MOTIVATION: Accurate prediction of synergistic drug combinations can accelerate anticancer combination discovery. Existing methods inadequately model higher order drug-drug-cell-line interactions and drug-disease associations and remain sensitive to sparse and noisy multiomics data, limiting generalization to unseen cell lines and drug combinations. RESULTS: We present Momentum Contrast (MoCo)-MultiSynergy, a multimodal framework that combines modality-specific momentum contrastive learning with heterogeneous hypergraph modeling. The hypergraph represents synergistic drug-drug-cell-line triplets and drug-disease associations, while gated residual propagation refines node representations. MoCo modules regularize encoded drug and cell-line representations using latent feature masking and Gaussian perturbation. On the O'Neil and NCI-ALMANAC datasets, MoCo-MultiSynergy achieves the highest AUROC and AUPRC across the evaluated settings, with the largest gains when generalizing to unseen cell lines and drug combinations. AVAILABILITY AND IMPLEMENTATION: Source code is available at https://github.com/27167199/MoCo-MultiSynergy.

The arduous and costly journey of drug discovery is increasingly intersecting with computational approaches, which promise to accelerate the analysis of bioassays and biomedical literature. The critical role of microRNAs (miRNAs) in disease progression has been underscored in recent studies, elevating them as potential therapeutic targets. This emphasizes the need for the development of sophisticated computational models that can effectively identify promising drug targets such as miRNAs. Herein, we present a novel method, termed Duplex Link Prediction (DLP), rooted in subspace segmentation, to pinpoint potential miRNA targets. Our approach initiates with the application of the Network Enhancement (NE) algorithm to refine the similarity metric between miRNAs. Thereafter, we construct two matrices by pre-loading the association matrix from both the drug and miRNA perspectives, employing the K Nearest Neighbors (KNN) technique. The DLSR algorithm is then applied to predict potential associations. The final predicted association scores are ascertained through the weighted mean of the two matrices. Our empirical findings suggest that the DLP algorithm outperforms current methodologies in the realm of identifying potential miRNA drug targets. Case study validations further reinforce the real-world applicability and effectiveness of our proposed method.

Accurately predicting drug-drug interaction events (DDIEs) is critical for optimizing combination therapies and ensuring drug safety. However, existing methods typically rely on either handcrafted molecular fingerprints or static embeddings from pretrained models, which limits their ability to jointly capture local chemical substructures and three-dimensional geometric features. To overcome these limitations, we propose MMFF-DDI, a multi-modal fusion framework based on contrastive learning for drug-drug interaction event (DDIE) prediction. MMFF-DDI extracts drug representations from three modalities-Morgan fingerprints, canonical SMILES, and 3D molecular graphs-using an attention-augmented autoencoder, a MolFormer encoder, and an Equivariant Graph Neural Network (EGNN), respectively. Furthermore, a contrastive multi-modal integration submodule is designed to transform multi-modal representation learning from a concatenation-based paradigm to an alignment-based paradigm, thereby achieving cross-modal consistency and complementary feature fusion. Experimental results show that MMFF-DDI outperforms the best competitive method (MRGCDDI) in predicting DDIE involving existing drugs, achieving improvements of 7.87% and 7.99% in Macro-F1 and Macro-precision, respectively. Furthermore, MMFF-DDI outperforms the best competitive method (DSN-DDI) in predicting DDIEs involving new drugs, achieving improvements of 8.06% and 12.79% in Macro-F1 and Macro-precision, respectively. Visualization experiments and case studies validate its practical applicability and superior predictive performance.

Effective segmentation of unseen categories in zero-shot semantic segmentation is hindered by models’ limited ability to interpret edges in unfamiliar contexts. In this paper, we propose EdgeCLIP, which addresses this by integrating CLIP with explicit edge-awareness. Based on the premise that edge variation patterns are similar across both seen and unseen class objects, EdgeCLIP introduces the Contextual Edge Sensing module. This module accurately discerns and utilizes edge information, which is crucial in complex border areas where conventional models struggle. Further, our Text-Guided Dense Feature Matching strategy precisely aligns text encodings with corresponding visual edge features, effectively distinguishing them from background edges. This strategy not only optimizes the training of CLIP’s image and text encoders but also leverages the intrinsic completeness of objects, enhancing the model’s ability to generalize and accurately segment objects in unseen classes. EdgeCLIP significantly outperforms the current state-of-the-art method, achieving a deep impressive margin of 17.5% on COCO-20i datasets. Our code is available at github.com/aqingaqinghh/EdgeCLIP.

Evaluating the blood-brain barrier (BBB) perme-ability of potential drugs is a critical step in the initial phases of drug discovery and development, especially for enhancing the effectiveness of central nervous system (CNS) medications. Traditional experimental methods are not only costly but also time-intensive, prompting the development of computational techniques utilizing Graph Neural Networks (GNNs) to predict drug BBB permeability. Although these techniques have shown significant promise, there is still room for improvement in their predictive accuracy. Furthermore, they also face challenges related to over-parameterization and over-smoothing. Therefore, we introduce MRCCBBB, a method built on a multi-relational graph neural network (MRGNN) with Collaborative Constraints, including both feature and topological constraints. First, we construct drug-protein heterogeneous graph and initialize the features of drugs and proteins. Next, we apply MRGNN with collaborative constraints to learn the embeddings of drugs, which alleviates over-smoothing and over-parameterization problems by preserving some of the original information and using only one learnable weight coefficient for each relation, respectively. Finally, we process the drug embeddings using PairNorm and then feed them into a single-layer multilayer perceptron (MLP). The compared experiment results demonstrate that MRCCBBB outperforms other methods and can effectively predict the drug BBB permeability.

MicroRNAs (miRNAs) are short non-coding RNAs, typically 18–25 nucleotides long, that serve as key regulators of gene expression. They participate in numerous biological activities, including cell growth, differentiation, metabolic processes, and programmed cell death. The subcellular localization of miRNAs directly influences their function and is closely associated with the development of various diseases. Therefore, accurately predicting miRNA subcellular localization is essential for understanding their functional mechanisms, identifying potential biomarkers, and advancing precision medicine. To address the limitations of existing methods in multi-source data fusion and feature representation, this study proposes a computational method called HyCoMiLoc, based on hypergraph convolution and contrastive learning. HyCoMiLoc integrates multi-source features of miRNAs, including miRNA sequence features, miRNA functional similarity, miRNA-disease associations, and miRNA-mRNA associations. Additionally, hyperedges are constructed based on the miRNA functional similarity network, and hyper-graph convolution is applied to capture high-order relationships. A contrastive learning framework is then employed to integrate miRNA sequence, miRNA-mRNA, and miRNA-disease features, optimizing feature representation and enhancing generalization ability, thereby improving prediction performance. On a public benchmark dataset, the average prediction performance of the model for seven subcellular localization categories reach AUC 0.9467 and AUPR 0.8664, which are 0.0434 and 0.0951 higher than the existing best model PMiSLocMF.

MOTIVATION: Accurately identifying and predicting molecular properties is a crucial task in molecular machine learning, and the key lies in how to extract effective molecular representations. Contrastive learning opens new avenues for representation learning, and a large amount of unlabeled data enables the model to generalize to the huge chemical space. However, existing contrastive learning-based models face two challenges: (i) existing methods destroy the original molecular environment and ignore chemical prior information, and (ii) there is a lack of a prior knowledge to guide the prediction of molecular properties. RESULTS: In this work, we propose a molecular property prediction framework called MolFCL, which consists of fragment-based contrastive learning and functional group-based prompt learning. Specifically, we introduced fragment-fragment interactions for the first time in the contrastive learning framework and designed a fragment-based augmented molecular graph that integrates the original chemical environment and fragment reactions. Furthermore, we proposed a novel functional group-based prompt learning during fine-tuning, which first incorporates functional group knowledge and the corresponding atomic signals, to improve molecular representation and provide interpretable analyses. The results show that MolFCL outperforms state-of-the-art baseline models on 23 molecular property prediction datasets. Moreover, visualizations show that MolFCL can learn to embed molecules into representations that can distinguish chemical properties. MolFCL can give higher weight to functional groups consistent with chemical knowledge during the prediction of molecular properties, which offers an interpretable ability of the model. Overall, MolFCL is a practically useful tool for molecular property prediction and assists drug scientists in designing drugs more effectively. AVAILABILITY AND IMPLEMENTATION: MolFCL is available at https://github.com/tangxiangcsu/MolFCLSupplementary.

MOTIVATION: Drug side effects refer to harmful or adverse reactions that occur during drug use, unrelated to the therapeutic purpose. A core issue in drug side effect prediction is determining the frequency of these drug side effects in the population, which can guide patient medication use and drug development. Many computational methods have been developed to predict the frequency of drug side effects as an alternative to clinical trials. However, existing methods typically build regression models on five frequency classes of drug side effects and tend to overfit the training set, leading to boundary handling issues and the risk of overfitting. RESULTS: To address this problem, we develop a multi-source similarity fusion-based model, named multi-source similarity fusion (MSSF), for predicting five frequency classes of drug side effects. Compared to existing methods, our model utilizes the multi-source feature fusion module and the self-attention mechanism to explore the relationships between drugs and side effects deeply and employs Bayesian variational inference to more accurately predict the frequency classes of drug side effects. The experimental results indicate that MSSF consistently achieves superior performance compared to existing models across multiple evaluation settings, including cross-validation, cold-start experiments, and independent testing. The visual analysis and case studies further demonstrate MSSF's reliable feature extraction capability and promise in predicting the frequency classes of drug side effects. AVAILABILITY AND IMPLEMENTATION: The source code of MSSF is available on GitHub (https://github.com/dingxlcse/MSSF.git) and archived on Zenodo (DOI: 10.5281/zenodo.15462041).

Probiotics are active microorganisms that provide substantial health benefits. They can serve as an alternative or complement to medications, enabling effective and targeted treatment for various diseases. However, traditional experimental methods for screening probiotics are time-consuming and labor-intensive, underscoring the need for efficient computational approaches. While some studies have introduced link prediction methods based on known probiotic-disease associations, these methods often fail to address errors and noise within the dataset and overlook the rich, intrinsic features of probiotics and diseases. To address these limitations, this paper presents MFFPDA, the first deep-learning framework based on multi-feature fusion for predicting probiotic-disease associations. We systematically screened a probiotic-disease association dataset and collected probiotic and disease-related data from various sources. Furthermore, we calculate multiple features of probiotics and diseases, and design some feature extraction and fusion modules to integrate these features. The comparison results demonstrate that MFFPDA surpasses all other comparison methods. Feature visualization results confirmed the necessity and rationale for incorporating multi-source features. Additionally, case studies on colonic pseudo-obstruction and dysentery further validated the effectiveness of MFFPDA, underscoring its reliability as a tool for predicting probiotic-disease associations.

Molecular associations are central to most biological processes. The discovery and identification of potential associations between molecules can provide insights into biological exploration, diagnostic and therapeutic interventions, and drug development. So far many relevant computational methods have been proposed, but most of them are usually limited to specific domains and rely on complex preprocessing procedures, which restricts the models' ability to be applied to other tasks. Therefore, it remains a challenge to explore a generalized approach to accurately predicting potential associations. In this study, We propose Left-Right Transition Matrices (LRTM) for molecular association prediction. From the perspective on the diffusion model, we construct two transition matrices to model undirected graph information propagation. This allows modeling the transition probabilities of links, which facilitates link prediction in molecular bipartite networks. The extensive experimental results show that the proposed LRTM algorithm performs better than the compared methods. Also, the proposed algorithm has the potential for cross-task prediction. Furthermore, case studies show that LRTM is a powerful tool that can be effectively applied to practical applications.

To date, the study of the resistance between miRNA (microRNA) and drugs has consistently garnered widespread attention.Understanding the resistance between miRNAs and drugs holds significant implications for disease treatment and the development of new drugs. However, traditional biological experimental models are time-consuming and costly, and existing computational models still need further improvement in capturing complex miRNA drug resistance. We propose a miRNA-drug resistance prediction model based on a self-attention mechanism and contrastive learning(SMCL-MDR). The model uses the self-attention mechanism to encode the features of miRNAs and drugs, adaptively capturing their complex resistance. The self-attention mechanism effectively handles long-distance dependencies, enhancing the model’s focus on important features. In addition, to enhance the model’s robustness and prediction accuracy, we employ a contrastive learning strategy. By creating positive and negative sample pairs, the model maximizes the similarity among positive pairs and minimizes it among negative pairs, thereby improving the learning of feature representations for miRNAs and drugs. Experimental results show that our model attains AUC and AUPR scores of 0.9896 and 0.9881 on the ncDR dataset, significantly outperforming existing calculation models and demonstrating substantial application potential. The proposed miRNA-drug resistance prediction model based on the self-attention mechanism and contrastive learning not only exhibits high prediction accuracy and robustness but also provides new ideas and methods for future miRNA-drug research.

Privacy-Preserving Decision Tree (PPDT) evaluation is a typical algorithm in Machine Learning as a Service scenario. For services like health analysis, PPDT evaluation by fusing private data from multiple Wearable Devices is necessary. Homomorphic Encryption (HE) implements PPDT evaluation without revealing locally sensitive data. However, existing HE schemes need better scalability and are incompatible with clients such as Wearable Devices, which have limited computing power, bandwidth, memory, and storage. This paper proposed a noninteractive PPDT evaluation scheme for multiple Wearable Devices. We apply transciphering technology and an efficient Fully Homomorphic Encryption (FHE) cryptosystem to optimize overall performance. Simultaneously, a Computing Server and a Trusted Third Party (TTP) are adopted to perform all the homomorphic operations on the server side, leaving clients to encrypt and decrypt local data using stream ciphers. Then, we implement an instance of our scheme based on FiLIP stream cipher, a homomorphic comparison algorithm, and a homomorphic traverse algorithm. The experimental results show that the various overheads on the client side are relatively lower.

MOTIVATION: Drug-drug interactions (DDIs) can cause unexpected adverse drug reactions, affecting treatment efficacy and patient safety. The need for computational methods to predict DDIs has been growing due to the necessity of identifying potential risks associated with drug combinations in advance. Although several deep learning methods have been recently proposed to predict DDIs, many overlook feature learning based on interactions between the substructures of drug pairs. RESULTS: In this work, we introduce a molecular Substructure-based Dual Attention Feature Learning framework (MSDAFL), designed to fully utilize the information between substructures of drug pairs to enhance the performance of DDI prediction. We employ a self-attention module to obtain a set number of self-attention vectors, which are associated with various substructural patterns of the drug molecule itself, while also extracting interaction vectors representing inter-substructure interactions between drugs through an interactive attention module. Subsequently, an interaction module based on cosine similarity is used to further capture the interactive characteristics between the self-attention vectors of drug pairs. We also perform normalization after the interaction feature extraction to mitigate overfitting. After applying three-fold cross-validation, the MSDAFL model achieved average precision scores of 0.9707, 0.9991, and 0.9987, and area under the receiver operating characteristic curve scores of 0.9874, 0.9934, and 0.9974 on three datasets, respectively. In addition, the experiment results of five-fold cross-validation and cross-datum study also indicate that MSDAFL performs well in predicting DDIs. AVAILABILITY AND IMPLEMENTATION: Data and source codes are available at https://github.com/27167199/MSDAFL.

Many studies have proven that microRNAs (miRNAs) can participate in a wide range of biological processes and can be considered as potential noninvasive biomarkers for disease diagnosis and prognosis. However, it is well-established that identifying potential miRNA-disease associations through wet-lab experimental methods is expensive and time-consuming. Therefore, many computational methods have been developed to reduce the cost of identifying miRNA-disease associations, ultimately enhancing the efficiency of disease diagnosis and treatment. In this study, we also introduced a new computational method called PMDAGS, which predicts miRNA-disease associations by utilizing graph nonlinear diffusion convolution network and similarities. PMDAGS first calculates miRNA functional similarity and disease functional similarity based on miRNA-target interactions and disease-gene associations, respectively. Additionally, we compute Gaussian Interaction Profile (GIP) kernel similarities of miRNAs and diseases based on the known miRNA-disease associations. The final miRNA similarity is obtained by fusing the miRNA GIP kernel similarity to fill in the zero values of miRNA functional similarity. Similarly, based on disease functional similarity and GIP kernel similarity, we obtain the final disease similarity using the same principle. Next, we construct the initial feature of each miRNA (disease) by concatenating its final similarity vector with its known association vector. Based on the known miRNA-disease association network and the initial feature vector of each node, we further apply nonlinear diffusion graph convolution network model to extract the feature embedding vectors. Finally, we concatenate the feature embedding vectors of miRNA and disease and input them into a multi-layer perceptron to generate the low-dimensional embedding of miRNA-disease pairs, which is then fed into a sigmoid classifier to identify potential miRNA-disease associations. To evaluate the prediction performance of our method and compare it with other computational methods, we conduct 5-fold cross validation (5CV), 10-fold cross validation (10CV), and global leave-one-out cross validation (GLOOCV) on HMDD v2.0 and HMDD v3.2. The evaluation metrics includes the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPR), accuracy, precision, recall, and F1-score. PMDAGS achieves AUCs of 0.9222, 0.9228, and 0.9221 under 5CV, 10CV and GLOOCV on HMDD v2.0, respectively. In addition, PMDAGS also achieves AUC values of 0.9366, 0.9377, and 0.9376 under 5CV, 10CV and GLOOCV on HMDD v3.2, respectively. According to the experimental results, we can conclude that PMDAGS outperforms other compared methods. Additionally, the case studies also demonstrate that PMDAGS can effectively predict miRNA-disease associations and provide assistance in disease diagnosis and treatment.

Identifying miRNA-disease associations (MDAs) is crucial for improving the diagnosis and treatment of various diseases. However, biological experiments can be time-consuming and expensive. To overcome these challenges, computational approaches have been developed, with Graph Convolutional Networks (GCNs) showing promising results in MDAs prediction. The success of GCN-based methods relies on learning a meaningful spatial operator to extract effective node feature representations. To enhance the inference of MDAs, we propose a novel method called PGCNMDA, which employs graph convolutional networks with a learning graph spatial operator from paths. This approach enables the generation of meaningful spatial convolutions from paths in GCNs, leading to improved prediction performance. We evaluate PGCNMDA using 5-fold cross-validation (5-CV) on databases HMDD v2.0 and HMDD v3.2. Additionally, we compare it with other methods. The experimental results demonstrate that PGCNMDA outperforms other miRNA-disease association prediction methods.

Deep learning has played an important role in medical image segmentation of liver and liver tumors, but existing models are still insufficient in accuracy and efficiency. In this paper, We proposed SCTransNet, a 3D image segmentation model based on the fusion of CNN and Transformer model. SCTransNet combines the feature extraction and expression capabilities of convolutional neural network(CNN) and the long-distance dependency modeling capability of Transformer model. SCTransNet improves the embedding layer and position encoding layer of the Transformer model to enhance the global contextual feature extraction ability. Meanwhile, a spatial attention module and a channel attention module based on improved Transformer model are designed in SCTransNet to enhance the feature extraction ability of low-dimensional pixel information and high-dimensional semantic information. Experimental results on the public dataset show that SCTransNet achieve relatively better performance than state-of-the-art methods.

Emerging evidence has proved that circular RNAs (circRNAs) are implicated in pathogenic processes. They are regarded as promising biomarkers for diagnosis due to covalently closed loop structures. As opposed to traditional experiments, computational approaches can identify circRNA-disease associations at a lower cost. Aggregating multi-source pathogenesis data helps to alleviate data sparsity and infer potential associations at the system level. The majority of computational approaches construct a homologous network using multi-source data, but they lose the heterogeneity of the data. Effective methods that use the features of multi-source data are considered as a matter of urgency. In this paper, we propose a model (CDHGNN) based on edge-weighted graph attention and heterogeneous graph neural networks for potential circRNA-disease association prediction. The circRNA network, micro RNA network, disease network and heterogeneous network are constructed based on multi-source data. To reflect association probabilities between nodes, an edge-weighted graph attention network model is designed for node features. To assign attention weights to different types of edges and learn contextual meta-path, CDHGNN infers potential circRNA-disease association based on heterogeneous neural networks. CDHGNN outperforms state-of-the-art algorithms in terms of accuracy. Edge-weighted graph attention networks and heterogeneous graph networks have both improved performance significantly. Furthermore, case studies suggest that CDHGNN is capable of identifying specific molecular associations and investigating biomolecular regulatory relationships in pathogenesis. The code of CDHGNN is freely available at https://github.com/BioinformaticsCSU/CDHGNN.

The Anatomical Therapeutic Chemical (ATC) classification system, designated by the World Health Organization Collaborating Center (WHOCC), has been widely used in drug screening, repositioning, and similarity research. The ATC classification system assigns different codes to drugs according to the organ or system on which they act and/or their therapeutic and chemical characteristics. Correctly identifying the potential ATC codes for drugs can accelerate drug development and reduce the cost of experiments. Several classifiers have been proposed in this regard. However, they lack of ability to learn basic features from sparsely known drug-ATC code associations. Therefore, there is an urgent need for novel computational methods to precisely predict potential drug-ATC code associations in multiple levels of the ATC classification system based on known associations between drugs and ATC codes. In this paper, we provide a novel end-to-end model, so-called RNPredATC, to predict potential drug-ATC code associations in five ATC classification levels. RNPredATC can extract dense feature vectors from sparsely known drug-ATC code associations and reduce the impact from the degradation problem by a novel deep residual learning. We extensively compare our method with some state-of-the-art methods, including NetPredATC, SPACE, and some multi-label-based methods. Our experimental results show that RNPredATC achieves better performances in five-fold and ten-fold cross validations. Furthermore, the visualization analysis of hidden layers and case studies of predicted associations at the fifth ATC classification level confirm that RNPredATC can effectively identify the potential ATC codes of drugs.

The identification of drug-target relations (DTRs) is substantial in drug development. A large number of methods treat DTRs as drug-target interactions (DTIs), a binary classification problem. The main drawback of these methods are the lack of reliable negative samples and the absence of many important aspects of DTR, including their dose dependence and quantitative affinities. With increasing number of publications of drug-protein binding affinity data recently, DTRs prediction can be viewed as a regression problem of drug-target affinities (DTAs) which reflects how tightly the drug binds to the target and can present more detailed and specific information than DTIs. The growth of affinity data enables the use of deep learning architectures, which have been shown to be among the state-of-the-art methods in binding affinity prediction. Although relatively effective, due to the black-box nature of deep learning, these models are less biologically interpretable. In this study, we proposed a deep learning-based model, named AttentionDTA, which uses attention mechanism to predict DTAs. Different from the models using 3D structures of drug-target complexes or graph representation of drugs and proteins, the novelty of our work is to use attention mechanism to focus on key subsequences which are important in drug and protein sequences when predicting its affinity. We use two separate one-dimensional Convolution Neural Networks (1D-CNNs) to extract the semantic information of drug's SMILES string and protein's amino acid sequence. Furthermore, a two-side multi-head attention mechanism is developed and embedded to our model to explore the relationship between drug features and protein features. We evaluate our model on three established DTA benchmark datasets, Davis, Metz, and KIBA. AttentionDTA outperforms the state-of-the-art deep learning methods under different evaluation metrics. The results show that the attention-based model can effectively extract protein features related to drug information and drug features related to protein information to better predict drug target affinities. It is worth mentioning that we test our model on IC50 dataset, which provides the binding sites between drugs and proteins, to evaluate the ability of our model to locate binding sites. Finally, we visualize the attention weight to demonstrate the biological significance of the model. The source code of AttentionDTA can be downloaded from https://github.com/zhaoqichang/AttentionDTA_TCBB.

Identifying the function of therapeutic peptides is an important issue in the development of novel drugs. To reduce the time and labor costs required to identify therapeutic peptides, computational methods are increasingly required. However, most of the existing peptide therapeutic function prediction models are used for predicting a single therapeutic function, ignoring the fact that a bioactive peptide might simultaneously consist of multi-activities. Furthermore, in the few existing multi-label classification models, the feature extraction procedures are still rough. We propose a multi-label framework, called SCN-MLTPP, with a stacked capsule network for predicting the therapeutic properties of peptides. Instead of using peptide sequence vectors alone, SCN-MLTPP extracts different view representation vectors from the therapeutic peptides and learns the contributions of different views to the properties of therapeutic peptides based on the dynamic routing mechanism. Benchmarking results show that as compared with existing multi-label predictors, SCN-MLTPP achieves better and more robust performance for different peptides. In addition, some visual analyses and case studies also demonstrate the model can reliably capture features from multi-view data and predict different peptides.

Drug discovery and drug repurposing often rely on the successful prediction of drug-target interactions (DTIs). Recent advances have shown great promise in applying deep learning to drug-target interaction prediction. One challenge in building deep learning-based models is to adequately represent drugs and proteins that encompass the fundamental local chemical environments and long-distance information among amino acids of proteins (or atoms of drugs). Another challenge is to efficiently model the intermolecular interactions between drugs and proteins, which plays vital roles in the DTIs. To this end, we propose a novel model, GIFDTI, which consists of three key components: the sequence feature extractor (CNNFormer), the global molecular feature extractor (GF), and the intermolecular interaction modeling module (IIF). Specifically, CNNFormer incorporates CNN and Transformer to capture the local patterns and encode the long-distance relationship among tokens (atoms or amino acids) in a sequence. Then, GF and IIF extract the global molecular features and the intermolecular interaction features, respectively. We evaluate GIFDTI on six realistic evaluation strategies and the results show it improves DTI prediction performance compared to state-of-the-art methods. Moreover, case studies confirm that our model can be a useful tool to accurately yield low-cost DTIs. The codes of GIFDTI are available at https://github.com/zhaoqichang/GIFDTI.

MicroRNAs (miRNAs) as small 19- to 24-nucleotide noncoding RNAs play crucial roles in some key biological progress associated with human diseases. Therefore, identifying the essentiality of miRNAs is important to systematically understand the pathogenic mechanism of diseases. There are some computational methods have been developed to predict essential miRNAs because traditional biological experiments are both time- and labor-consuming. However, these computational methods only used the statistical feature and structural feature of miRNA sequences. The timing characteristics of sequences also should be considered to improve the prediction performance. In addition, the capability deep learning model is well-known. Therefore, in this study, we present a computational method (called EMDS) to predict essential miRNAs. EMDS takes not only the statistical and structural features of sequences but also the subsequence features based on the time characteristics of sequences and Convolutional Neural Networks (CNN). Furthermore, considering that the successful applications of attention mechanism and the subsequence in a miRNA sequence are important, we use a neural attention mechanism to obtain subsequence features of miRNAs. Finally, we integrate the statistical features and structural features, subsequence features as final miRNA features which is inputted into Light Gradient Boosting Machine (LGBM) to predict essential miRNAs. We evaluate the prediction performance of our method by the 5-fold cross validation. We also compare EMDS with other four competing methods which include PESM, miES, Gaussian Naive Bayes (Gaus_NB) and Support Vector Machine (SVM) by performing same cross validation experiments. The results show that EMDS achieves better prediction performance in terms of AUC (EMDS:0.9335, PESM:0.9117, miES:0.8837, Gaus_NB:0.8720, SVM:0.8571). It also illustrates that our method can effectively predict the essential miRNAs.

Identifying microbe-drug associations is important to systematically understand a drug’s mechanism of action in the therapeutic application. Since identifying microbe-drug associations is expensive and time-consuming via biological experiments, in this study, we propose a Pre-completion-based Label Propagation (PLP) method (called PLPMDA) to predict microbe-drug associations based on the multi-type similarities. To obtain richer information of drugs and microbes, we calculate drug chemical structure similarity, drug Anatomical Therapeutic Chemical (ATC) code similarity, microbe functional similarity, microbe sequence similarity and Gaussian Interaction Profile (GIP) kernel similarities of microbes and drugs, and then introduce a non-linear similarity fusion method. Comparing baseline methods, our advantage lies in performing an effective pre-completion step on the initial association matrix from the drug-related and microbe-related information and does not rely on the known drug-microbe associations, which can accelerate the design and discovery of the new drugs. The computational experiment results demonstrate that our proposed approach PLPMDA achieves significantly higher performance than the comparative methods in de novo and cross-validation experiments.

Receptor-binding is the first step of viral infection. Discovering potential virus-receptor interactions may give insight into potential strategies for treating viral infectious diseases. Most of computational methods for the virus-receptor interaction prediction are mainly based on sequence information. They neither makes effective use of structure information nor effectively handles with missing values of multiple similarities. In addition, the Link Prediction via linear optimization (LP) only uses contribution of neighbors of a node and ignores contribution of neighbors of another node on the network link. In this article, we present a virus-receptor interaction prediction method (MVLP) based on Multi-View learning and LP via contributions of all neighbors of two nodes on the network link. First, missing values of the receptor secondary structure similarity, the receptor conserved domain secondary structure similarity, the viral protein secondary structure similarity, the viral protein sequence similarity and the viral genome sequence similarity are updated by the gaussian radial basis function (GRB). To improve these similarities, we fuse updated and initial values of each similarity with multi-view learning, respectively. Next, three virus values and receptor similarities are integrated into the comprehensive virus and receptor similarity by the averaging method, respectively. Finally, LP based on contribution of neighbors of two nodes is presented for the virus-receptor interaction prediction. To evaluate the ability of MVLP, we compare MVLP with four related methods in 10 fold Cross-Validation (10CV). Computational results indicate that an average Area Under Curve (AUC) values of MVLP on viralReceptor sup and viralReceptor are 0.9427 and 0.9444, respectively, which are superior to other related methods. Furthermore, a case study also demonstrates the ability of MVLP in practice.

Determining drug indications is a critical part of the drug development process. However, traditional drug discovery is expensive and time-consuming. Drug repositioning aims to find potential indications for existing drugs, which is considered as an important alternative to the traditional drug discovery. In this article, we propose a multi-view learning with matrix completion (MLMC) method to predict the potential associations between drugs and diseases. Specifically, MLMC first learns the comprehensive similarity matrices from five drug similarity matrices and two disease similarity matrices based on the multi-view learning (ML) with Laplacian graph regularization, and updates the drug-disease association matrix simultaneously. Then, we introduce matrix completion (MC) to add some positive entries in original association matrix based on low-rank structure, and re-execute the multi-view learning algorithm for association prediction. At last, the prediction results of the above two operations are integrated as the final output. Evaluated by 10-fold cross-validation and de novo tests, MLMC achieves higher prediction accuracy than the current state-of-the-art methods. Moreover, case studies confirm the ability of our method in novel drug-disease association discovery. The codes of MLMC are available at https://github.com/BioinformaticsCSU/MLMC. Contact: [email protected].

MOTIVATION: Many studies have shown that microRNAs (miRNAs) play a key role in human diseases. Meanwhile, traditional experimental methods for miRNA-disease association identification are extremely costly, time-consuming and challenging. Therefore, many computational methods have been developed to predict potential associations between miRNAs and diseases. However, those methods mainly predict the existence of miRNA-disease associations, and they cannot predict the deep-level miRNA-disease association types. RESULTS: In this study, we propose a new end-to-end deep learning method (called PDMDA) to predict deep-level miRNA-disease associations with graph neural networks (GNNs) and miRNA sequence features. Based on the sequence and structural features of miRNAs, PDMDA extracts the miRNA feature representations by a fully connected network (FCN). The disease feature representations are extracted from the disease-gene network and gene-gene interaction network by GNN model. Finally, a multilayer with three fully connected layers and a softmax layer is designed to predict the final miRNA-disease association scores based on the concatenated feature representations of miRNAs and diseases. Note that PDMDA does not take the miRNA-disease association matrix as input to compute the Gaussian interaction profile similarity. We conduct three experiments based on six association type samples (including circulations, epigenetics, target, genetics, known association of which their types are unknown and unknown association samples). We conduct fivefold cross-validation validation to assess the prediction performance of PDMDA. The area under the receiver operating characteristic curve scores is used as metric. The experiment results show that PDMDA can accurately predict the deep-level miRNA-disease associations. AVAILABILITY AND IMPLEMENTATION: Data and source codes are available at https://github.com/27167199/PDMDA.

A drug-drug interaction (DDI) is defined as an association between two drugs where the pharmacological effects of a drug are influenced by another drug. Positive DDIs can usually improve the therapeutic effects of patients, but negative DDIs cause the major cause of adverse drug reactions and even result in the drug withdrawal from the market and the patient death. Therefore, identifying DDIs has become a key component of the drug development and disease treatment. In this study, we propose a novel method to predict DDIs based on the integrated similarity and semi-supervised learning (DDI-IS-SL). DDI-IS-SL integrates the drug chemical, biological and phenotype data to calculate the feature similarity of drugs with the cosine similarity method. The Gaussian Interaction Profile kernel similarity of drugs is also calculated based on known DDIs. A semi-supervised learning method (the Regularized Least Squares classifier) is used to calculate the interaction possibility scores of drug-drug pairs. In terms of the 5-fold cross validation, 10-fold cross validation and de novo drug validation, DDI-IS-SL can achieve the better prediction performance than other comparative methods. In addition, the average computation time of DDI-IS-SL is shorter than that of other comparative methods. Finally, case studies further demonstrate the performance of DDI-IS-SL in practical applications.

Viral infectious diseases have become a serious threat to human health and global security. The receptor-binding is the first step of viral infection. Identifying potential virus-receptor interactions gives us a new perspective on understanding interaction mechanisms, and further find potential targets for prevention and therapy of viral infectious diseases. Many predicted methods have been proposed to identify potential virus-receptor interactions. They didn’t focus on fusing multiple biological features and using multiple similarity measures depending on multiple biological characteristics to improve the prediction performance. In this study, a novel predictive method (LOMCVRI) is proposed to identify potential VirusReceptor Interactions based on similarity fusion and Matrix Completion of Linear optimization. In LOMCVRI, the viral protein structure similarity, the viral protein sequence similarity and the viral genomic sequence similarity are computed based on viral secondary structure features, viral protein sequences and viral genomic sequences, respectively. The gaussian radial basis function is used to improve these viral similarities. They are further combined into a compositive viral similarity by the linear weighting average method. Second, we compute the receptor conserved domain sequence similarity, the receptor sequence similarity and the receptor protein-protein interaction network (PPI) similarity based on the receptor conserved domain sequences, the receptor amino acid sequences and the human PPI data. They are also fused into a compositive receptor similarity. Next, the K-nearest neighbor preprocessing is employed to prefill missing entries in original interaction matrix. Finally, based on updated virus-receptor interactions and compositive similarities of virus and receptor, the matrix completion of linear optimization is applied to identify potential virus-receptor interactions. 10-fold Cross-Validation (10CV) and Leave-One-Out Cross-Validation (LOOCV) experimental results show that the area under of ROC curve (AUC) values of LOMCVRI are 0.9231 and 0.9438, respectively, which consistently outperforms all other related methods. In addition, a case study further confirms the effectiveness of our method.

Various microbes have proved to be closely related to the pathogenesis of human diseases. While many computational methods for predicting human microbe-disease associations (MDAs) have been developed, few systematic reviews on these methods have been reported. In this study, we provide a comprehensive overview of the existing methods. Firstly, we introduce the data used in existing MDA prediction methods. Secondly, we classify those methods into different categories by their nature and describe their algorithms and strategies in detail. Next, experimental evaluations are conducted on representative methods using different similarity data and calculation methods to compare their prediction performances. Based on the principles of computational methods and experimental results, we discuss the advantages and disadvantages of those methods and propose suggestions for the improvement of prediction performances. Considering the problems of the MDA prediction at present stage, we discuss future work from three perspectives including data, methods and formulations at the end.

With the development of high-through sequencing technology and microbiology, many studies have evidenced that microbes are associated with human diseases, such as obesity, liver cancer, and so on. Therefore, identifying the association between microbes and diseases has become an important study topic in current bioinformatics. The emergence of microbe-disease association database has provided an unprecedented opportunity to develop computational method for predicting microbe-disease associations. In the study, we propose a low-rank matrix completion method (called MCHMDA) to predict microbe-disease associations by integrating similarities of microbes and diseases and known microbe-disease associations into a heterogeneous network. The microbe similarity is computed from Gaussian Interaction Profile (GIP) kernel similarity based on the known microbe-disease associations. Then, we further improve the microbe similarity by taking into account the inhabiting organs of these microbes in human body. The disease similarity is computed by the average of disease GIP similarity, disease symptom-based similarity, and disease functional similarity. Then, we construct a heterogeneous microbe-disease association network by integrating the microbe similarity network, disease similarity network, and known microbe-disease association network. Finally, a matrix completion method is used to calculate the association scores of unknown microbe-disease pairs by the fast Singular Value Thresholding (SVT) algorithm. Via 5-fold Cross Validation (5CV) and Leave-One-Out Cross Validation (LOOCV), we evaluate the prediction performances of MCHMDA and other state-of-the-art methods which include BRWMDA, NGRHMDA, LRLSHMDA, and KATZHMDA. On benchmark dataset HMDAD, the experimental results show that MCHMDA outperforms other methods in terms of area under the receiver operating characteristic curve (AUC). MCHMDA achieves the AUC values of 0.9251 and 0.9495 in 5CV and LOOCV, respectively, which are the highest values among the competing methods. In addition, we also further indicate the prediction generality of MCHMDA on an expanded microbe-disease associations dataset (HMDAD-SUP). Finally, case studies prove the prediction ability in practical applications.

BACKGROUND: MicroRNAs (miRNAs) are a kind of small noncoding RNA molecules that are direct posttranscriptional regulations of mRNA targets. Studies have indicated that miRNAs play key roles in complex diseases by taking part in many biological processes, such as cell growth, cell death and so on. Therefore, in order to improve the effectiveness of disease diagnosis and treatment, it is appealing to develop advanced computational methods for predicting the essentiality of miRNAs. RESULT: In this study, we propose a method (PESM) to predict the miRNA essentiality based on gradient boosting machines and miRNA sequences. First, PESM extracts the sequence and structural features of miRNAs. Then it uses gradient boosting machines to predict the essentiality of miRNAs. We conduct the 5-fold cross-validation to assess the prediction performance of our method. The area under the receiver operating characteristic curve (AUC), F-measure and accuracy (ACC) are used as the metrics to evaluate the prediction performance. We also compare PESM with other three competing methods which include miES, Gaussian Naive Bayes and Support Vector Machine. CONCLUSION: The results of experiments show that PESM achieves the better prediction performance (AUC: 0.9117, F-measure: 0.8572, ACC: 0.8516) than other three computing methods. In addition, the relative importance of all features also further shows that newly added features can be helpful to improve the prediction performance of methods.

Many current studies have evidenced that microbes play important roles in human diseases. Therefore, discovering the associations between microbes and diseases is beneficial to systematically understanding the mechanisms of diseases, diagnosing, and treating complex diseases. It is well known that finding new potential microbe-disease associations via biological experiments is a time-consuming and expensive process. However, the computation methods can provide an opportunity to effectively predict microbe-disease associations. In recent years, efforts toward predicting microbe-disease associations are not in proportional to the importance of microbes to human diseases. In this study, we develop a method (called BRWMDA) to predict new microbe-disease associations based on similarity and improving bi-random walk on the disease and microbe networks. BRWMDA integrates microbe network, disease network, and known microbe-disease associations into a single network. After calculating the Gaussian Interaction Profile (GIP) kernel similarity of microbes based on known microbe-disease associations, the microbe network is obtained by adjusting the similarity with the logistics function. In addition, the disease network is computed by the similarity network fusion (SNF) method with the symptom-based similarity and the GIP kernel similarity based on known microbe-disease associations. Then, these two networks of microbe and disease are connected by known microbe-disease associations. Based on the assumption that similar microbes are normally associated with similar diseases and vice versa, BRWMDA is employed to predict new potential microbe-disease associations via random walk with different steps on microbe and disease networks, which reasonably uses the similarity of microbe network and disease network. The 5-fold cross validation and Leave One Out Cross Validation (LOOCV) are adopted to assess the prediction performance of our BRWMDA algorithm, as well as other competing methods for comparison. 5-fold cross validation experiments show that BRWMDA obtained the maximum AUC value of 0.9087, which is again superior to other methods of 0.9025(NGRHMDA), 0.8797 (LRLSHMDA), 0.8571 (KATZHMDA), 0.7782 (HGBI), and 0.5629 (NBI). In addition, BRWMDA also outperforms other methods in terms of LOOCV, whose AUC value is 0.9397, which is superior to other methods of 0.9111(NGRHMDA), 0.8909 (LRLSHMDA), 0.8644 (KATZHMDA), 0.7866 (HGBI), and 0.5553 (NBI). Case studies also illustrate that BRWMDA is an effective method to predict microbe-disease associations.

Complex and diverse microbial communities do not only take important roles in human health and disease, but also are clinically drug targets. Predicting potential microbe-drug associations is helpful to understand complex mechanisms of microbes in clinical treatment, drug discovery, combinations, and repositioning. But potential microbe-drug association's prediction is time-consuming and expensive by using biological experiments, while computational methods can effectively overcome these limitations. To predict Human Microbe-Drug Association, a new computational method of KATZ measure (HMDAKATZ) is proposed. As we have known so far, HMDAKATZ is the first tool to predict potential associations between microbe and drug. In our method, we firstly construct the microbe similarity network by computing the GIP kernel similarity of microbes based on known microbe-drug associations. Then, the drug similarity network is constructed by integrating the chemical structures similarity and GIP kernel similarity of drugs. We further construct the microbe-drug heterogeneous network based on two similarity networks and known microbe-drug associations. Based on the microbe-drug heterogeneous network, we apply HMDAKATZ to predict potential microbe-drug associations based on the microbe-drug heterogeneous network. The experimental result shows that HMDAKATZ has obtained an average area under the curve (AUC) value of$0.9010\pm 0.0020$in the 5-fold cross validation (5-fold CV). Furthermore, a case study also demonstrate that 100% of top 20 potential drugs of human immunodeficiency virus have been validated by existing literature, confirming the effectiveness of HMDAKATZ.

Shared e-bikes are popular because of their green, eco-friendly and efficient features. Due to the limited battery capacity of the e-bikes, the energy problem has become one of the main factors limiting its further development. The energy problem can be solved by using static charging piles (SCP) to replenish the batteries of shared e-bike. The location of the shared e-bike is time-varying, resulting in the optimal deployment of SCP as a complex location problem. In this paper, we propose an optimal Deployment algorithm for Maximum Coverage combined the Dynamic Changes of nodes (max-DCDC) based on the known number of SCP. This method first quantitatively analyzes the dynamic change process of the shared e-bike to reduce the deployment scope of the SCP. Then, according to the geometric characteristics of the e-bike distribution within the deployment scope to optimizes the deployment location of the SCP. Simulation experiments show that max-DCDC has better performance in terms of deployment stability and e-bike coverage compared with the other algorithms.

BACKGROUND: A drug-drug interaction (DDI) is defined as a drug effect modified by another drug, which is very common in treating complex diseases such as cancer. Many studies have evidenced that some DDIs could be an increase or a decrease of the drug effect. However, the adverse DDIs maybe result in severe morbidity and even morality of patients, which also cause some drugs to withdraw from the market. As the multi-drug treatment becomes more and more common, identifying the potential DDIs has become the key issue in drug development and disease treatment. However, traditional biological experimental methods, including in vitro and vivo, are very time-consuming and expensive to validate new DDIs. With the development of high-throughput sequencing technology, many pharmaceutical studies and various bioinformatics data provide unprecedented opportunities to study DDIs. RESULT: In this study, we propose a method to predict new DDIs, namely DDIGIP, which is based on Gaussian Interaction Profile (GIP) kernel on the drug-drug interaction profiles and the Regularized Least Squares (RLS) classifier. In addition, we also use the k-nearest neighbors (KNN) to calculate the initial relational score in the presence of new drugs via the chemical, biological, phenotypic data of drugs. We compare the prediction performance of DDIGIP with other competing methods via the 5-fold cross validation, 10-cross validation and de novo drug validation. CONLUSION: In 5-fold cross validation and 10-cross validation, DDRGIP method achieves the area under the ROC curve (AUC) of 0.9600 and 0.9636 which are better than state-of-the-art method (L1 Classifier ensemble method) of 0.9570 and 0.9599. Furthermore, for new drugs, the AUC value of DDIGIP in de novo drug validation reaches 0.9262 which also outperforms the other state-of-the-art method (Weighted average ensemble method) of 0.9073. Case studies and these results demonstrate that DDRGIP is an effective method to predict DDIs while being beneficial to drug development and disease treatment.

BACKGROUND: Viral infectious diseases are the serious threat for human health. The receptor-binding is the first step for the viral infection of hosts. To more effectively treat human viral infectious diseases, the hidden virus-receptor interactions must be discovered. However, current computational methods for predicting virus-receptor interactions are limited. RESULT: In this study, we propose a new computational method (IILLS) to predict virus-receptor interactions based on Initial Interaction scores method via the neighbors and the Laplacian regularized Least Square algorithm. IILLS integrates the known virus-receptor interactions and amino acid sequences of receptors. The similarity of viruses is calculated by the Gaussian Interaction Profile (GIP) kernel. On the other hand, we also compute the receptor GIP similarity and the receptor sequence similarity. Then the sequence similarity is used as the final similarity of receptors according to the prediction results. The 10-fold cross validation (10CV) and leave one out cross validation (LOOCV) are used to assess the prediction performance of our method. We also compare our method with other three competing methods (BRWH, LapRLS, CMF). CONLUSION: The experiment results show that IILLS achieves the AUC values of 0.8675 and 0.9061 with the 10-fold cross validation and leave-one-out cross validation (LOOCV), respectively, which illustrates that IILLS is superior to the competing methods. In addition, the case studies also further indicate that the IILLS method is effective for the virus-receptor interaction prediction.

In the anonymous communication mechanisms based on key infrastructure, public key or pre-shared key are widely used to set up relay paths and negotiate shared keys in session. Therefore, these systems always have complicated architecture and high key management cost. However, key infrastructure is hard to deployed in distributed environment. Based on multi-paths network coding, this paper firstly proposes a new information slicing and transmitting method ITNC. Then a novel anonymous communication mechanism AC-ITNC without key infrastructure, which is based on ITNC, is presented. In the new mechanism, the anonymous path setup information is sliced into pieces and each piece is coded by the random coding coefficient. The coding coefficients and coded information pieces are delivered along multiple paths, which makes the anonymous relay paths be set up in the case of non-cryptographic scheme. Theoretical analysis and simulation results show that AC-ITNC can significantly improve the security against conspiracy attack in anonymous communication system without key infrastructure.

With the development of Internet applications, a number of anonymous communication systems have been realized to protect the identity of communication participants. Therefore, it is essential to give a theoretically based and practically usable objective numerical measure for the provided level of anonymity. In this paper some typical anonymity measures are analyzed and limitations of these measures was highlighted. Then a new anonymity measure based on partial entropy is proposed, in which the anonymity is measured by using the entropy of the probability distribution of some distinct subjects in anonymity set. The results of analysis and calculation show that the new measure is preferable for anonymity evaluation.