Inference of gene regulatory networks based on directed graph convolutional networks.

Inferring gene regulatory network (GRN) is one of the important challenges in systems biology, and many outstanding computational methods have been proposed; however there remains some challenges especially in real datasets. In this study, we propose Directed Graph Convolutional neural network-based method for GRN inference (DGCGRN). To better understand and process the directed graph structure data of GRN, a directed graph convolutional neural network is conducted which retains the structural information of the directed graph while also making full use of neighbor node features. The local augmentation strategy is adopted in graph neural network to solve the problem of poor prediction accuracy caused by a large number of low-degree nodes in GRN. In addition, for real data such as E.coli, sequence features are obtained by extracting hidden features using Bi-GRU and calculating the statistical physicochemical characteristics of gene sequence. At the training stage, a dynamic update strategy is used to convert the obtained edge prediction scores into edge weights to guide the subsequent training process of the model. The results on synthetic benchmark datasets and real datasets show that the prediction performance of DGCGRN is significantly better than existing models. Furthermore, the case studies on bladder uroepithelial carcinoma and lung cancer cells also illustrate the performance of the proposed model.

Predicting Clinically Significant Prostate Cancer Using Urine Metabolomics via Liquid Chromatography Mass Spectrometry.

PURPOSE: Biomarkers predicting clinically significant prostate cancer (sPC) before biopsy are currently lacking. This study aimed to develop a non-invasive urine test to predict sPC in at-risk men using urinary metabolomic profiles. MATERIALS AND METHODS: Urine samples from 934 at-risk subjects and 268 treatment-naïve PC patients were subjected to liquid chromatography/mass spectrophotometry (LC-MS)-based metabolomics profiling using both C18 and hydrophilic interaction liquid chromatography (HILIC) column analyses. Four models were constructed (training cohort [n=647]) and validated (validation cohort [n=344]) for different purposes. Model I differentiates PC from benign cases. Models II, III, and a Gleason score model (model GS) predict sPC that is defined as National Comprehensive Cancer Network (NCCN)-categorized favorable-intermediate risk group or higher (Model II), unfavorable-intermediate risk group or higher (Model III), and GS ≥7 PC (model GS), respectively. The metabolomic panels and predicting models were constructed using logistic regression and Akaike information criterion. RESULTS: The best metabolomic panels from the HILIC column include 25, 27, 28 and 26 metabolites in Models I, II, III, and GS, respectively, with area under the curve (AUC) values ranging between 0.82 and 0.91 in the training cohort and between 0.77 and 0.86 in the validation cohort. The combination of the metabolomic panels and five baseline clinical factors that include serum prostate-specific antigen, age, family history of PC, previously negative biopsy, and abnormal digital rectal examination results significantly increased AUCs (range 0.88-0.91). At 90% sensitivity (validation cohort), 33%, 34%, 41%, and 36% of unnecessary biopsies were avoided in Models I, II, III, and GS, respectively. The above results were successfully validated using LC-MS with the C18 column. CONCLUSIONS: Urinary metabolomic profiles with baseline clinical factors may accurately predict sPC in men with elevated risk before biopsy.

Chlorogenic Acid Intravesical Therapy Changes Acute Voiding Behavior of Systemic Lipopolysaccharide Inflammation-Induced Cystitis Bladder in Mice.

This study explores the potential efficacy of chlorogenic acid (CGA) in mitigating lipopolysaccharide (LPS)-induced cystitis in a mice model. C57BL/6J mice were divided into four groups: normal control (NC), LPS, LPS + low CGA, and LPS + high CGA. Evaluation methods included cystometrogram (CMG), histopathological, western blot, and immunohistological analysis. In the LPS group, CMG revealed abnormal voiding behavior with increased micturition pressure, voided volume (VV), and decreased voided frequency. Low CGA treatment in LPS mice demonstrated improved micturition pressure and inter-contraction intervals (ICI). However, high CGA treatment exhibited prolonged ICI and increased VV, suggesting potential adverse effects. Histological analysis of LPS-treated mice displayed bladder inflammation and interstitial edema. Low CGA treatment reduced interstitial edema and bladder inflammation, confirmed by Masson's trichrome staining. Western blotting revealed increased cytokeratin 20 (K20) expression in the low CGA group, indicating structural abnormalities in the bladder umbrella layer after LPS administration. In conclusion, low CGA treatment positively impacted voiding behavior and decreased bladder edema and inflammation in the LPS-induced cystitis mice model, suggesting its potential as a supplement for inflammation cystitis prevention. However, high CGA treatment exhibited adverse effects, emphasizing the importance of dosage considerations in therapeutic applications.

DeepFGRN: inference of gene regulatory network with regulation type based on directed graph embedding.

The inference of gene regulatory networks (GRNs) from gene expression profiles has been a key issue in systems biology, prompting many researchers to develop diverse computational methods. However, most of these methods do not reconstruct directed GRNs with regulatory types because of the lack of benchmark datasets or defects in the computational methods. Here, we collect benchmark datasets and propose a deep learning-based model, DeepFGRN, for reconstructing fine gene regulatory networks (FGRNs) with both regulation types and directions. In addition, the GRNs of real species are always large graphs with direction and high sparsity, which impede the advancement of GRN inference. Therefore, DeepFGRN builds a node bidirectional representation module to capture the directed graph embedding representation of the GRN. Specifically, the source and target generators are designed to learn the low-dimensional dense embedding of the source and target neighbors of a gene, respectively. An adversarial learning strategy is applied to iteratively learn the real neighbors of each gene. In addition, because the expression profiles of genes with regulatory associations are correlative, a correlation analysis module is designed. Specifically, this module not only fully extracts gene expression features, but also captures the correlation between regulators and target genes. Experimental results show that DeepFGRN has a competitive capability for both GRN and FGRN inference. Potential biomarkers and therapeutic drugs for breast cancer, liver cancer, lung cancer and coronavirus disease 2019 are identified based on the candidate FGRNs, providing a possible opportunity to advance our knowledge of disease treatments.

Deep Self-Reconstruction Fusion Similarity Hashing for the Diagnosis of Alzheimer's Disease on Multi-Modal Data.

The pathogenesis of Alzheimer's disease (AD) is extremely intricate, which makes AD patients almost incurable. Recent studies have demonstrated that analyzing multi-modal data can offer a comprehensive perspective on the different stages of AD progression, which is beneficial for early diagnosis of AD. In this paper, we propose a deep self-reconstruction fusion similarity hashing (DS-FSH) method to effectively capture the AD-related biomarkers from the multi-modal data and leverage them to diagnose AD. Given that most existing methods ignore the topological structure of the data, a deep self-reconstruction model based on random walk graph regularization is designed to reconstruct the multi-modal data, thereby learning the nonlinear relationship between samples. Additionally, a fused similarity hash based on anchor graph is proposed to generate discriminative binary hash codes for multi-modal reconstructed data. This allows sample fused similarity to be effectively modeled by a fusion similarity matrix based on anchor graph while modal correlation can be approximated by Hamming distance. Especially, extracted features from the multi-modal data are classified using deep sparse autoencoders classifier. Finally, experiments conduct on the AD Neuroimaging Initiative database show that DS-FSH outperforms comparable methods of AD classification. To conclude, DS-FSH identifies multi-modal features closely associated with AD, which are expected to contribute significantly to understanding of the pathogenesis of AD.

UsIL-6: An unbalanced learning strategy for identifying IL-6 inducing peptides by undersampling technique.

BACKGROUND AND OBJECTIVE: Interleukin-6 (IL-6) is the critical factor of early warning, monitoring, and prognosis in the inflammatory storm of COVID-19 cases. IL-6 inducing peptides, which can induce cytokine IL-6 production, are very important for the development of diagnosis and immunotherapy. Although the existing methods have some success in predicting IL-6 inducing peptides, there is still room for improvement in the performance of these models in practical application. METHODS: In this study, we proposed UsIL-6, a high-performance bioinformatics tool for identifying IL-6 inducing peptides. First, we extracted five groups of physicochemical properties and sequence structural information from IL-6 inducing peptide sequences, and obtained a 636-dimensional feature vector, we also employed NearMiss3 undersampling method and normalization method StandardScaler to process the data. Then, a 40-dimensional optimal feature vector was obtained by Boruta feature selection method. Finally, we combined this feature vector with extreme randomization tree classifier to build the final model UsIL-6. RESULTS: The AUC value of UsIL-6 on the independent test dataset was 0.87, and the BACC value was 0.808, which indicated that UsIL-6 had better performance than the existing methods in IL-6 inducing peptide recognition. CONCLUSIONS: The performance comparison on independent test dataset confirmed that UsIL-6 could achieve the highest performance, best robustness, and most excellent generalization ability. We hope that UsIL-6 will become a valuable method to identify, annotate and characterize new IL-6 inducing peptides.

Inflammatory and Nutritional Biomarkers in Patients With Esophageal Squamous Cell Carcinoma Undergoing Neoadjuvant Chemotherapy and Radiation Therapy.

OBJECTIVES: To investigate the relationship between pretreatment inflammatory and nutritional biomarkers in patients with esophageal squamous cell carcinoma (ESCC) undergoing neoadjuvant chemotherapy and radiation therapy (nCRT). SAMPLE & SETTING: 213 patients with newly diagnosed stage II-III ESCC who received nCRT at an academic hospital in Taiwan. METHODS & VARIABLES: Electronic health record data were used. Records on inflammatory and nutritional biomarkers and clinical outcomes were extracted. Logistic regression analysis was used to predict treatment-related adverse events, Cox regression was used for survival outcomes, and receiver operating characteristic curve analysis was used to determine optimal cutoff values. RESULTS: There was a significant association between low prognostic nutritional index (PNI) and nCRT toxicities and survival. Advanced cancer stage, high platelet-to-lymphocyte ratio, and occurrence of pneumonia/infection were linked to survival outcomes. IMPLICATIONS FOR NURSING: PNI shows promise in predicting prognosis, helps identify high-risk patients, and enables nurses to apply tailored interventions.

Predictive factors for percutaneous nephrolithotomy bleeding risks.

Objective: This study aimed to identify predictive factors for percutaneous nephrolithotomy (PCNL) bleeding risks. With better risk stratification, bleeding in high-risk patient can be anticipated and facilitates early identification. Methods: A prospective observational study of PCNL performed at our institution was done. All adults with radio-opaque renal stones planned for PCNL were included except those with coagulopathy, planned for additional procedures. Factors including gender, co-morbidities, body mass index, stone burden, puncture site, tract dilatation size, operative position, surgeon's seniority, and operative duration were studied using stepwise multivariate regression analysis to identify the predictive factors associated with higher estimated hemoglobin (Hb) deficiency. Results: Overall, 4.86% patients (n=7) received packed cells transfusion. The mean estimated Hb deficiency was 1.3 (range 0-6.5) g/dL and the median was 1.0 g/dL. Stepwise multivariate regression analysis revealed that absence of hypertension (p=0.024), puncture site (p=0.027), and operative duration (p=0.023) were significantly associated with higher estimated Hb deficiency. However, the effect sizes are rather small with partial eta-squared of 0.037, 0.066, and 0.038, respectively. Observed power obtained was 0.621, 0.722, and 0.625, respectively. Other factors studied did not correlate with Hb difference. Conclusion: Hypertension, puncture site, and operative duration have significant impact on estimated Hb deficiency during PCNL. However, the effect size is rather small despite adequate study power obtained. Nonetheless, operative position (supine or prone), puncture number, or tract dilatation size did not correlate with Hb difference. The mainstay of reducing bleeding in PCNL is still meticulous operative technique. Our study findings also suggest that PCNL can be safely done by urology trainees under supervision in suitably selected patient, without increasing risk of bleeding.

Multi-Kernel Graph Attention Deep Autoencoder for MiRNA-Disease Association Prediction.

Accumulating evidence indicates that microRNAs (miRNAs) can control and coordinate various biological processes. Consequently, abnormal expressions of miRNAs have been linked to various complex diseases. Recognizable proof of miRNA-disease associations (MDAs) will contribute to the diagnosis and treatment of human diseases. Nevertheless, traditional experimental verification of MDAs is laborious and limited to small-scale. Therefore, it is necessary to develop reliable and effective computational methods to predict novel MDAs. In this work, a multi-kernel graph attention deep autoencoder (MGADAE) method is proposed to predict potential MDAs. In detail, MGADAE first employs the multiple kernel learning (MKL) algorithm to construct an integrated miRNA similarity and disease similarity, providing more biological information for further feature learning. Second, MGADAE combines the known MDAs, disease similarity, and miRNA similarity into a heterogeneous network, then learns the representations of miRNAs and diseases through graph convolution operation. After that, an attention mechanism is introduced into MGADAE to integrate the representations from multiple graph convolutional network (GCN) layers. Lastly, the integrated representations of miRNAs and diseases are input into the bilinear decoder to obtain the final predicted association scores. Corresponding experiments prove that the proposed method outperforms existing advanced approaches in MDA prediction. Furthermore, case studies related to two human cancers provide further confirmation of the reliability of MGADAE in practice.

Comparative Mitogenome Analyses Uncover Mitogenome Features and Phylogenetic Implications of the Reef Fish Family Holocentridae (Holocentriformes).

To understand the molecular mechanisms and adaptive strategies of holocentrid fish, we sequenced the mitogenome of eight species within the family Holocentridae and compared them with six other holocentrid species. The mitogenomes were found to be 16,507-16,639 bp in length and to encode 37 typical mitochondrial genes, including 13 PCGs, two ribosomal RNAs, and 22 transfer RNA genes. Structurally, the gene arrangement, base composition, codon usage, tRNA size, and putative secondary structures were comparable between species. Of the 13 PCGs, nad6 was the most specific gene that exhibited negative AT-skews and positive GC-skews. Most of the genes begin with the standard codon ATG, except cox1, which begins with the codon GTG. By examining their phylogeny, Sargocentron and Neoniphon were verified to be closely related and to belong to the same subfamily Holocentrinae, while Myripristis and Ostichthys belong to the other subfamily Myripristinae. The subfamilies were clearly distinguished by high-confidence-supported clades, which provide evidence to explain the differences in morphology and feeding habits between the two subfamilies. Selection pressure analysis indicated that all PCGs were subject to purifying selection. Overall, our study provides valuable insight into the habiting behavior, evolution, and ecological roles of these important marine fish.

Prediction of clinically significant prostate cancer through urine metabolomic signatures: A large-scale validated study.

PURPOSE: Currently, there are no accurate markers for predicting potentially lethal prostate cancer (PC) before biopsy. This study aimed to develop urine tests to predict clinically significant PC (sPC) in men at risk. METHODS: Urine samples from 928 men, namely, 660 PC patients and 268 benign subjects, were analyzed by gas chromatography/quadrupole time-of-flight mass spectrophotometry (GC/Q-TOF MS) metabolomic profiling to construct four predictive models. Model I discriminated between PC and benign cases. Models II, III, and GS, respectively, predicted sPC in those classified as having favorable intermediate risk or higher, unfavorable intermediate risk or higher (according to the National Comprehensive Cancer Network risk groupings), and a Gleason sum (GS) of ≥ 7. Multivariable logistic regression was used to evaluate the area under the receiver operating characteristic curves (AUC). RESULTS: In Models I, II, III, and GS, the best AUCs (0.94, 0.85, 0.82, and 0.80, respectively; training cohort, N = 603) involved 26, 24, 26, and 22 metabolites, respectively. The addition of five clinical risk factors (serum prostate-specific antigen, patient age, previous negative biopsy, digital rectal examination, and family history) significantly improved the AUCs of the models (0.95, 0.92, 0.92, and 0.87, respectively). At 90% sensitivity, 48%, 47%, 50%, and 36% of unnecessary biopsies could be avoided. These models were successfully validated against an independent validation cohort (N = 325). Decision curve analysis showed a significant clinical net benefit with each combined model at low threshold probabilities. Models II and III were more robust and clinically relevant than Model GS. CONCLUSION: This urine test, which combines urine metabolic markers and clinical factors, may be used to predict sPC and thereby inform the necessity of biopsy in men with an elevated PC risk.

scGCC: Graph Contrastive Clustering With Neighborhood Augmentations for scRNA-Seq Data Analysis.

Single-cell RNA sequencing (scRNA-seq) has rapidly emerged as a powerful technique for analyzing cellular heterogeneity at the individual cell level. In the analysis of scRNA-seq data, cell clustering is a critical step in downstream analysis, as it enables the identification of cell types and the discovery of novel cell subtypes. However, the characteristics of scRNA-seq data, such as high dimensionality and sparsity, dropout events and batch effects, present significant computational challenges for clustering analysis. In this study, we propose scGCC, a novel graph self-supervised contrastive learning model, to address the challenges faced in scRNA-seq data analysis. scGCC comprises two main components: a representation learning module and a clustering module. The scRNA-seq data is first fed into a representation learning module for training, which is then used for data classification through a clustering module. scGCC can learn low-dimensional denoised embeddings, which is advantageous for our clustering task. We introduce Graph Attention Networks (GAT) for cell representation learning, which enables better feature extraction and improved clustering accuracy. Additionally, we propose five data augmentation methods to improve clustering performance by increasing data diversity and reducing overfitting. These methods enhance the robustness of clustering results. Our experimental study on 14 real-world datasets has demonstrated that our model achieves extraordinary accuracy and robustness. We also perform downstream tasks, including batch effect removal, trajectory inference, and marker genes analysis, to verify the biological effectiveness of our model.

Non-Negative Low-Rank Representation With Similarity Correction for Cell Type Identification in scRNA-Seq Data.

Single-cell RNA sequencing (scRNA-Seq) technology has emerged as a powerful tool to investigate cellular heterogeneity within tissues, organs, and organisms. One fundamental question pertaining to single-cell gene expression data analysis revolves around the identification of cell types, which constitutes a critical step within the data processing workflow. However, existing methods for cell type identification through learning low-dimensional latent embeddings often overlook the intercellular structural relationships. In this paper, we present a novel non-negative low-rank similarity correction model (NLRSIM) that leverages subspace clustering to preserve the global structure among cells. This model introduces a novel manifold learning process to address the issue of imbalanced neighbourhood spatial density in cells, thereby effectively preserving local geometric structures. This procedure utilizes a position-sensitive hashing algorithm to construct the graph structure of the data. The experimental results demonstrate that the NLRSIM surpasses other advanced models in terms of clustering effects and visualization experiments. The validated effectiveness of gene expression information after calibration by the NLRSIM model has been duly ascertained in the realm of relevant biological studies. The NLRSIM model offers unprecedented insights into gene expression, states, and structures at the individual cellular level, thereby contributing novel perspectives to the field.

iCircDA-NEAE: Accelerated attribute network embedding and dynamic convolutional autoencoder for circRNA-disease associations prediction.

Accumulating evidence suggests that circRNAs play crucial roles in human diseases. CircRNA-disease association prediction is extremely helpful in understanding pathogenesis, diagnosis, and prevention, as well as identifying relevant biomarkers. During the past few years, a large number of deep learning (DL) based methods have been proposed for predicting circRNA-disease association and achieved impressive prediction performance. However, there are two main drawbacks to these methods. The first is these methods underutilize biometric information in the data. Second, the features extracted by these methods are not outstanding to represent association characteristics between circRNAs and diseases. In this study, we developed a novel deep learning model, named iCircDA-NEAE, to predict circRNA-disease associations. In particular, we use disease semantic similarity, Gaussian interaction profile kernel, circRNA expression profile similarity, and Jaccard similarity simultaneously for the first time, and extract hidden features based on accelerated attribute network embedding (AANE) and dynamic convolutional autoencoder (DCAE). Experimental results on the circR2Disease dataset show that iCircDA-NEAE outperforms other competing methods significantly. Besides, 16 of the top 20 circRNA-disease pairs with the highest prediction scores were validated by relevant literature. Furthermore, we observe that iCircDA-NEAE can effectively predict new potential circRNA-disease associations.

ARGLRR: A Sparse Low-Rank Representation Single-Cell RNA-Sequencing Data Clustering Method Combined with a New Graph Regularization.

The development of single-cell transcriptome sequencing technologies has opened new ways to study biological phenomena at the cellular level. A key application of such technologies involves the employment of single-cell RNA sequencing (scRNA-seq) data to identify distinct cell types through clustering, which in turn provides evidence for revealing heterogeneity. Despite the promise of this approach, the inherent characteristics of scRNA-seq data, such as higher noise levels and lower coverage, pose major challenges to existing clustering methods and compromise their accuracy. In this study, we propose a method called Adjusted Random walk Graph regularization Sparse Low-Rank Representation (ARGLRR), a practical sparse subspace clustering method, to identify cell types. The fundamental low-rank representation (LRR) model is concerned with the global structure of data. To address the limited ability of the LRR method to capture local structure, we introduced adjusted random walk graph regularization in its framework. ARGLRR allows for the capture of both local and global structures in scRNA-seq data. Additionally, the imposition of similarity constraints into the LRR framework further improves the ability of the proposed model to estimate cell-to-cell similarity and capture global structural relationships between cells. ARGLRR surpasses other advanced comparison approaches on nine known scRNA-seq data sets judging by the results. In the normalized mutual information and Adjusted Rand Index metrics on the scRNA-seq data sets clustering experiments, ARGLRR outperforms the best-performing comparative method by 6.99% and 5.85%, respectively. In addition, we visualize the result using Uniform Manifold Approximation and Projection. Visualization results show that the usage of ARGLRR enhances the separation of different cell types within the similarity matrix.

Investigating sarcopenia, physical activity, and inflammation biomarkers in newly diagnosed oral cancer patients during curative treatment: A prospective longitudinal study.

Objective: This prospective longitudinal study aimed to investigate changes in sarcopenia, physical activity, and inflammation biomarkers in patients with oral cavity cancer during curative treatment and explore their association with treatment outcomes. Methods: Patients newly diagnosed with oral cavity cancer who underwent primary surgery with (chemo)radiation therapy were included. Along with physical activity and inflammatory markers, sarcopenia was assessed using a 5-time chair stand test, hand grip strength, and skeletal muscle index (SMI). Data were collected before operation and after 3 months (T2) and 6 months after operation. Logistic regression and Cox proportional hazards models were used to identify predictors of treatment outcomes. Results: Out of 56 patients, 21 (37.5%) had sarcopenia. SMI score, physical activity, and neutrophil-to-lymphocyte ratio (NLR) showed significant changes after surgery, with exacerbation at T2. Patients with sarcopenia exhibited a significant decrease in SMI scores at T2. Advanced cancer stage and sarcopenia were associated with treatment-related dysphagia (odds ratio [OR] â€‹= â€‹3.01, P â€‹= â€‹0.034; OR â€‹= â€‹7.62, P â€‹= â€‹0.018). Sarcopenia (OR â€‹= â€‹3.02, P â€‹= â€‹0.002) and NLR (OR â€‹= â€‹5.38, P â€‹< â€‹0.001) were significantly associated with infections. Pretreatment SMI independently predicted poor survival outcomes (hazard ratio â€‹= â€‹7.00, P â€‹= â€‹0.005). Conclusions: Identifying patients with oral cavity cancer, sarcopenia, and high NLR levels can ensure prompt education and vigilant monitoring, potentially improving treatment outcomes and patient well-being during curative treatment.

A New Binary Biclustering Algorithm Based on Weight Adjacency Difference Matrix for Analyzing Gene Expression Data.

Biclustering algorithms are essential for processing gene expression data. However, to process the dataset, most biclustering algorithms require preprocessing the data matrix into a binary matrix. Regrettably, this type of preprocessing may introduce noise or cause information loss in the binary matrix, which would reduce the biclustering algorithm's ability to effectively obtain the optimal biclusters. In this paper, we propose a new preprocessing method named Mean-Standard Deviation (MSD) to resolve the problem. Additionally, we introduce a new biclustering algorithm called Weight Adjacency Difference Matrix Binary Biclustering (W-AMBB) to effectively process datasets containing overlapping biclusters. The basic idea is to create a weighted adjacency difference matrix by applying weights to a binary matrix that is derived from the data matrix. This allows us to identify genes with significant associations in sample data by efficiently identifying similar genes that respond to specific conditions. Furthermore, the performance of the W-AMBB algorithm was tested on both synthetic and real datasets and compared with other classical biclustering methods. The experiment results demonstrate that the W-AMBB algorithm is significantly more robust than the compared biclustering methods on the synthetic dataset. Additionally, the results of the GO enrichment analysis show that the W-AMBB method possesses biological significance on real datasets.

CNNGRN: A Convolutional Neural Network-Based Method for Gene Regulatory Network Inference From Bulk Time-Series Expression Data.

Gene regulatory networks (GRNs) participate in many biological processes, and reconstructing them plays an important role in systems biology. Although many advanced methods have been proposed for GRN reconstruction, their predictive performance is far from the ideal standard, so it is urgent to design a more effective method to reconstruct GRN. Moreover, most methods only consider the gene expression data, ignoring the network structure information contained in GRN. In this study, we propose a supervised model named CNNGRN, which infers GRN from bulk time-series expression data via convolutional neural network (CNN) model, with a more informative feature. Bulk time series gene expression data imply the intricate regulatory associations between genes, and the network structure feature of ground-truth GRN contains rich neighbor information. Hence, CNNGRN integrates the above two features as model inputs. In addition, CNN is adopted to extract intricate features of genes and infer the potential associations between regulators and target genes. Moreover, feature importance visualization experiments are implemented to seek the key features. Experimental results show that CNNGRN achieved competitive performance on benchmark datasets compared to the state-of-the-art computational methods. Finally, hub genes identified based on CNNGRN have been confirmed to be involved in biological processes through literature.

Potential circRNA-Disease Association Prediction Using DeepWalk and Nonnegative Matrix Factorization.

Circular RNAs (circRNAs) are a category of noncoding RNAs that exist in great numbers in eukaryotes. They have recently been discovered to be crucial in the growth of tumors. Therefore, it is important to explore the association of circRNAs with disease. This paper proposes a new method based on DeepWalk and nonnegative matrix factorization (DWNMF) to predict circRNA-disease association. Based on the known circRNA-disease association, we calculate the topological similarity of circRNA and disease via the DeepWalk-based method to learn the node features on the association network. Next, the functional similarity of the circRNAs and the semantic similarity of the diseases are fused with their respective topological similarities at different scales. Then, we use the improved weighted K-nearest neighbor (IWKNN) method to preprocess the circRNA-disease association network and correct nonnegative associations by setting different parameters K1 and K2 in the circRNA and disease matrices. Finally, the L2,1-norm, dual-graph regularization term and Frobenius norm regularization term are introduced into the nonnegative matrix factorization model to predict the circRNA-disease correlation. We perform cross-validation on circR2Disease, circRNADisease, and MNDR. The numerical results show that DWNMF is an efficient tool for forecasting potential circRNA-disease relationships, outperforming other state-of-the-art approaches in terms of predictive performance.