease associations. In comparison to six other advanced methods, MOSFL-LNP exhibits superior prediction performance in the leave-one-out cross-validation and 5-fold validation frameworks. In the case study, the predicted 10 microbes associated with asthma and type 1 diabetes have an accuracy rate of up to 90% and 100%, respectively. [ABSTRACT FROM AUTHOR]

Studies have shown that microbes are closely related to human health. Clarifying the relationship between microbes and diseases that cause health problems can provide new solutions for the treatment, diagnosis, and prevention of diseases, and provide strong protection for human health. Currently, more and more similarity fusion methods are available to predict potential microbe-disease associations. However, existing methods have noise problems in the process of similarity fusion. To address this issue, we propose a method called MSIF-LNP that can efficiently and accurately identify potential connections between microbes and diseases, and thus clarify the relationship between microbes and human health. This method is based on matrix factorization denoising similarity fusion (MSIF) and bidirectional linear neighborhood propagation (LNP) techniques. First, we use non-linear iterative fusion to obtain a similarity network for microbes and diseases by fusing the initial microbe and disease similarities, and then reduce noise by using matrix factorization. Next, we use the initial microbe-disease association pairs as label information to perform linear neighborhood label propagation on the denoised similarity network of microbes and diseases. This enables us to obtain a score matrix for predicting microbe-disease relationships. We evaluate the predictive performance of MSIF-LNP and seven other advanced methods through 10-fold cross-validation, and the experimental results show that MSIF-LNP outperformed the other seven methods in terms of AUC. In addition, the analysis of Cystic fibrosis and Obesity cases further demonstrate the predictive ability of this method in practical applications. [ABSTRACT FROM AUTHOR]

Recently, several land-cover classification models have achieved great success in terms of both accuracy and computational performance. However, it remains challenging due to interclass similarities, intraclass variations, scale-related inaccuracies, and high computational complexity. First, these methods fail to establish a correlation among different feature maps during multiscale feature extraction, leading to interclass similarities and intraclass variations. Second, they underutilize feature interdependencies of the context contained in each layer of the encoder–decoder architecture, causing scale-related inaccuracies. Third, they cause checkerboard artifacts and blurry edges, which can negatively impact the accuracy and generate segmentation map at increased computational cost. To address these problems, this article proposes a novel multiscale context-aware feature fusion network (MCN) for high-resolution urban scene images. MCN mainly consists of three modules: First, a multiscale feature enhancement module for backbone network to extract rich spatial information dynamically by incorporating dense correlation among feature maps with different receptive fields; second, multilayer feature fusion module as skip connections to produce a single high-level representation of the local–global context by capturing low-, mid-, and high-level interdependencies at different encoder–decoder stages; and third, pixel-shuffle decoder to reduce the blurry edges and checkerboard artifacts while upsampling with reduced number of parameters. Experiments on three high-resolution aerial and satellite urban scene datasets show that MCN consistently outperforms the mainstream land-cover classification models. Specifically, MCN achieves an OA of 93.51 on Potsdam, 90.18 on Vaihingen, and an mIoU of 73.73 on DeepGlobe.

Although significant progress has been made in scene classification of high-resolution remote-sensing images (HRRSIs), dual-modal HRRSI scene classification is still an active and challenging issue. In this study, we introduce an end-to-end dense-attention–similarity-fusion network (DASFNet) for dual-modal HRRSIs. Specifically, we propose a dense-attention map module based on graph convolution, which adaptively captures long-range semantic cues and further directs shallow-attention cues to the deep level to guide the generation of high-level feature attention cues. At the encoder stage, DASFNet uses feature similarity to explore the correlation between dual-modal features; a similarity-fusion module extracts complementary information by fusing features from different modalities. A multiscale context-feature-aggregation module is used to strengthen the feature embedding of any two spatial scales; this solves the of scale change problem. A large number of experiments on two HRRSI benchmark datasets for scene classification indicate that the proposed DASFNet outperforms the outstanding scene classification approaches.

Simple Summary: Accurate identification of potential targets for drugs to interact with can accelerate drug development. The identification of drug–target interactions can provide insights into hidden drug efficacy. This paper presents a prediction model based on feature similarity fusion that can identify crucial features of drugs and targets to help predict drug–target interactions. The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions. [ABSTRACT FROM AUTHOR]

Abstract Background Drug repositioning refers to the identification of new indications for existing drugs. Drug-based inference methods for drug repositioning apply some unique features of drugs for new indication prediction. Complementary information is provided by these different features. It is therefore necessary to integrate these features for more accurate in silico drug repositioning. Results In this study, we collect 3 different types of drug features (i.e., chemical, genomic and pharmacological spaces) from public databases. Similarities between drugs are separately calculated based on each of the features. We further develop a fusion method to combine the 3 similarity measurements. We test the inference abilities of the 4 similarity datasets in drug repositioning under the guilt-by-association principle. Leave-one-out cross-validations show the integrated similarity measurement IntegratedSim receives the best prediction performance, with the highest AUC value of 0.8451 and the highest AUPR value of 0.2201. Case studies demonstrate IntegratedSim produces the largest numbers of confirmed predictions in most cases. Moreover, we compare our integration method with 3 other similarity-fusion methods using the datasets in our study. Cross-validation results suggest our method improves the prediction accuracy in terms of AUC and AUPR values. Conclusions Our study suggests that the 3 drug features used in our manuscript are valuable information for drug repositioning. The comparative results indicate that integration of the 3 drug features would improve drug-disease association prediction. Our study provides a strategy for the fusion of different drug features for in silico drug repositioning.

The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions.

Background: Drug repositioning refers to the identification of new indications for existing drugs. Drug-based inference methods for drug repositioning apply some unique features of drugs for new indication prediction. Complementary information is provided by these different features. It is therefore necessary to integrate these features for more accurate in silico drug repositioning. Results: In this study, we collect 3 different types of drug features (i.e., chemical, genomic and pharmacological spaces) from public databases. Similarities between drugs are separately calculated based on each of the features. We further develop a fusion method to combine the 3 similarity measurements. We test the inference abilities of the 4 similarity datasets in drug repositioning under the guilt-by-association principle. Leave-one-out cross-validations show the integrated similarity measurement IntegratedSim receives the best prediction performance, with the highest AUC value of 0.8451 and the highest AUPR value of 0.2201. Case studies demonstrate IntegratedSim produces the largest numbers of confirmed predictions in most cases. Moreover, we compare our integration method with 3 other similarity-fusion methods using the datasets in our study. Cross-validation results suggest our method improves the prediction accuracy in terms of AUC and AUPR values. Conclusions: Our study suggests that the 3 drug features used in our manuscript are valuable information for drug repositioning. The comparative results indicate that integration of the 3 drug features would improve drug-disease association prediction. Our study provides a strategy for the fusion of different drug features for in silico drug repositioning. [ABSTRACT FROM AUTHOR]

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• This paper focuses on content-based information retrieval with similarity fusion. • Contextual information of fused similarity graph is used to enhance performance. • Sparsity of fused similarity matrix is utilized to improve retrieval efficiency. • The effectiveness of the proposed model is verified in 4 different retrieval tasks. • The proposed model can be modified and applied in other important retrieval tasks. Similarity networks contain important topological features and patterns critical to understanding interactions among samples in a large dataset. To create a comprehensive view of the interactions within a dataset, the Similarity Network Fusion (SNF) technique has been proposed to fuse the similarity networks based on different data types into one similarity network that represents the full spectrum of underlying data. In this paper, a modified version of SNF, which is named as Contextual Information based SNF (CI-SNF), is proposed. In CI-SNF, first, modified Jaccard distance is performed on the SNF fused similarity to utilize the contextual information contained in the fused similarity network. Second, the local consistency of samples from the same category is enhanced by speculating that the samples which are located high in the Jaccard distance based ranking list of a specific query are from the same category as the query. Third, the inverted index technique is introduced to utilize the sparsity property of the locally consistent similarity network to enhance the computational efficiency. To verify the effectiveness and efficiency of CI-SNF model, it is applied in four different tasks, Cover Song Identification (CSI), image classification, cancer subtype identification, and drug taxonomy, respectively. Extensive experiments on thirteen challenging datasets demonstrate that CI-SNF scheme outperforms state-of-the-art similarity fusion algorithms including SNF in all four tasks. It is also verified that utilizing the contextual information contained in the SNF-based similarity network helps to enhance the performance of the SNF-based scheme, further. [ABSTRACT FROM AUTHOR]

The traditional collaborative filtering model suffers from high-dimensional sparse user rating information and ignores user preference information contained in user reviews. To address the problem, this paper proposes a new collaborative filtering model UL SAM (UBCF LDA SIMILAR ADD MEAN) which integrates topic model with user-based collaborative filtering model. UL SAM extracts user preference information from user reviews through topic model and then fuses user preference information with user rating information by similarity fusion method to create fusion information. UL SAM creates collaborative filtering recommendations according to fusion information. It is the advantage of UL SAM on improving recommendation effectiveness that UL SAM enriches information for collaborative recommendation by integrating user preference with user rating information. Experimental results of two public datasets demonstrate significant improvement on recommendation effectiveness in our model. [ABSTRACT FROM AUTHOR]

A music similarity model that combines Cross Recurrence Plot (CRP) fusion and Multi-Kernel Integration (MKI) is proposed for Cover Song Identification (CSI) task. First, two complementary descriptors: Harmonic Pitch Class Profile (HPCP), which represents the harmonic progression, and MeLoDy (MLD), which describes the melody evolution, are extracted from each track. Then, the CRP between each pair of tracks is constructed based on HPCP descriptor and MLD descriptor, respectively. To take advantage of the complementarity between the recurrence properties described by the HPCP based and MLD based CRPs, nonlinear graph fusion technique is adopted to fuse them to obtain the fused CRP. Next, recurrence quantification analysis is applied to the fused CRP to obtain the similarity score. Finally, MKI is introduced to refine the obtained similarity score to make it fit for diverse statistical characteristics of the tracks. Experimental results on three cover song datasets verify the superiority of the proposed model, in terms of identification accuracy and classification accuracy, over state-of-the-art CSI schemes based on single similarity function or similarity fusion. The proposed model can be modified and applied in other tasks, such as image classification, visual object tracking, and drug taxonomy, etc. [ABSTRACT FROM AUTHOR]

Collaborative Filtering (CF) recommenders work by collecting user ratings for items in a given domain and computing similarities between users or items to produce recommendations. The user-item rating database is extremely sparse. This means the number of ratings obtained is very small compared with the number of ratings that need to be predicted. CF suffers from the sparsity problem, resulting in poor quality recommendations and reduced coverage. Further, a CF algorithm needs calculations that are very expensive and grow non-linearly with the number of users and items in a database. Incited by these challenges, we present Cluster-Based Similarity Fusion (CBSF), a new hybrid collaborative filtering algorithm which can deal with the sparsity and scalability issues simultaneously. By the use of carefully selected clusters of users and items, CBSF reduces the computational cost of traditional CF, while retaining high accuracy. Experimental results demonstrate that apart from being scalable, CBSF leads to a better precision and coverage for the recommendation engine.

The prediction of electrical machines’ Remaining Useful Life (RUL) can facilitate making electrical machine maintenance policies, which is important for improving their security and extending their life span. This paper proposes an RUL prediction model with similarity fusion of multi-parameter and multi-sample. Firstly, based on the time domain and frequency domain extraction of vibration signals, the performance damage indicator system of a gearbox is established to select the optimal damage indicators for RUL prediction. Low-pass filtering based on approximate entropy variance (Aev) is introduced in this process because of its stability. Secondly, this paper constructs Dynamic Time Warping Distance (DTWD) as a similarity measurement function, which belongs to the nonlinear dynamic programming algorithm. It performed better than the traditional Euclidean distance. Thirdly, based on DTWD, similarity fusion of multi-parameter and multi-sample methods is proposed here to achieve RUL prediction. Next, the performance evaluation indicator Q is adopted to evaluate the RUL prediction accuracy of different methods. Finally, the proposed method is verified by experiments, and the Multivariable Support Vector Machine (MSVM) and Principal Component Analysis (PCA) are introduced for comparative studies. The results show that the Mean Absolute Percentage Error (MAPE) of the similarity fusion of multi-parameter and multi-sample methods proposed here is below 14%, which is lower than MSVM’s and PCA’s. Additionally, the RUL prediction based on the DTWD function in multi-sample similarity fusion exhibits the best accuracy.

Collaborative filtering (CF) systems help address information overload, by using the preferences of users in a community to make personal recommendations for other users. The widespread use of these systems has exposed some well-known limitations, such as sparsity, scalability, and cold-start, which can lead to poor recommendations. During the last years, a great number of works have focused on the improvement of CF, but they do not solve all its problems efficiently. In this article, we present a new approach that applies semantic similarity fusion as well as biclustering to alleviate the aforementioned problems. The experimental results verify the effectiveness and efficiency of our approach over the benchmark CF methods. [ABSTRACT FROM AUTHOR]

Kinship verification using face images (KVFI) is a relatively new and challenging problem in computer vision and biometrics, while kin relationship in psychology has been well studied over the past decades. Recent advances in KVFI have shown that learning an effective similarity metric plays a critical role in the verification problem. However, most existing distance metric learning (DML) based KVFI methods use batch learning techniques to seek an optimal kin similarity metric, making them less scalable in practical verification tasks. To address this, we propose in this paper a scalable similarity learning (SSL) method for KVFI. Unlike existing DML-based solutions, SSL aims to learn a diagonal bilinear similarity model by online truncated gradient learning, which enjoys superiority in scalability and computational efficiency for practical KVFI with high-dimensional data. We further derive a multiview SSL algorithm by optimal fusion of the diagonal similarity models from multiple feature representations in a coherent online process, such that the interactions and correlations in multiview kin data can be leveraged to obtain refined and high-level information. Empirically, we evaluate our proposed method on two benchmark datasets against the state-of-the-art DML-based solutions, and the results demonstrate that our method can achieve competitive or better verification performance, and enjoys the superiority in scalability and computational efficiency. [ABSTRACT FROM AUTHOR]

This paper presents a classification-driven biomedical image retrieval framework based on image filtering and similarity fusion by employing supervised learning techniques. In this framework, the probabilistic outputs of a multiclass support vector machine (SVM) classifier as category prediction of query and database images are exploited at first to filter out irrelevant images, thereby reducing the search space for similarity matching. Images are classified at a global level according to their modalities based on different low-level, concept, and keypoint-based features. It is difficult to find a unique feature to compare images effectively for all types of queries. Hence, a query-specific adaptive linear combination of similarity matching approach is proposed by relying on the image classification and feedback information from users. Based on the prediction of a query image category, individual precomputed weights of different features are adjusted online. The prediction of the classifier may be inaccurate in some cases and a user might have a different semantic interpretation about retrieved images. Hence, the weights are finally determined by considering both precision and rank order information of each individual feature representation by considering top retrieved relevant images as judged by the users. As a result, the system can adapt itself to individual searches to produce query-specific results. Experiment is performed in a diverse collection of 5 000 biomedical images of different modalities, body parts, and orientations. It demonstrates the efficiency (about half computation time compared to search on entire collection) and effectiveness (about 10%–15% improvement in precision at each recall level) of the retrieval approach. [ABSTRACT FROM PUBLISHER]

Abstract: This paper presents a learning-based unified image retrieval framework to represent images in local visual and semantic concept-based feature spaces. In this framework, a visual concept vocabulary (codebook) is automatically constructed by utilizing self-organizing map (SOM) and statistical models are built for local semantic concepts using probabilistic multi-class support vector machine (SVM). Based on these constructions, the images are represented in correlation and spatial relationship-enhanced concept feature spaces by exploiting the topology preserving local neighborhood structure of the codebook, local concept correlation statistics, and spatial relationships in individual encoded images. Finally, the features are unified by a dynamically weighted linear combination of similarity matching scheme based on the relevance feedback information. The feature weights are calculated by considering both the precision and the rank order information of the top retrieved relevant images of each representation, which adapts itself to individual searches to produce effective results. The experimental results on a photographic database of natural scenes and a bio-medical database of different imaging modalities and body parts demonstrate the effectiveness of the proposed framework. [Copyright &y& Elsevier]

Abstract: We present a content-based image retrieval framework for diverse collections of medical images of different modalities, anatomical regions, acquisition views, and biological systems. For the image representation, the probabilistic output from multi-class support vector machines (SVMs) with low-level features as inputs are represented as a vector of confidence or membership scores of pre-defined image categories. The outputs are combined for feature-level fusion and retrieval based on the combination rules that are derived by following Bayes’ theorem. We also propose an adaptive similarity fusion approach based on a linear combination of individual feature level similarities. The feature weights are calculated by considering both the precision and the rank order information of top retrieved relevant images as predicted by SVMs. The weights are dynamically updated by the system for each individual search to produce effective results. The experiments and analysis of the results are based on a diverse medical image collection of 11,000 images of 116 categories. The performances of the classification and retrieval algorithms are evaluated both in terms of error rate and precision–recall. Our results demonstrate the effectiveness of the proposed framework as compared to the commonly used approaches based on low-level feature descriptors. [Copyright &y& Elsevier]

The prediction of electrical machines' Remaining Useful Life (RUL) can facilitate making electrical machine maintenance policies, which is important for improving their security and extending their life span. This paper proposes an RUL prediction model with similarity fusion of multi-parameter and multi-sample. Firstly, based on the time domain and frequency domain extraction of vibration signals, the performance damage indicator system of a gearbox is established to select the optimal damage indicators for RUL prediction. Low-pass filtering based on approximate entropy variance (Aev) is introduced in this process because of its stability. Secondly, this paper constructs Dynamic Time Warping Distance (DTWD) as a similarity measurement function, which belongs to the nonlinear dynamic programming algorithm. It performed better than the traditional Euclidean distance. Thirdly, based on DTWD, similarity fusion of multi-parameter and multi-sample methods is proposed here to achieve RUL prediction. Next, the performance evaluation indicator Q is adopted to evaluate the RUL prediction accuracy of different methods. Finally, the proposed method is verified by experiments, and the Multivariable Support Vector Machine (MSVM) and Principal Component Analysis (PCA) are introduced for comparative studies. The results show that the Mean Absolute Percentage Error (MAPE) of the similarity fusion of multi-parameter and multi-sample methods proposed here is below 14%, which is lower than MSVM's and PCA's. Additionally, the RUL prediction based on the DTWD function in multi-sample similarity fusion exhibits the best accuracy. [ABSTRACT FROM AUTHOR]

The identification of cancer subtypes is crucial to cancer diagnosis and treatments. A number of methods have been proposed to identify cancer subtypes by integrating multi-omics data in recent years. However, the existing methods rarely consider the biases of similarity between samples and weights of different omics data in integration. More accurate and flexible integration approaches need to be developed to comprehensively investigate cancer subtypes. In this paper, we propose a simple and flexible similarity fusion model for integrating multi-omics data to identify cancer subtypes. We consider the similarity biases between samples in each omics data and predict corrected similarities between samples using a generalized linear model. We integrate the corrected similarity information from multi-omics data according to different data-view weights. Based on the integrative similarity information, we cluster patient samples into different subtype groups. Comprehensive experiments demonstrate that the proposed approach obtains more significant results than the state-of-the-art integrative methods. In conclusion, our approach provides an effective and flexible tool to investigate subtypes in cancer by integrating multi-omics data. [ABSTRACT FROM AUTHOR]