Current diffusion model based image denoising methods suffer from semantic inconsistency and distortion due to their inability to maintain structural integrity, while diffusion models face two inherent limitations: (1) mandatory sampling initiation from pure Gaussian noise that mismatches denoising scenarios, and (2) uncontrollable uncertainty during stochastic sampling processes. Our work is motivated by the potential to harness precise edge information as conditional guidance to recalibrate diffusion sampling trajectories, thereby aligning the generative process with denoising objectives while preserving critical image structures. We propose a new image denoising framework, the EGDCF: Edge-Guided Diffusion networks with Coarse-to-Fine learning for image denoising, that synergizes edge-aware conditional guidance with a coarse-to-fine refinement mechanism through three key components: edge extractor, conditional diffusion model, and iterative denoising scheduler. EGDCF first uses a trainable Canny operator to extract multi-scale edge maps from noisy inputs, while calculating the number of denoising steps in the diffusion model’s reverse process based on the noise level of the input, thereby aligning the denoising trajectory with the actual noise distribution. Then, these structural priors are injected into the modified U-Net backbone network through attention based feature fusion, thereby guiding the sampling trajectory of the diffusion model’s reverse process. Finally, by fusing the noise input with the denoising results as the input for a new iteration, a clean denoised image can be obtained after multiple iterations. Quantitative evaluations on Gaussian and real-world noise datasets show effectiveness of our proposed method compared to state-of-the-art methods, particularly effective in high-noise regimes where conventional approaches fail.

Recently, Graph neural networks(GNNs) has achieved tremendous success in a variety of fields. Many approaches have been proposed to address data with graph structure. However, many of these are deterministic methods, therefore, they are unable to capture the uncertainty, which is inherent in the nature of graph data. Various VAE(Variational auto-encoder)-based approaches have been proposed to tackle such problems. Unfortunately, due to the simple a posterior and a prior assumption problems of such methods, they are not well suited to handle uncertainty in graph data. For example, VGAE(Variational graph auto-encoder) assumes that the posterior and prior distributions are simple Gaussian distributions, which can lead to overfitting problems when incompatible with the true distributions. Many methods propose to solve the posterior distribution problem, but most ignore the effect of the prior distribution. Therefore, in this paper, we proposed a novel method to solve the Gaussian prior problem. Specifically, in order to enhance the representation power of the prior distribution, we use the diffusion model to model the prior distribution. We incorporate the diffusion model into VGAE. In the forward diffusion process, noise is gradually added to the latent variables, and then the samples are recovered by the backward diffusion process. To realize the backward diffusion process, we propose a new denoising model which predicts noise by stacking GCN(Graph Convolution Network) and MLP(Multi-layers Perceptron). We perform experiments on different datasets and the experimental results demonstrate that our method obtains state-of-the-art results.

Melanoma is a malignant tumor originating from the lesions of skin cells. Medical image segmentation tasks for skin lesion play a crucial role in quantitative analysis. Achieving precise and efficient segmentation remains a significant challenge for medical practitioners. Hence, a skin lesion segmentation model named MSDUNet, which incorporates multi-scale deformable block (MSD Block) and dual-input dynamic enhancement module(D2M), is proposed. Firstly, the model employs a hybrid architecture encoder that better integrates global and local features. Secondly, to better utilize macroscopic and microscopic multiscale information, improvements are made to skip connection and decoder block, introducing D2M and MSD Block. The D2M leverages large kernel dilated convolution to draw out attention bias matrix on the decoder features, supplementing and enhancing the semantic features of the decoder's lower layers transmitted through skip connection features, thereby compensating semantic gaps. The MSD Block uses channel-wise split and deformable convolutions with varying receptive fields to better extract and integrate multi-scale information while controlling the model's size, enabling the decoder to focus more on task-relevant regions and edge details. MSDUNet attains outstanding performance with Dice scores of 93.08% and 91.68% on the ISIC-2016 and ISIC-2018 datasets, respectively. Furthermore, experiments on the HAM10000 dataset demonstrate its superior performance with a Dice score of 95.40%. External validation experiments based on the ISIC-2016, ISIC-2018, and HAM10000 experimental weights on the PH2 dataset yield Dice scores of 92.67%, 92.31%, and 93.46%, respectively, showcasing the exceptional generalization capability of MSDUNet. Our code implementation is publicly available at the Github.

MOTIVATION: Cell-type-specific gene expression is maintained in large part by transcription factors (TFs) selectively binding to distinct sets of sites in different cell types. Recent research works have provided evidence that such cell-type-specific binding is determined by TF's intrinsic sequence preferences, cooperative interactions with co-factors, cell-type-specific chromatin landscapes and 3D chromatin interactions. However, computational prediction and characterization of cell-type-specific and shared binding sites is rarely studied. RESULTS: In this article, we propose two computational approaches for predicting and characterizing cell-type-specific and shared binding sites by integrating multiple types of features, in which one is based on XGBoost and another is based on convolutional neural network (CNN). To validate the performance of our proposed approaches, ChIP-seq datasets of 10 binding factors were collected from the GM12878 (lymphoblastoid) and K562 (erythroleukemic) human hematopoietic cell lines, each of which was further categorized into cell-type-specific (GM12878- and K562-specific) and shared binding sites. Then, multiple types of features for these binding sites were integrated to train the XGBoost- and CNN-based models. Experimental results show that our proposed approaches significantly outperform other competing methods on three classification tasks. Moreover, we identified independent feature contributions for cell-type-specific and shared sites through SHAP values and explored the ability of the CNN-based model to predict cell-type-specific and shared binding sites by excluding or including DNase signals. Furthermore, we investigated the generalization ability of our proposed approaches to different binding factors in the same cellular environment. AVAILABILITY AND IMPLEMENTATION: The source code is available at: https://github.com/turningpoint1988/CSSBS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: The limited knowledge of miRNA-lncRNA interactions is considered as an obstruction of revealing the regulatory mechanism. Accumulating evidence on Human diseases indicates that the modulation of gene expression has a great relationship with the interactions between miRNAs and lncRNAs. However, such interaction validation via crosslinking-immunoprecipitation and high-throughput sequencing (CLIP-seq) experiments that inevitably costs too much money and time but with unsatisfactory results. Therefore, more and more computational prediction tools have been developed to offer many reliable candidates for a better design of further bio-experiments. METHODS: In this work, we proposed a novel link prediction model based on Gaussian kernel-based method and linear optimization algorithm for inferring miRNA-lncRNA interactions (GKLOMLI). Given an observed miRNA-lncRNA interaction network, the Gaussian kernel-based method was employed to output two similarity matrixes of miRNAs and lncRNAs. Based on the integrated matrix combined with similarity matrixes and the observed interaction network, a linear optimization-based link prediction model was trained for inferring miRNA-lncRNA interactions. RESULTS: To evaluate the performance of our proposed method, k-fold cross-validation (CV) and leave-one-out CV were implemented, in which each CV experiment was carried out 100 times on a training set generated randomly. The high area under the curves (AUCs) at 0.8623 ± 0.0027 (2-fold CV), 0.9053 ± 0.0017 (5-fold CV), 0.9151 ± 0.0013 (10-fold CV), and 0.9236 (LOO-CV), illustrated the precision and reliability of our proposed method. CONCLUSION: GKLOMLI with high performance is anticipated to be used to reveal underlying interactions between miRNA and their target lncRNAs, and deciphers the potential mechanisms of the complex diseases.

Growing studies have shown that miRNAs are inextricably linked with many human diseases, and a great deal of effort has been spent on identifying their potential associations. Compared with traditional experimental methods, computational approaches have achieved promising results. In this article, we propose a graph representation learning method to predict miRNA-disease associations. Specifically, we first integrate the verified miRNA-disease associations with the similarity information of miRNA and disease to construct a miRNA-disease heterogeneous graph. Then, we apply a graph attention network to aggregate the neighbor information of nodes in each layer, and then feed the representation of the hidden layer into the structure-aware jumping knowledge network to obtain the global features of nodes. The output features of miRNAs and diseases are then concatenated and fed into a fully connected layer to score the potential associations. Through five-fold cross-validation, the average AUC, accuracy and precision values of our model are 93.30%, 85.18% and 88.90%, respectively. In addition, for three case studies of the esophageal tumor, lymphoma and prostate tumor, 46, 45 and 45 of the top 50 miRNAs predicted by our model were confirmed by relevant databases. Overall, our method could provide a reliable alternative for miRNA-disease association prediction.

Transcription factors (TFs) play a part in gene expression. TFs can form complex gene expression regulation system by combining with DNA. Thereby, identifying the binding regions has become an indispensable step for understanding the regulatory mechanism of gene expression. Due to the great achievements of applying deep learning (DL) to computer vision and language processing in recent years, many scholars are inspired to use these methods to predict TF binding sites (TFBSs), achieving extraordinary results. However, these methods mainly focus on whether DNA sequences include TFBSs. In this paper, we propose a fully convolutional network (FCN) coupled with refinement residual block (RRB) and global average pooling layer (GAPL), namely FCNARRB. Our model could classify binding sequences at nucleotide level by outputting dense label for input data. Experimental results on human ChIP-seq datasets show that the RRB and GAPL structures are very useful for improving model performance. Adding GAPL improves the performance by 9.32% and 7.61% in terms of IoU (Intersection of Union) and PRAUC (Area Under Curve of Precision and Recall), and adding RRB improves the performance by 7.40% and 4.64%, respectively. In addition, we find that conservation information can help locate TFBSs.

Recently, with the superior capacity for analyzing the multiplex graph data, self-supervised multiplex graph representation learning (SMGRL) has received much interest. However, existing SMGRL methods are still limited by the following issues: (i) they generally ignore the noisy information within each graph and the common information among different graphs, thus weakening the effectiveness of SMGRL, and (ii) they conduct negative sample encoding and complex pretext tasks for contrastive learning, thus weakening the efficiency of SMGRL. To solve these issues, in this work, we propose a new framework to conduct effective and efficient SMGRL. Specifically, the proposed method investigates the intra-graph and inter-graph decorrelation losses, respectively, for reducing the impact of noisy information within each graph and capturing the common information among different graphs, to achieve the effectiveness. Moreover, the proposed method does not need negative samples for the SMGRL and designs a simple pretext task, to achieve the efficiency. We further theoretically justify that our method achieves the maximal mutual information instead of directly conducting contrastive learning and theoretically justify that our method actually minimizes the multiplex graph information bottleneck, which guarantees the effectiveness. In addition, an extension for semi-supervised scenarios is proposed to fit the case that a few labels are provided in reality. Extensive experimental results verify the effectiveness and efficiency of the proposed method with respect to various downstream tasks.

Recent advances in localization techniques have fundamentally enhanced social networking services, allowing users to share their locations and location-related contents. This has further increased the popularity of location-based social networks (LBSNs) and produces a huge amount of trajectories composed of continuous and complex spatio-temporal points from people’s daily lives. How to accurately aggregate large-scale trajectories is an important and challenging task. Conventional clustering algorithms (e.g., k -means or k -mediods) cannot be directly employed to process trajectory data due to their serialization, triviality and redundancy. Aiming to overcome the drawbacks of traditional k -means algorithm and k -mediods, including their sensitivity to the selection of the initial k value, the cluster centers and easy convergence to a locally optimal solution, we first propose an optimized k -means algorithm (namely OKM ) to obtain k optimal initial clustering centers based on the density of trajectory points. Second, because k -means is sensitive to noisy points, we propose an improved k -mediods algorithm called IKMD based on an acceptable radius r by considering users’ geographic location in LBSNs. The value of k can be calculated based on r , and the optimal k points are selected as the initial clustering centers with high densities to reduce the cost of distance calculation. Thirdly, we thoroughly analyze the advantages of IKMD by comparing it with the commonly used clustering approaches through illustrative examples. Last, we conduct extensive experiments to evaluate the performance of IKMD against seven clustering approaches including the proposed optimized k -means algorithm, k -mediods algorithm, traditional density-based k -mediods algorithm and the state-of-the-arts trajectory clustering methods. The results demonstrate that IKMD significantly outperforms existing algorithms in the cost of distance calculation and the convergence speed. The methods proposed is proved to contribute to a larger effort targeted at advancing the study of intelligent trajectory data analytics.

Long short-term memory (LSTM) neural networks and attention mechanism have been widely used in sentiment representation learning and detection of texts. However, most of the existing deep learning models for text sentiment analysis ignore emotion's modulation effect on sentiment feature extraction, and the attention mechanisms of these deep neural network architectures are based on word- or sentence-level abstractions. Ignoring higher level abstractions may pose a negative effect on learning text sentiment features and further degrade sentiment classification performance. To address this issue, in this article, a novel model named AEC-LSTM is proposed for text sentiment detection, which aims to improve the LSTM network by integrating emotional intelligence (EI) and attention mechanism. Specifically, an emotion-enhanced LSTM, named ELSTM, is first devised by utilizing EI to improve the feature learning ability of LSTM networks, which accomplishes its emotion modulation of learning system via the proposed emotion modulator and emotion estimator. In order to better capture various structure patterns in text sequence, ELSTM is further integrated with other operations, including convolution, pooling, and concatenation. Then, topic-level attention mechanism is proposed to adaptively adjust the weight of text hidden representation. With the introduction of EI and attention mechanism, sentiment representation and classification can be more effectively achieved by utilizing sentiment semantic information hidden in text topic and context. Experiments on real-world data sets show that our approach can improve sentiment classification performance effectively and outperform state-of-the-art deep learning-based methods significantly.

Underlying a cancer phenotype is a specific gene regulatory network that represents the complex regulatory relationships between genes. It remains, however, a challenge to find cancer-related gene regulatory network because of insufficient sample sizes and complex regulatory mechanisms in which gene is influenced by not only other genes but also other biological factors. With the development of high-throughput technologies and the unprecedented wealth of multi-omics data it gives us a new opportunity to design machine learning method to investigate underlying gene regulatory network. In this paper, we propose an approach, which use Biweight Midcorrelation to measure the correlation between factors and make use of Nonconvex Penalty based sparse regression for Gene Regulatory Network inference (BMNPGRN). BMNCGRN incorporates multi-omics data (including DNA methylation and copy number variation) and their interactions in gene regulatory network model. The experimental results on synthetic datasets show that BMNPGRN outperforms popular and state-of-the-art methods (including DCGRN, ARACNE, and CLR) under false positive control. Furthermore, we applied BMNPGRN on breast cancer (BRCA) data from The Cancer Genome Atlas database and provided gene regulatory network.

Post translational modification plays a significiant role in the biological processing. The potential post translational modification is composed of the center sites and the adjacent amino acid residues which are fundamental protein sequence residues. It can be helpful to perform their biological functions and contribute to understanding the molecular mechanisms that are the foundations of protein design and drug design. The existing algorithms of predicting modified sites often have some shortcomings, such as lower stability and accuracy. In this paper, a combination of physical, chemical, statistical, and biological properties of a protein have been ulitized as the features, and a novel framework is proposed to predict a protein's post translational modification sites. The multi-layer neural network and support vector machine are invoked to predict the potential modified sites with the selected features that include the compositions of amino acid residues, the E-H description of protein segments, and several properties from the AAIndex database. Being aware of the possible redundant information, the feature selection is proposed in the propocessing step in this research. The experimental results show that the proposed method has the ability to improve the accuracy in this classification issue.

The problem of matrix approximation appears ubiquitously in recommendation systems, computer vision and text mining. The prevailing assumption is that the partially observed matrix has a low-rank or can be well approximated by a low-rank matrix. However, this assumption is strictly that the partially observed matrix is globally low rank. In this paper, we propose a local sensitive formulation of matrix approximation which relaxes the global low-rank assumption, leading to a representation of the observed matrix as a weighted sum of low-rank matrices. We solve the problem by an efficient way based on the alternating direction method of multipliers (ADMM). Our experiments show improvements in prediction accuracy over classical approaches for recommendation tasks.