Since genomics was proposed, the exploration of genes has been the focus of research. The emergence of single-cell RNA sequencing (scRNA-seq) technology makes it possible to explore gene expression at the single-cell level. Due to the limitations of sequencing technology, the data contains a lot of noise. At the same time, it also has the characteristics of high-dimensional and sparse. Clustering is a common method of analyzing scRNA-seq data. This paper proposes a novel single-cell clustering method called Robust Manifold Nonnegative Low-Rank Representation with Adaptive Total-Variation Regularization (MLRR-ATV). The Adaptive Total-Variation (ATV) regularization is introduced into Low-Rank Representation (LRR) model to reduce the influence of noise through gradient learning. Then, the linear and nonlinear manifold structures in the data are learned through Euclidean distance and cosine similarity, and more valuable information is retained. Because the model is non-convex, we use the Alternating Direction Method of Multipliers (ADMM) to optimize the model. We tested the performance of the MLRR-ATV model on eight real scRNA-seq datasets and selected nine state-of-the-art methods as comparison methods. The experimental results show that the performance of the MLRR-ATV model is better than the other nine methods.

The advancement of single-cell RNA sequencing (scRNA-seq) technology has enabled researchers to capture cellular heterogeneity at the individual cell level, driving progress in diverse fields such as developmental biology, immunology, and cancer research. Accurate cell clustering is a crucial step for researchers utilizing scRNA-seq data; however, inherent characteristics like high dimensionality and sparsity pose significant challenges to obtaining precise clustering results. To achieve accurate clustering, this paper proposes a novel approach that integrates dimensionality reduction, self-representation matrix construction, and the clustering process into an end-to-end model termed LDSLRR (Low-Dimensional Sparse and Low-Rank Representation). Specifically, the original gene expression matrix first undergoes dimensionality reduction via projection. Subsequently, low-rank representation combined with a sparsity constraint facilitates the learning of the self-representation matrix. Finally, the cluster assignment matrix is acquired using graph-regularized non-negative matrix factorization (NMF). These three modules are simultaneously optimized, enhancing the accuracy of the clustering results. Comparative experiments against multiple state-of-the-art clustering methods on various scRNA-seq datasets demonstrate the superiority of the proposed LDSLRR method.

Accurate prediction of drug-disease associations (DDAs) is essential for drug repositioning and the development of novel therapeutic strategies. However, existing methods often suffer from limited prior knowledge and the use of oversimplified negative sampling techniques, which hinder their ability to capture the complex relationships between drugs and diseases. To break through these limitations, we propose a new model, Hierarchical Attention Mechanism-Based Negative Sampling (HA-NegS), which aims to enhance the prediction of potential DDAs. In this study, HA-NegS further computes the similarity information between drugs and diseases and constructs heterogeneous and homogeneous networks based on it. For the similarity network, HA-NegS fuses Graph Convolutional Network (GCN) and Graph Attention Network (GAT) to effectively capture the neighborhood features of the target nodes. Subsequently, the model incorporates a hierarchical sampling strategy using the PageRank algorithm to rank nodes in descending order of global importance. The attention mechanism is then used to calculate the attention score and re-rank the nodes accordingly. This approach ensures the reliability of the negative sample selection. In order to obtain optimized representations, we use graph contrastive learning methods to refine drug and disease features with homogeneous and heterogeneous neighborhood information. Experimental results on a benchmark dataset show that HA-NegS outperforms existing baseline methods in predicting DDA. In addition, case studies for Alzheimer's disease and Parkinson's disease highlight the effectiveness of HA-NegS in discovering new therapeutic applications for existing drugs.

Recent advancements in spatial transcriptomics technology have enabled the capture of gene expression profiles while maintaining spatial information. Accurately identifying spatial clustering plays a pivotal role in analyzing spatial transcriptomics data and understanding tissue microenvironments. However, current spatial domain identification methods cannot explore the complex relationship of gene expression profiles and spatial topology. To alleviate this issue, we propose STMCCL, a novel self-supervised learning framework that jointly trains a masked autoencoder and cluster-guided contrastive learning. This framework extracts informative latent representations from gene expression profiles and spatial information. Specifically, we first use data augmentation strategies to build augmented views and employ a masked encoder to generate a feature view. Then, encoders are applied to learn view-unique embeddings of each view. Furthermore, we introduce a multiple cluster-perspectives module that considers both geometric and structural relationships between clusters to produce more reliable cluster assignments. Finally, to derive more discriminative positives and negatives, the cluster-guided contrastive module calculates the confidence of each sample based on the initial cluster. Comprehensive experiments on 7 public datasets demonstrate that STMCCL outperforms the state-of-the-art baselines with finer-scale spatial domain identification.

A mounting body of research indicates that dysregulation of MicroRNAs (miRNAs) causes disease through a variety of underlying mechanisms. Predicting microRNA (miRNA)-disease associations (MDAs) is essential for disease prognosis and therapeutics. Compared to conventional biological experiments, computational models save time and effort. A new method is proposed inspired by the graph convolutional networks. It has been named Multi source similarity fusion-based graph convolutional neural network and attention mechanism network for predicting miRNA-disease associations (MGAMDA). First, the several similarity networks between miRNAs and diseases were built. Then, multi-source information network is fused. And the feature was aggregated by using GCNs. In order to address the different levels of importance of the information, an attention mechanism was used to assign weights. The similar features of the disease side and miRNA side were finally obtained separately. It is combined with the association features that are obtained from the association information, and then it is fed into the multi-layer perceptron (MLP). To obtain prediction scores for unknown associations between miRNAs and diseases, a multilayer perceptron was utilized. To validate the new methodology's effectiveness, we performed a series of experimental studies using the Human MicroRNA Disease Database (HMDD v3.2). The performance of the$\mathbf{5}$-fold cross-validation on the datasets shows that MGAMDA surpasses other methods in the area of AUC, AUPR, ACC, F1-score, Recall, and Precision. Furthermore, case studies have demonstrated that MGAMDA accurately predicts miRNAs associated with colon, breast, and stomach cancer.

The development of spatial transcriptomics (ST) has enabled the simultaneous preservation of gene expression profiles and spatial information, facilitating deeper insights into the tissue microenvironment. Spatial domain identification is a critical challenge in ST analysis. To address this, we propose STAGCL, a contrastive learning framework with an adversarial mechanism to identify spatial domains. Specifically, we first construct high-quality augmented views using both learnable and predefined augmentation strategies. These views are then processed by encoders to learn unique latent representations. Additionally, we introduce a contrastive learning framework with an adversarial mechanism to extract reliable clustering information and mitigate semantic drift. To encourage the clustering to guide model learning, we employ a label matching mechanism that aligns semantic labels with high-confidence pseudo-labels. On five real datasets, we perform STAGCL and seven state-of-the-art methods. Extensive experiments reveal the superiority of our proposed method in spatial domain identification.

Single-cell RNA sequencing (scRNA-seq) is a key technology for studying cellular heterogeneity. However, the high levels of sparsity and noise in scRNA-seq data present challenges for accurate cell clustering. To address this, we propose Graph-based ZINB Deep Clustering for Single-cell RNA-seq Data (scGZDC), a novel framework that operates within a variational autoencoder (VAE). The encoder of scGZDC employs a Graph Convolutional Network (GCN) to learn low-dimensional representations by leveraging both a preprocessed gene expression matrix and the cell-cell similarity graph. The decoder, in turn, employs a Graph Attention Network (GAT) to reconstruct gene expression counts via a Zero-Inflated Negative Binomial (ZINB) distribution, a distribution particularly well-suited for scRNA-seq data. To achieve end-to-end optimization, a Deep Embedding for Clustering (DEC) objective is integrated into the framework. Extensive experiments on public datasets demonstrate that scGZDC consistently outperforms existing methods. Our results show that unifying graph structural information with a suitable probabilistic model in an end-to-end clustering framework is an effective strategy for improving single-cell analysis.

Clustering is critical for scRNA-seq because it reveals the similarity of single-cell expression patterns. However, single-cell data contains numerous noises and outliers. Traditional clustering algorithms may fail to capture accurate clustering information. In this study, we propose the GAEKLRR method for single-cell type identification, which is a low-rank representation (LRR) method based on a graph autoencoder (GAE) and relaxed k-means. GAEKLRR consists of gedLRR and relaxed k-means. Among them, gedLRR is a GAEbased LRR algorithm that captures structural information and node features of samples using GAE. Relaxed k-means is a soft clustering method that can better preserve complex relationships between samples through soft partitioning. Specifically, to reduce the impact of noise and outliers on the mapping benchmark, GAEKLRR generates a robust graph embedding dictionary using gedLRR. Due to the reconstruction using inner product distance, the graph embedding dictionary has interpretability. Meanwhile, to capture accurate clustering information, GAEKLRR utilizes gedLRR to seek the LRR matrix of the graph embedding dictionary while using relaxed k -means to update the clustering centroid. It is worth noting that the continuous clustering indication matrix captured by relaxed k-means contains clustering labels, which can be used directly for clustering tasks. Finally, experiments on real singlecell datasets demonstrate that GAEKLRR has significant advantages for clustering.

Accurate and efficient detection of epileptic seizures from electroencephalogram (EEG) signals is of great significance for clinical diagnosis and real-time monitoring. However, traditional EEG analysis methods face limitations in feature extraction and classification accuracy, primarily due to their heavy reliance on handcrafted features and rigid decision boundaries. Moreover, in clinical settings, the scarcity of seizure EEG signals and the difficulty in obtaining labeled data often lead to overfitting, especially when training data is insufficient. To address these challenges, this paper proposes a novel end-to-end seizure detection framework that integrates an attention-guided lightweight neural network with an advanced metric learning strategy. Based on the baseline EEGNet architecture, the proposed framework incorporates an Efficient Channel Attention (ECA) module to enhance the extraction of discriminative features from multichannel EEG signals. Furthermore, to improve the separability between seizure and non-seizure interictal states, we introduce a triplet loss-based metric learning method using the Earth Mover's Distance. By employing Earth Mover's Distance as the distance metric in the feature space and introducing a triplet loss function to constrain the relative distance relationships between samples, the proposed method ensures more compact embeddings for intra-class samples and better separation between inter-class feature distributions, thereby effectively mitigating overfitting risks under limited data conditions. Experimental evaluations on the CHB-MIT dataset demonstrate the superior performance of the proposed method, achieving an average accuracy of 97.51 %, sensitivity of 95.56 %, and specificity of 97.93 %. These results indicate that the proposed framework provides a promising and computationally efficient solution for automatic seizure detection in practical EEG analysis.

Single-cell RNA sequencing (scRNA-seq) provides the transcriptome of a single cell, allowing researchers to study cellular phenomena at a higher resolution level. Nevertheless, noise generated by technical limitations and other results seriously interferes with the downstream analysis of sequencing data such as clustering. How to minimize the impact of noise on the accuracy of clustering methods has become a focus of current research. In this case, we propose a novel cell clustering algorithm called low-rank representation constrained clustering based on noise weight fusion (LRBNW). First, we mitigate the noise interference by introducing a noise weight matrix and assigning different weights to the noise through a reliability assessment strategy. By assigning larger weights to smaller reconstruction errors, we then highlight useful features with small errors, which clean features more representative in data analysis. Finally, we impose a k-block diagonal constraint on the affinity matrix through a block strategy, grouping related features into the same block, to eliminate redundancy among them and avoid over-reliance on related features. Extensive experiments demonstrate that LRBNW achieves higher accuracy results than existing state-of-the-art clustering methods on 10 real scRNA-seq datasets. In addition, downstream analysis experiments also indicated that LRBNW can identify biologically significant groups and reduce noise interference in scRNA-seq data. The result proves LRBNW is a powerful cell type identification tool, and has potential in predicting new cell types.

Spatial transcriptomics (ST) technologies offer an unprecedented opportunity to resolve complex tissue microenvironments. The accurate identification of spatial domains is still a pivotal and challenging task in spatial transcriptomics studies. Although numerous computational methods have been developed for spatial domain detection, prevailing methods struggle with multi-modal data fusion, noise robustness, and clustering stability. To address these limitations, we introduce DPST, an end-to-end deep learning model, which integrates gene expression, spatial coordinates, and histology images with an attention mechanism. DPST leverages the self-supervised bootstrap your own latent (BYOL) framework to extract robust feature embeddings from histology images without requiring negative samples. At its core, DPST employs a MASK-REMASK dual-view decoding strategy that simultaneously corrects for noise in masked data while recovering details from unmasked data. Furthermore, we use the breaking the reclustering barriers mechanism. This mechanism incorporates weight resets, reclustering, and momentum resets. It helps deep embedded clustering algorithms overcome performance bottlenecks. The experimental results show that DPST outperforms state-of-the-art methods consistently in several tasks, including spatial clustering and trajectory inference.

The rapid advancement of spatial multi-omics technology enables the simultaneous acquisition of diverse expression data from the same tissue or slice. Different omics offer unique and critical information about the biological system. However, most existing methods are unable to fully utilize this information for downstream tasks such as spatial domain identification. To integrate this information effectively for downstream analysis, we introduce a novel Spatial Multi-omics data integration method based on Information-Aware Multi-view Contrastive Learning (SM-IAMCL). It optimizes the spatial and feature neighborhood graphs for each omics by the specific graph learner and fused graph learner, and learns the fused graph of spatial and feature neighborhood graphs at the same time. Then, to make fused graph of each omics integrate both shared and unique information of spatial and feature neighborhood graphs, we incorporate graph-level contrastive learning between different views in each omics. Finally, the learned fused representation of each omics is then integrated via a weighted fusion strategy to generate an integrated low-dimensional latent representation of spatial multiomics. This integrated representation is used for a variety of downstream analysis tasks. The experimental results show that SM-IAMCL outperforms other seven existing methods in the downstream tasks such as spatial domain identification.

Seizures have a serious impact on the physical function and daily life of epileptic patients. The automated detection of seizures can assist clinicians in taking preventive measures for patients during the diagnosis process. The combination of deep learning (DL) model with convolutional neural network (CNN) and transformer network can effectively extract both local and global features, resulting in improved seizure detection performance. In this study, an enhanced transformer network named Inresformer is proposed for seizure detection, which is combined with Inception and Residual network extracting different scale features of electroencephalography (EEG) signals to enrich the feature representation. In addition, the improved transformer network replaces the existing Feedforward layers with two half-step Feedforward layers to enhance the nonlinear representation of the model. The proposed architecture utilizes discrete wavelet transform (DWT) to decompose the original EEG signals, and the three sub-bands are selected for signal reconstruction. Then, the Co-MixUp method is adopted to solve the problem of data imbalance, and the processed signals are sent to the Inresformer network for seizure information capture and recognition. Finally, discriminant fusion is performed on the results of three-scale EEG sub-signals to achieve final seizure recognition. The proposed network achieves the best accuracy of 100% on Bonn dataset and the average accuracy of 98.03%, sensitivity of 95.65%, and specificity of 98.57% on the long-term CHB-MIT dataset. Compared to the existing DL networks, the proposed method holds significant potential for clinical research and diagnosis applications with competitive performance.

The models used to predict epileptic seizures based on electroencephalogram (EEG) signals often encounter substantial challenges due to the requirement for large, labeled datasets and the inherent complexity of EEG data, which hinders their robustness and generalization capability. This study proposes CLResNet, a framework for predicting epileptic seizures, which combines contrastive self-supervised learning with a modified deep residual neural network to address the above challenges. In contrast to traditional models, CLResNet uses unlabeled EEG data for pre-training to extract robust feature representations. It is then fine-tuned on a smaller labeled dataset to significantly reduce its reliance on labeled data while improving its efficiency and predictive accuracy. The contrastive learning (CL) framework enhances the ability of the model to distinguish between preictal and interictal states, thus improving its robustness and generalizability. The architecture of CLResNet contains residual connections that enable it to learn deep features of the data and ensure an efficient gradient flow. The results of the evaluation of the model on the CHB-MIT dataset showed that it outperformed prevalent methods in the field, with an accuracy of 92.97%, sensitivity of 94.18%, and false-positive rate of 0.043/h. On the Siena dataset, the model also achieved competitive performance, with an accuracy of 92.79%, a sensitivity of 91.47%, and a false-positive rate of 0.041/h. These results confirm the effectiveness of CLResNet in addressing variations in EEG data, and show that contrastive self-supervised learning is a robust and accurate approach for predicting seizures.

Recent developments in spatial transcriptomics (ST) technologies have afforded us a profound understanding of gene expression patterns in the tissue microenvironment. Recently, several prominent spatial domain identification methods have been introduced to employ both spatial and expression information for precisely deciphering tissue structures. However, existing methods only focus on information from immediate neighbors, failing to capture the mixed relationships of neighbors at various scales and learn a general mixed feature from neighbors at different distances. To this end, we propose ST-HNHG, which fuses gene expression profiles, spatial information, and morphological images for deciphering spatial domains. Specifically, the high-order neighbor feature hybrid graph convolutional network (HNHGCN) is designed to capture feature representations between neighbors at different distances and learn their linear mixing. A data augmentation module is also proposed to enhance data diversity and model robustness. The attention mechanism is also introduced to integrate the embeddings learned from morphological and expression information, obtaining the latent representation for spatial domain identification. We test ST-HNHG on two ST datasets. The results indicate that ST-HNHG outperforms most existing methods, and considering the linear mixing between neighbors at various scales is beneficial for improving the accuracy of recognizing spatial domains.

Exploring new therapeutic applications for existing drugs can effectively reduce drug development costs. However, current drug-disease association (DDA) prediction methods often fail to effectively integrate multi-domain information. The lack of multi-domain information integration causes these methods to heavily rely on prior knowledge, thereby limiting their generalization ability. To address this issue, we developed a Multi-Domain Graph Collaborative Contrastive Learning (MNGCCL) model for DDA prediction. In the MNGCCL framework, a feature extraction module is designed to effectively extract both single-domain and multi-domain features. The single-domain and multi-domain feature extraction components in this module run in parallel, extracting key features of drugs and diseases from different latent spaces (e.g., homogeneous and heterogeneous networks). MNGCCL employs graph collaborative contrastive learning to integrate these features and enhances information interaction by designing new node scoring for negative sample sampling. This significantly enriches the semantic features of drugs and diseases. In DDA prediction, MNGCCL outperforms other state-of-the-art models across various datasets and partitioning methods. Notably, MNGCCL excels in drug repositioning for Parkinson’s disease and Alzheimer’s disease, as well as handling data sparsity. These findings highlight its tremendous potential for drug repositioning and DDA prediction, especially in the context of sparse omics data.

The advent and development of single-cell RNA sequencing (scRNA-seq) have provided new avenues for exploring cellular heterogeneity. Although many researchers have designed and developed efficient models to address cell heterogeneity and diversity by clustering cells into several groups, the performance of these methods may need improvement due to the characteristics of scRNA-seq data, such as high dimensionality, sparsity, and high dropout rates. In this paper, we propose a new method that couples low-rank representation (LRR) and concept factorization (CF) to learn a better clustering assignment matrix from both global and local perspectives, named SLRRGCF. Specifically, the LRR with similarity constraints based on tired random walk (TRW) can reduce the dimensionality of high-dimensional data while capturing more comprehensive global structure. At the same time, hypergraph regularization and CF are utilized to capture the local structure of the data further and directly obtain the clustering assignment matrix. We evaluated the performance of SLRRGCF on several real datasets, and comparisons with other competitive methods validated the effectiveness of our approach.

Recent advancements in spatially transcriptomics (ST) technologies have enabled the comprehensive measurement of gene expression profiles while preserving the spatial information of cells. Combining gene expression profiles and spatial information has been the most commonly used method to identify spatial functional domains and genes. However, most existing spatial domain decipherer methods are more focused on spatially neighboring structures and fail to take into account balancing the self-characteristics and the spatial structure dependency of spots. Therefore, we propose a novel model called SpaGCAC, which recognizes spatial domains with the help of an adaptive feature-spatial balanced graph convolutional network named AFSBGCN. The AFSBGCN can dynamically learn the relationship between spatial local topology structures and the self-characteristics of spots by adaptively increasing or declining the weight on the self-characteristics during message aggregation. Moreover, to better capture the local structures of spots, SpaGCAC exploits a local topology structure contrastive learning strategy. Meanwhile, SpaGCAC utilizes a probability distribution contrastive learning strategy to increase the similarity of probability distributions for points belonging to the same category. We validate the performance of SpaGCAC for spatial domain identification on four spatial transcriptomic datasets. In comparison with seven spatial domain recognition methods, SpaGCAC achieved the highest NMI median of 0.683 and the second highest ARI median of 0.559 on the multi-slice DLPFC dataset. SpaGCAC achieved the best results on all three other single-slice datasets. The above-mentioned results show that SpaGCAC outperforms most existing methods, providing enhanced insights into tissue heterogeneity.

The advent of single-cell RNA sequencing (scRNA-seq) technology offers the opportunity to conduct biological research at the cellular level. Single-cell type identification based on unsupervised clustering is one of the fundamental tasks of scRNA-seq data analysis. Although many single-cell clustering methods have been developed recently, few can fully exploit the deep potential relationships between cells, resulting in suboptimal clustering. In this paper, we propose scGAMF, a graph autoencoder-based multi-level kernel subspace fusion framework for scRNA-seq data analysis. Based on multiple top feature sets, scGAMF unifies deep feature embedding and kernel space analysis into a single framework to learn an accurate clustering affinity matrix. First, we construct multiple top feature sets to avoid the high variability caused by single feature set learning. Second, scGAMF uses a graph autoencoder (GAEs) to extract deep information embedded in the data, and learn embeddings including gene expression patterns and cell-cell relationships. Third, to fully explore the deep potential relationships between cells, we design a multi-level kernel space fusion strategy. This strategy uses a kernel expression model with adaptive similarity preservation to learn a self-expression matrix shared by all embedding spaces of a given feature set, and a consensus affinity matrix across multiple top feature sets. Finally, the consensus affinity matrix is used for spectral clustering, visualization, and identification of gene markers. Extensive validation on real datasets shows that scGAMF achieves higher clustering accuracy than many popular single-cell analysis methods.

Advances in high-throughput single-cell RNA sequencing (scRNA-seq) technology have provided more comprehensive biological information on cell expression. Clustering analysis is a critical step in scRNA-seq research and provides clear knowledge of the cell identity. Unfortunately, the characteristics of scRNA-seq data and the limitations of existing technologies make clustering encounter a considerable challenge. Meanwhile, some existing methods treat different features equally and ignore differences in feature contributions, which leads to a loss of information. To overcome limitations, we introduce a weighted distance constraint into the construction of the similarity graph and combine the similarity constraint. We propose the Joint Automatic Weighting Similarity Graph and Low-rank Representation (JAGLRR) clustering method. Evaluating the contributions of each feature and assigning various weight values can increase the significance of valuable features while decreasing the interference of redundant features. The similarity constraint allows the model to generate a more symmetric affinity matrix. Benefitting from that affinity matrix, JAGLRR recovers the original linear relationship of the data more accurately and obtains more discriminative information. The results on simulated datasets and 8 real datasets show that JAGLRR outperforms 11 existing comparison methods in clustering experiments, with higher clustering accuracy and stability.

Numerous scientific studies have found a link between diverse microorganisms in the human body and complex human diseases. Because traditional experimental approaches are time-consuming and expensive, using computational methods to identify microbes correlated with diseases is critical. In this paper, a new microbe-disease association prediction model is proposed that combines a multi-view multi-modal network and a multi-scale feature fusion mechanism, called M3HOGAT. Firstly, a microbe-disease association network and multiple similarity views are constructed based on multi-source information. Then, consider that neighbor information from disparate orders might be more adept at learning node representations. Consequently, the higher-order graph attention network (HOGAT) is devised to aggregate neighbor information from disparate orders to extract microbe and disease features from different networks and views. Given that the embedding features of microbe and disease from different views possess varying importance, a multi-scale feature fusion mechanism is employed to learn their interaction information, thereby generating the final feature of microbes and diseases. Finally, an inner product decoder is used to reconstruct the microbe-disease association matrix. Compared with five state-of-the-art methods on the HMDAD and Disbiome datasets, the results of 5-fold cross-validations show that M3HOGAT achieves the best performance. Furthermore, case studies on asthma and obesity confirm the effectiveness of M3HOGAT in identifying potential disease-related microbes.

As an important tool for detecting and diagnosing epilepsy, multi-channel EEG records the neuronal activities of different brain regions. Visual identification of abnormal EEG signals poses challenges, making the use of artificial intelligence techniques for automated seizure detection an inevitable trend. However, existing seizure detection methods often overlook the spatial relationship between EEG channels, which can't take full advantage of brain network structure. In this paper, we design an end-to-end spatiotemporal architecture for seizure detection based on Graph Convolutional Networks (GCN) and Bidirectional Gated Recurrent Units (BiGRU) to efficiently model the spatial dependence and temporal dynamics of EEG. Firstly, the original EEG signals are preprocessed by applying wavelet transform for temporal-frequency analysis. The Pearson correlation matrix is computed for specific frequency bands and GCN is utilized to extract spatial features between EEG channels. Then, these features are sent into the BiGRU network to capture temporal relationships. Finally, the detection decisions are achieved using fully connected layers and the multi-level decision rules are implemented to provide the final results. The proposed method is validated on CHB-MIT EEG dataset, achieving 98.85% sensitivity, 95.83% specificity, 97.35% accuracy, 97.4% F1-score, and 97.33% AUC. This network fusions multiple EEG characteristics in the spatial-temporal-frequency domains to improve the detection performance and the promising result demonstrates that the performance of this model is superior to or on par with existing methods.

CircRNA as a biomarker has been shown to have an essential effect on the occurrence and prognosis of a wide range of human diseases. Because of the high cost of wet experiments, computational methods are widely used to explore circRNA. However, the performance and robustness of the computational models still need to be further improved. To solve these problems, this paper proposes a novel method based on graph random propagation network and multi-head dynamic graph attention network (GRPGAT) to predict the potential associations between circRNAs and diseases. Firstly, GRPGAT uses centered kernel alignment method to fuse the circRNA similarity kernels and disease similarity kernels. Then the integrated vectors build a heterogeneous graph and are sent to a graph random propagation network. The remaining nodes are fed into a multi-head dynamic attention network for feature extraction. Finally, a four-layer Multilayer Perceptron is used to learn features and gain the prediction scores. Experiments are supported by cirR2Disease, and achieve Area Under Curve (AUC) scores of 0.9636 in 5-fold cross validation. In comparison with the state-of-the-art models, GRPGAT also shows superior performance.

Single-cell RNA sequencing (scRNA-seq) data are collected at an unheard-of rate thanks to the advancement of high-throughput sequencing technologies. However, due to the limitations of current technology, scRNA-seq is sometimes unable to capture the expressed genes, resulting in a large number of zero counts (also known as dropout events) in the data. These dropout events can cause data loss in the gene expression matrix and severely hampers the accuracy of downstream analysis. To address this problem, in this paper, we propose a new imputation method called scNMF-impute. The scNMF-impute method imputes the dropout events and performs dimensionality reduction under the framework of nonnegative matrix factorization (NMF). To effectively identify the location of the dropout and recover the value of the dropout, we explicitly model the dropout events as a matrix. Therefore, the gene expression matrix without dropout is represented as the sum of the original data matrix and the dropout matrix. In addition, to reduce the influence of dropout on factorization, we introduce the similarity information between genes into the NMF model. The introduction of gene similarity information can ensure the accurate recovery of data structures obscured by dropout events in the gene expression matrix. We conducted extensive experiments on simulated datasets and real scRNA-seq datasets to verify the effectiveness of scNMF-impute and other state-of-the-art methods. The results show that scNMF-impute can accurately calculate missing data and restore true gene expression, thus improving the accuracy of existing clustering methods and obtaining more accurate cell clustering results.

Advances in omics technology have enriched the understanding of the biological mechanisms of diseases, which has provided a new approach for cancer research. Multi-omics data contain different levels of cancer information, and comprehensive analysis of them has attracted wide attention. However, limited by the dimensionality of matrix models, traditional methods cannot fully use the key high-dimensional global structure of multi-omics data. Moreover, besides global information, local features within each omics are also critical. It is necessary to consider the potential local information together with the high-dimensional global information, ensuring that the shared and complementary features of the omics data are comprehensively observed. In view of the above, this article proposes a new tensor integrative framework called the strong complementarity tensor decomposition model (BioSTD) for cancer multi-omics data. It is used to identify cancer subtype specific genes and cluster subtype samples. Different from the matrix framework, BioSTD utilizes multi-view tensors to coordinate each omics to maximize high-dimensional spatial relationships, which jointly considers the different characteristics of different omics data. Meanwhile, we propose the concept of strong complementarity constraint applicable to omics data and introduce it into BioSTD. Strong complementarity is used to explore the potential local information, which can enhance the separability of different subtypes, allowing consistency and complementarity in the omics data to be fully represented. Experimental results on real cancer datasets show that our model outperforms other advanced models, which confirms its validity.

Single-cell RNA sequencing (scRNA-seq) technology can provide expression profile of single cells, which propels biological research into a new chapter. Clustering individual cells based on their transcriptome is a critical objective of scRNA-seq data analysis. However, the high-dimensional, sparse and noisy nature of scRNA-seq data pose a challenge to single-cell clustering. Therefore, it is urgent to develop a clustering method targeting scRNA-seq data characteristics. Due to its powerful subspace learning capability and robustness to noise, the subspace segmentation method based on low-rank representation (LRR) is broadly used in clustering researches and achieves satisfactory results. In view of this, we propose a personalized low-rank subspace clustering method, namely PLRLS, to learn more accurate subspace structures from both global and local perspectives. Specifically, we first introduce the local structure constraint to capture the local structure information of the data, while helping our method to obtain better inter-cluster separability and intra-cluster compactness. Then, in order to retain the important similarity information that is ignored by the LRR model, we utilize the fractional function to extract similarity information between cells, and introduce this information as the similarity constraint into the LRR framework. The fractional function is an efficient similarity measure designed for scRNA-seq data, which has theoretical and practical implications. In the end, based on the LRR matrix learned from PLRLS, we perform downstream analyses on real scRNA-seq datasets, including spectral clustering, visualization and marker gene identification. Comparative experiments show that the proposed method achieves superior clustering accuracy and robustness.

Identifying drug-disease associations (DDAs) is critical to the development of drugs. Traditional methods to determine DDAs are expensive and inefficient. Therefore, it is imperative to develop more accurate and effective methods for DDAs prediction. Most current DDAs prediction methods utilize original DDAs matrix directly. However, the original DDAs matrix is sparse, which greatly affects the prediction consequences. Hence, a prediction method based on multi-similarities graph convolutional autoencoder (MSGCA) is proposed for DDAs prediction. First, MSGCA integrates multiple drug similarities and disease similarities using centered kernel alignment-based multiple kernel learning (CKA-MKL) algorithm to form new drug similarity and disease similarity, respectively. Second, the new drug and disease similarities are improved by linear neighborhood, and the DDAs matrix is reconstructed by weighted K nearest neighbor profiles. Next, the reconstructed DDAs and the improved drug and disease similarities are integrated into a heterogeneous network. Finally, the graph convolutional autoencoder with attention mechanism is utilized to predict DDAs. Compared with extant methods, MSGCA shows superior results on three datasets. Furthermore, case studies further demonstrate the reliability of MSGCA.

The development of single-cell RNA sequencing (scRNA-seq) technology has opened up a new perspective for us to study disease mechanisms at the single cell level. Cell clustering reveals the natural grouping of cells, which is a vital step in scRNA-seq data analysis. However, the high noise and dropout of single-cell data pose numerous challenges to cell clustering. In this study, we propose a novel matrix factorization method named NLRRC for single-cell type identification. NLRRC joins non-negative low-rank representation (LRR) and random walk graph regularized NMF (RWNMFC) to accurately reveal the natural grouping of cells. Specifically, we find the lowest rank representation of single-cell samples by non-negative LRR to reduce the difficulty of analyzing high-dimensional samples and capture the global information of the samples. Meanwhile, by using random walk graph regularization (RWGR) and NMF, RWNMFC captures manifold structure and cluster information before generating a cluster allocation matrix. The cluster assignment matrix contains cluster labels, which can be used directly to get the clustering results. The performance of NLRRC is validated on simulated and real single-cell datasets. The results of the experiments illustrate that NLRRC has a significant advantage in single-cell type identification.

Automatic seizure detection could facilitate early detection, improve treatment planning, and reduce medical workload. This study describes a novel Logarithmic Euclidean-Gaussian Mixture Models (LE-GMMs) and an improved Deep Forest learning algorithm for epileptic seizure detection. The LE-GMMs could map the Riemannian manifold structure of Gaussian models to linear Euclidean space, which fully exploits the ability of GMMs to distinguish non-seizure and seizure EEG signals. The Multi-Pooling and error Screening Forest (MPSForest) learning method based on Deep Forest uses multi-pooling and out-of-bagging (OOB) error screening to reduce memory load and random tree construction. Firstly, variational modal decomposition (VMD) is applied to decompose electroencephalogram (EEG) signals into five layers, and the first three layers are chosen to construct EEG time-frequency distribution. Then Gaussian Mixture Models are estimated, and the LE-GMMs are constructed to extract valid EEG features. These features are input into the MPSForest model to classify seizure and non-seizure samples. After that, the outputs are subjected to post-processing to get the final seizure detection results, including moving average filtering and the adaptive collar technique. The proposed method achieves average sensitivity of 98.22% and specificity of 98.99% on the UPenn and Mayo Clinic dataset, and for the long-term Freiburg EEG dataset with 21 patients, the sensitivity of 98.47% and specificity of 98.57% are yielded respectively with the false detection rate of 0.24/h. The experimental results show that this proposed method has excellent accuracy in distinguishing non-seizure and seizure EEG signals and holds great potential for clinical research and diagnostics.

Recently, cancer sample clustering research based on gene expression data has been completely developed. Moreover, studies discover that other genomic data in TCGA besides gene expression data also contain features that can be utilized to cluster. Thus, by integrating these genomic data, new cancer clustering feature source can be formed. As a powerful subspace clustering method, Low-Rank Representation (LRR) has delivered an important breakthrough in clustering cancer samples. However, most methods based on LRR are only employed to analyze gene expression data, and cannot make full use of the characteristic information of other genomic data. Based on the LRR method, this paper proposes a novel Multi-Graph Laplacian regularized Low-Rank Representation (MGLLRR) method for cancer sample clustering using multi-omics datasets. To preserve the local geometry in genomic data, multi-graph regularization is led into MGLLRR method. The multi-graph Laplacian can fully preserve the hidden non-linear manifold structure in the data to make sure the smoothness of the integrated data along the estimated manifold. Considering the noise effect of different genomic data, we also introduce the idea of block constraint. We set each genome data as a data block and impose different constraint on it. Therefore, it can avoid the influence of different noise in multiple genomic data and improve the reliability of tumor clustering. The clustering experimental results indicate the effectiveness of MGLLRR on cancer sample clustering. And MGLLRR is a practical and effective analysis method of multiple genomic data.

Accurate identification of cancer driver modules or pathways is important for controlling disease progression and timely treatment. In recent years, most approaches have been based on mutation data combined with gene interaction networks to identify cancer driver modules, but cancer-related genes tend to interact with each other, and the mutations they experience disruption their neighbors. Therefore, we propose a framework that combines network function and topological information to quantify the extent to which mutated genes disrupt their neighbors. Firstly, similarity in protein-protein interaction networks binds to high coverage and high mutual exclusivity of mutant genes, which are used to obtain the impact of the interaction between two mutant genes on biological function. Secondly, we quantified the degree of gene disruption by mutant genes in their neighborhood using an adaptive spread strength measure to obtain the gene spread strength network (GSSN). Finally, the module is extended using CFinder strategy to obtain the optimal driving module. We apply our method to 12 cancer datasets, and the experimental results show that our method outperforms the other three methods on most datasets. At the same time, we also analyze common and low-frequency driver modules in cancer.

The mining and analysis of genomics data provides a new idea for exploring the pathogenesis of human disease. Since these data often have the features of small samples, high-dimensional, and high redundancy, the traditional matrix decomposition method cannot fully mine the spatial structure and multiple perspective information of cancer genomics data. Inspired by the recently proposed robust tensor completion method, a tensor robust PCA method (TTTD) was proposed based on U-product and transformed tensor singular value decomposition (t-SVD) to explore the integrated cancer genomics data in this paper. Specifically, the unitary transform matrix is employed to replace the discrete Fourier transform matrix in t-SVD, which contributes to recover a lower tubal rank tensor to a certain extent. Meanwhile, the $\mathrm{L}_{2,1}-$norm is employed to learn the sparse term, and the row sparse constraint generated by it can better detect the abnormal value of the real tensor. In addition, the alternating direction method of the multiplier algorithm is used to optimize the TTTD method. Experimental results on the three integrated cancer multi-omics datasets show that the TTTD method achieves the better performance.

With the development of research on the complex aetiology of many diseases, computational drug repositioning methodology has proven to be a shortcut to costly and inefficient traditional methods. Therefore, developing more promising computational methods is indispensable for finding new candidate diseases to treat with existing drugs. In this paper, a model integrating a new variant of message passing neural network and a novel-gated fusion mechanism called GLGMPNN is proposed for drug-disease association prediction. First, a light-gated message passing neural network (LGMPNN), including message passing, aggregation and updating, is proposed to separately extract multiple pieces of information from the similarity networks and the association network. Then, a gated fusion mechanism consisting of a forget gate and an output gate is applied to integrate the multiple pieces of information to extent. The forget gate calculated by the multiple embeddings is built to integrate the association information into the similarity information. Furthermore, the final node representations are controlled by the output gate, which fuses the topology information of the networks and the initial similarity information. Finally, a bilinear decoder is adopted to reconstruct an adjacency matrix for drug-disease associations. Evaluated by 10-fold cross-validations, GLGMPNN achieves excellent performance compared with the current models. The following studies show that our model can effectively discover novel drug-disease associations.

Biclustering algorithm is an effective tool for processing gene expression datasets. There are two kinds of data matrices, binary data and non-binary data, which are processed by biclustering method. A binary matrix is usually converted from pre-processed gene expression data, which can effectively reduce the interference from noise and abnormal data, and is then processed using a biclustering algorithm. However, biclustering algorithms of dealing with binary data have a poor balance between running time and performance. In this paper, we propose a new biclustering algorithm called the Adjacency Difference Matrix Binary Biclustering algorithm (AMBB) for dealing with binary data to address the drawback. The AMBB algorithm constructs the adjacency matrix based on the adjacency difference values, and the submatrix obtained by continuously updating the adjacency difference matrix is called a bicluster. The adjacency matrix allows for clustering of gene that undergo similar reactions under different conditions into clusters, which is important for subsequent genes analysis. Meanwhile, experiments on synthetic and real datasets visually demonstrate that the AMBB algorithm has high practicability.

BACKGROUND: The identification of cancer types is of great significance for early diagnosis and clinical treatment of cancer. Clustering cancer samples is an important means to identify cancer types, which has been paid much attention in the field of bioinformatics. The purpose of cancer clustering is to find expression patterns of different cancer types, so that the samples with similar expression patterns can be gathered into the same type. In order to improve the accuracy and reliability of cancer clustering, many clustering methods begin to focus on the integration analysis of cancer multi-omics data. Obviously, the methods based on multi-omics data have more advantages than those using single omics data. However, the high heterogeneity and noise of cancer multi-omics data pose a great challenge to the multi-omics analysis method. RESULTS: In this study, in order to extract more complementary information from cancer multi-omics data for cancer clustering, we propose a low-rank subspace clustering method called multi-view manifold regularized compact low-rank representation (MmCLRR). In MmCLRR, each omics data are regarded as a view, and it learns a consistent subspace representation by imposing a consistence constraint on the low-rank affinity matrix of each view to balance the agreement between different views. Moreover, the manifold regularization and concept factorization are introduced into our method. Relying on the concept factorization, the dictionary can be updated in the learning, which greatly improves the subspace learning ability of low-rank representation. We adopt linearized alternating direction method with adaptive penalty to solve the optimization problem of MmCLRR method. CONCLUSIONS: Finally, we apply MmCLRR into the clustering of cancer samples based on multi-omics data, and the clustering results show that our method outperforms the existing multi-view methods.

Extracting genes involved in cancer lesions from gene expression data is critical for cancer research and drug development. The method of feature selection has attracted much attention in the field of bioinformatics. Principal Component Analysis (PCA) is a widely used method for learning low-dimensional representation. Some variants of PCA have been proposed to improve the robustness and sparsity of the algorithm. However, the existing methods ignore the high-order relationships between data. In this paper, a new model named Robust Principal Component Analysis via Hypergraph Regularization (HRPCA) is proposed. In detail, HRPCA utilizes L2,1-norm to reduce the effect of outliers and make data sufficiently row-sparse. And the hypergraph regularization is introduced to consider the complex relationship among data. Important information hidden in the data are mined, and this method ensures the accuracy of the resulting data relationship information. Extensive experiments on multi-view biological data demonstrate that the feasible and effective of the proposed approach.

Cancer genome data generally consists of multiple views from different sources. These views provide different levels of information about gene activity, as well as more comprehensive cancer information. The low-rank representation (LRR) method, as a powerful subspace clustering method, has been extended and applied in cancer data research. Although the multi-view learning methods based on low rank representation have achieved good results in cancer multi-omics analysis because they fully consider the consistency and complementarity between views, these methods have some shortcomings in mining the potential local geometry of data. In view of this, this paper proposes a new method named Multi-view Random-walk Graph regularization Low-Rank Representation (MRGLRR) to comprehensively analyze multi-view genomics data. This method uses multi-view model to find the common centroid of view. By constructing a joint affinity matrix to learn the low-rank subspace representation of multiple sets of data, the hidden information of each view is fully obtained. In addition, this method introduces random walk graph regularization constraint to obtain more accurate similarity between samples. Different from the traditional graph regularization constraint, after constructing the KNN graph, we use the random walk algorithm to obtain the weight matrix. The random walk algorithm can retain more local geometric information and better learn the topological structure of the data. What's more, a feature gene selection strategy suitable for multi-view model is proposed to find more differentially expressed genes with research value. Experimental results show that our method is better than other representative methods in terms of clustering and feature gene selection for cancer multi-omics data.

The exploration of single cell RNA-sequencing (scRNA-seq) technology generates a new perspective to analyze biological problems. One of the major applications of scRNA-seq data is to discover subtypes of cells by cell clustering. Nevertheless, it is challengeable for traditional methods to handle scRNA-seq data with high level of technical noise and notorious dropouts. To better analyze single cell data, a novel scRNA-seq data analysis model called Maximum correntropy criterion based Non-negative and Low Rank Representation (MccNLRR) is introduced. Specifically, the maximum correntropy criterion, as an effective loss function, is more robust to the high noise and large outliers existed in the data. Moreover, the low rank representation is proven to be a powerful tool for capturing the global and local structures of data. Therefore, some important information, such as the similarity of cells in the subspace, is also extracted by it. Then, an iterative algorithm on the basis of the half-quadratic optimization and alternating direction method is developed to settle the complex optimization problem. Before the experiment, we also analyze the convergence and robustness of MccNLRR. At last, the results of cell clustering, visualization analysis, and gene markers selection on scRNA-seq data reveal that MccNLRR method can distinguish cell subtypes accurately and robustly.

Single-cell clustering is a crucial task of scRNA-seq analysis, which reveals the natural grouping of cells. However, due to the high noise and high dimension in scRNA-seq data, how to effectively and accurately identify cell types from a great quantity of cell mixtures is still a challenge. Considering this, in this paper, we propose a novel subspace clustering algorithm termed SLRRSC. This method is developed based on the low-rank representation model, and it aims to capture the global and local properties inherent in data. In order to make the LRR matrix describe the spatial relationship of samples more accurately, we introduce the manifold-based graph regularization and similarity constraint into the LRR-based method SLRRSC. The graph regularization can preserve the local geometric structure of the data in low-rank decomposition, so that the low-rank representation matrix contains more local structure information. By imposing similarity constraint on the low-rank matrix, the similarity information between sample pairs is further introduced into the SLRRSC model to improve the learning ability of low-rank method for global structure. At the same time, the similarity constraint makes the low-rank representation matrix symmetric, which makes it better interpretable in clustering application. We compare the effectiveness of the SLRRSC algorithm with other single-cell clustering methods on simulated data and real single-cell datasets. The results show that this method can obtain more accurate sample similarity matrix and effectively solve the problem of cell type recognition.

Non-negative matrix factorization (NMF) is a dimensionality reduction technique based on high-dimensional mapping. It can learn part-based representations effectively. In this paper, we propose a method called Dual Hyper-graph Regularized Supervised Non-negative Matrix Factorization (HSNMF). To encode the geometric information of the data, the hyper-graph is introduced into the model as a regularization term. The advantage of hyper-graph learning is to find higher order data relationship to enhance data relevance. This method constructs the data hyper-graph and the feature hyper-graph to find the data manifold and the feature manifold simultaneously. The application of hyper-graph theory in cancer datasets can effectively find pathogenic genes. The discrimination information is further introduced into the objective function to obtain more information about the data. Supervised learning with label information greatly improves the classification effect. Furthermore, the real datasets of cancer usually contain sparse noise, so the$L_{2,1}$-norm is applied to enhance the robustness of HSNMF algorithm. Experiments under The Cancer Genome Atlas (TCGA) datasets verify the feasibility of the HSNMF method.

As we all know, science and technology are developing faster and faster. Many experts and scholars have demonstrated that human diseases are related to lncRNA, but only a few associations have been confirmed, and many unknown associations need to be found. In the process of finding associations, it takes a lot of time, so finding an efficient way to predict the associations between lncRNAs and diseases is particularly important. In this paper, we propose a multi-label fusion collaborative matrix factorization (MLFCMF) approach for predicting lncRNA-disease associations (LDAs). Firstly, the lncRNA space and disease space are optimized by multi-label to enhance the intrinsic link between lncRNA and disease and to tap potential information. Multi-label learning can encode a variety of data information from the sample space. Secondly, to learn multi-label information in the data space, the fusion method is used to handle the relationship between multiple labels. More comprehensive information will be obtained by weighing the effects of different labels. The addition of Gaussian interaction profile (GIP) kernel can increase the network similarity. Finally, the lncRNA-disease associations are predicted by the method of collaborative matrix factorization. The ten-fold cross-validation method is used to evaluate the MLFCMF method, and our method finally obtains an AUC value of 0.8612. Detailed analysis of ovarian cancer, colorectal cancer, and lung cancer in the simulation experiment results. So it can be seen that our method MLFCMF is an effective model for predicting lncRNA-disease associations.

In recent years, single-cell RNA sequencing (scRNA-seq) technology has made significant progress in many fields and become an important means to study cell dynamics. How to effectively mine valuable biological information from these sequencing data is a topic worthy of researching. In this paper, two new methods based on traditional principal component analysis (PCA) are proposed and used to scRNA-seq data. The first method named dual graph regularized PCA (DGPPCA) is based on Frobenius-norm and L2,p-norm constraints, and the method named the dual graph-regularization PCA (DG2PPCA) is based on the nonconvex proximal Lp-norm ( 02,p-norm constraints. We apply these two new methods to five scRNA-seq datasets, and perform bi-clustering on genes and samples at the same time. Extensive experiments are conducted to explore the influence of the combination of different norm constraints in the two optimization models.

With the rapid development of the next-generation sequencing technology, a large amount of genomics information has been obtained. The scale of biological sequencing data is particularly large and complex. The tensor robust principal component analysis (TRPCA) method can effectively preserve the spatial structure of tensor data, so it has received extensive attention. However, the low-rank tensor obtained by TRPCA may be damaged to a certain extent. To solve this problem, this paper proposes a model for weighting low-rank data based on the method of TRPCA. This model has an additional constraint penalty term that can repair corrupted low-rank data and the effective information in it can be fully utilized. In addition, the norm is used to constrain the sparse tensor to make the sparse effect better. In the experimental part, TRPCA model clusters samples by low-rank tensor. The experimental results on cancer omics data show that our method is superior to other methods.

In recent years, with the diversity and variability of cancer information, the multi-omics data have been applied in various fields. Many existing models of principal component analysis can only process single data, which makes limitations on cancer research. Therefore, in this paper, a new model called integrative principal component analysis (IPCA) is proposed to achieve the unification of multi-omics data. In addition, in order to preserve the high-order manifold structure between the data, an integrative hypergraph regularization principal component analysis (IHPCA) is further proposed by applying the hypergraph regularization constraint. The effectiveness of IHPCA method is tested on four multi-omics datasets. Experimental results show that the proposed method has better performance than other representative methods on sample clustering and common expression genes (co-expression genes) network analysis.

BACKGROUND: Predicting drug-disease interactions (DDIs) is time-consuming and expensive. Improving the accuracy of prediction results is necessary, and it is crucial to develop a novel computing technology to predict new DDIs. The existing methods mostly use the construction of heterogeneous networks to predict new DDIs. However, the number of known interacting drug-disease pairs is small, so there will be many errors in this heterogeneous network that will interfere with the final results. RESULTS: -norm are introduced in our method to achieve better results than other advanced methods. The network similarities of drugs and diseases with their chemical and semantic similarities are combined in this method. CONCLUSIONS: Cross validation is used to evaluate our method, and simulation experiments are used to predict new interactions using two different datasets. Finally, our prediction accuracy is better than other existing methods. This proves that our method is feasible and effective.

BACKGROUND: Predicting miRNA-disease associations (MDAs) is time-consuming and expensive. It is imminent to improve the accuracy of prediction results. So it is crucial to develop a novel computing technology to predict new MDAs. Although some existing methods can effectively predict novel MDAs, there are still some shortcomings. Especially when the disease matrix is processed, its sparsity is an important factor affecting the final results. RESULTS: -norm are introduced to our method to achieve the highest AUC value than other advanced methods. CONCLUSIONS: 5-fold cross validation is used to evaluate our method, and simulation experiments are used to predict novel associations on Gold Standard Dataset. Finally, our prediction accuracy is better than other existing advanced methods. Therefore, our approach is effective and feasible in predicting novel MDAs.

BACKGROUND: Predicting meaningful miRNA-disease associations (MDAs) is costly. Therefore, an increasing number of researchers are beginning to focus on methods to predict potential MDAs. Thus, prediction methods with improved accuracy are under development. An efficient computational method is proposed to be crucial for predicting novel MDAs. For improved experimental productivity, large biological datasets are used by researchers. Although there are many effective and feasible methods to predict potential MDAs, the possibility remains that these methods are flawed. RESULTS: A simple and effective method, known as Nearest Profile-based Collaborative Matrix Factorization (NPCMF), is proposed to identify novel MDAs. The nearest profile is introduced to our method to achieve the highest AUC value compared with other advanced methods. For some miRNAs and diseases without any association, we use the nearest neighbour information to complete the prediction. CONCLUSIONS: To evaluate the performance of our method, five-fold cross-validation is used to calculate the AUC value. At the same time, three disease cases, gastric neoplasms, rectal neoplasms and colonic neoplasms, are used to predict novel MDAs on a gold-standard dataset. We predict the vast majority of known MDAs and some novel MDAs. Finally, the prediction accuracy of our method is determined to be better than that of other existing methods. Thus, the proposed prediction model can obtain reliable experimental results.

BACKGROUND: Identifying different types of cancer based on gene expression data has become hotspot in bioinformatics research. Clustering cancer gene expression data from multiple cancers to their own class is a significance solution. However, the characteristics of high-dimensional and small samples of gene expression data and the noise of the data make data mining and research difficult. Although there are many effective and feasible methods to deal with this problem, the possibility remains that these methods are flawed. RESULTS: In this paper, we propose the graph regularized low-rank representation under symmetric and sparse constraints (sgLRR) method in which we introduce graph regularization based on manifold learning and symmetric sparse constraints into the traditional low-rank representation (LRR). For the sgLRR method, by means of symmetric constraint and sparse constraint, the effect of raw data noise on low-rank representation is alleviated. Further, sgLRR method preserves the important intrinsic local geometrical structures of the raw data by introducing graph regularization. We apply this method to cluster multi-cancer samples based on gene expression data, which improves the clustering quality. First, the gene expression data are decomposed by sgLRR method. And, a lowest rank representation matrix is obtained, which is symmetric and sparse. Then, an affinity matrix is constructed to perform the multi-cancer sample clustering by using a spectral clustering algorithm, i.e., normalized cuts (Ncuts). Finally, the multi-cancer samples clustering is completed. CONCLUSIONS: A series of comparative experiments demonstrate that the sgLRR method based on low rank representation has a great advantage and remarkable performance in the clustering of multi-cancer samples.

Tumor samples clustering based on biomolecular data is a hot issue of cancer classifications discovery. How to extract the valuable information from high dimensional genomic data is becoming an urgent problem in tumor samples clustering. In this paper, we introduce manifold regularization into low-rank representation model and present a novel method named Mixed-norm Laplacian regularized Low-Rank Representation (MLLRR) to identify the differentially expressed genes for tumor clustering based on gene expression data. Then, in order to advance the accuracy and stability of tumor clustering, we establish the clustering model based on Penalized Matrix Decomposition (PMD) and propose a novel cluster method named MLLRR-PMD. In this method, the cancer clustering research includes three steps. First, the matrix of gene expression data is decomposed into a low rank representation matrix and a sparse matrix by MLLRR. Second, the differentially expressed genes are identified based on the sparse matrix. Finally, the PMD is applied to cluster the samples based on the differentially expressed genes. The experiment results on simulation data and real genomic data illustrate that MLLRR method enhances the robustness to outliers and achieves remarkable performance in the extraction of differentially expressed genes.

Non-negative Matrix Factorization (NMF) is widely used as a data dimensionality reduction tool. However, the assumption of most conventional NMF-based methods is that the gene expression data are only destroyed by Gaussian noise. In practice, the gene expression data are unavoidably destroyed by sparse noise. Although Sparsity-Regularized Robust NMF by using L1/2constraint (L1/2-RNMF) can achieve satisfactory results when the sparse noise exists, it does not consider the intrinsic geometric structure in data. Hence, we introduce graph regularization into L1/2-RNMF. In this paper, we developed a novel NMF method named Graph regularized Robust Nonnegative Matrix Factorization (GrRNMF), which mainly consists of two aspects: Firstly, the Gaussian noise and sparse noise are modeled, respectively. Secondly, it can reveal the geometric information in data by adding graph regularization term. Extensive experimental results on The Cancer Genome Atlas (TCGA) data indicate that the GrRNMF method has higher accuracy than other state-of-the-art methods in samples clustering and the selection of differentially expressed genes.

Principal Component Analysis (PCA) as a tool for dimensionality reduction is widely used in many areas. In the area of bioinformatics, the first principal component of PCA is used to select characteristic genes. In order to improve the robustness of PCA-based method, this paper proposes a novel graph-Laplacian PCA algorithm by adopting L1/2constraint on error function (L1/2gLPCA) for characteristic gene selection. Augmented Lagrange Multipliers (ALM) method is applied to solve the sub-problem. This method gets better results in characteristic gene selection than traditional PCA approach. Meanwhile, the error function based on the L1/2norm helps to reduce the influence of outliers and noise. Extensive experimental results on gene expression data sets demonstrate that our method can get higher identification accuracies than others.