RESUMEN
Taiwan harbors five endemic species of salamanders (Hynobius spp.) that inhabit distinct alpine regions, contributing to population fragmentation across isolated "sky islands". With an evolutionary history spanning multiple glacial-interglacial cycles, these species represent an exceptional paradigm for exploring biogeography and speciation. However, a lack of suitable genetic markers applicable across species has limited research efforts. Thus, developing cross-amplifying markers is imperative. Expressed sequence-tag simple-sequence repeats (EST-SSRs) that amplify across divergent lineages are ideal for species identification in instances where phenotypic differentiation is challenging. Here, we report a suite of cross-amplifying EST-SSRs from the transcriptomes of the five Hynobius species that exhibit an interspecies transferability rate of 67.67%. To identify individual markers exhibiting cross-species polymorphism and to assess interspecies genetic diversity, we assayed 140 individuals from the five species across 84 sampling sites. A set of EST-SSRs with a high interspecies polymorphic information content (PIC = 0.63) effectively classified these individuals into five distinct clusters, as supported by discriminant analysis of principal components (DAPC), STRUCTURE assignment tests, and Neighbor-joining trees. Moreover, pair-wise FST values > 0.15 indicate notable between-cluster genetic divergence. Our set of 20 polymorphic EST-SSRs is suitable for assessing population structure within and among Hynobius species, as well as for long-term monitoring of their genetic composition.
Asunto(s)
Etiquetas de Secuencia Expresada , Repeticiones de Microsatélite , Animales , Repeticiones de Microsatélite/genética , Taiwán , Urodelos/genética , Urodelos/clasificación , Variación Genética , Polimorfismo Genético , Filogenia , Transcriptoma/genéticaRESUMEN
Circular RNA (circRNA)-microRNA (miRNA) interaction (CMI) plays crucial roles in cellular regulation, offering promising perspectives for disease diagnosis and therapy. Therefore, it is necessary to employ computational methods for the rapid and cost-effective prediction of potential circRNA-miRNA interactions. However, the existing methods are limited by incomplete data; therefore, it is difficult to model molecules with different attributes on a large scale, which greatly hinders the efficiency and performance of prediction. In this study, we propose an effective method for predicting circRNA-miRNA interactions, called RBNE-CMI, and introduce a framework that can embed incomplete multiattribute CMI heterogeneous networks. By combining the proposed method, we integrate different data sets in the CMI prediction field into one incomplete network for modeling, achieving superior performance in 5-fold cross-validation. Moreover, in the prediction task based on complete data, the proposed method still achieves better performance than the known model. In addition, in the case study, we successfully predicted 18 of the 20 potential cancer biomarkers. The data and source code can be found at https://github.com/1axin/RBNE-CMI.
RESUMEN
Cell type identification is an indispensable analytical step in single-cell data analyses. To address the high noise stemming from gene expression data, existing computational methods often overlook the biologically meaningful relationships between genes, opting to reduce all genes to a unified data space. We assume that such relationships can aid in characterizing cell type features and improving cell type recognition accuracy. To this end, we introduce scPriorGraph, a dual-channel graph neural network that integrates multi-level gene biosemantics. Experimental results demonstrate that scPriorGraph effectively aggregates feature values of similar cells using high-quality graphs, achieving state-of-the-art performance in cell type identification.
Asunto(s)
Análisis de la Célula Individual , Análisis de la Célula Individual/métodos , Humanos , Redes Neurales de la Computación , RNA-Seq/métodos , Biología Computacional/métodos , Algoritmos , Programas Informáticos , Análisis de Expresión Génica de una Sola CélulaRESUMEN
Circular RNA (CircRNA)-microRNA (miRNA) interaction (CMI) is an important model for the regulation of biological processes by non-coding RNA (ncRNA), which provides a new perspective for the study of human complex diseases. However, the existing CMI prediction models mainly rely on the nearest neighbor structure in the biological network, ignoring the molecular network topology, so it is difficult to improve the prediction performance. In this paper, we proposed a new CMI prediction method, BEROLECMI, which uses molecular sequence attributes, molecular self-similarity, and biological network topology to define the specific role feature representation for molecules to infer the new CMI. BEROLECMI effectively makes up for the lack of network topology in the CMI prediction model and achieves the highest prediction performance in three commonly used data sets. In the case study, 14 of the 15 pairs of unknown CMIs were correctly predicted.
Asunto(s)
Biología Computacional , MicroARNs , ARN Circular , MicroARNs/genética , MicroARNs/metabolismo , MicroARNs/química , ARN Circular/genética , ARN Circular/metabolismo , Humanos , Biología Computacional/métodos , ARN/química , ARN/genética , ARN/metabolismo , Algoritmos , Redes Reguladoras de GenesRESUMEN
BACKGROUND: Drug-drug interaction events influence the effectiveness of drug combinations and can lead to unexpected side effects or exacerbate underlying diseases, jeopardizing patient prognosis. Most existing methods are restricted to predicting whether two drugs interact or the type of drug-drug interactions, while very few studies endeavor to predict the specific risk levels of side effects of drug combinations. METHODS: In this study, we propose MathEagle, a novel approach to predict accurate risk levels of drug combinations based on multi-head attention and heterogeneous attribute graph learning. Initially, we model drugs and three distinct risk levels between drugs as a heterogeneous information graph. Subsequently, behavioral and chemical structure features of drugs are utilized by message passing neural networks and graph embedding algorithms, respectively. Ultimately, MathEagle employs heterogeneous graph convolution and multi-head attention mechanisms to learn efficient latent representations of drug nodes and estimates the risk levels of pairwise drugs in an end-to-end manner. RESULTS: To assess the effectiveness and robustness of the model, five-fold cross-validation, ablation experiments, and case studies were conducted. MathEagle achieved an accuracy of 85.85 % and an AUC of 0.9701 on the drug risk level prediction task and is superior to all comparative models. The MathEagle predictor is freely accessible at http://120.77.11.78/MathEagle/. CONCLUSIONS: The experimental results indicate that MathEagle can function as an effective tool for predicting accurate risk of drug combinations, aiding in guiding clinical medication, and enhancing patient outcomes.
Asunto(s)
Interacciones Farmacológicas , Humanos , Algoritmos , Redes Neurales de la Computación , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos , Aprendizaje AutomáticoRESUMEN
As post-transcriptional regulators of gene expression, micro-ribonucleic acids (miRNAs) are regarded as potential biomarkers for a variety of diseases. Hence, the prediction of miRNA-disease associations (MDAs) is of great significance for an in-depth understanding of disease pathogenesis and progression. Existing prediction models are mainly concentrated on incorporating different sources of biological information to perform the MDA prediction task while failing to consider the fully potential utility of MDA network information at the motif-level. To overcome this problem, we propose a novel motif-aware MDA prediction model, namely MotifMDA, by fusing a variety of high- and low-order structural information. In particular, we first design several motifs of interest considering their ability to characterize how miRNAs are associated with diseases through different network structural patterns. Then, MotifMDA adopts a two-layer hierarchical attention to identify novel MDAs. Specifically, the first attention layer learns high-order motif preferences based on their occurrences in the given MDA network, while the second one learns the final embeddings of miRNAs and diseases through coupling high- and low-order preferences. Experimental results on two benchmark datasets have demonstrated the superior performance of MotifMDA over several state-of-the-art prediction models. This strongly indicates that accurate MDA prediction can be achieved by relying solely on MDA network information. Furthermore, our case studies indicate that the incorporation of motif-level structure information allows MotifMDA to discover novel MDAs from different perspectives.
Asunto(s)
Biología Computacional , MicroARNs , MicroARNs/genética , Humanos , Biología Computacional/métodos , Predisposición Genética a la Enfermedad/genética , AlgoritmosRESUMEN
BACKGROUND: Whether hyperbaric oxygen therapy (HBOT) can cause paradoxical herniation is still unclear. CASE SUMMARY: A 65-year-old patient who was comatose due to brain trauma underwent decompressive craniotomy and gradually regained consciousness after surgery. HBOT was administered 22 d after surgery due to speech impairment. Paradoxical herniation appeared on the second day after treatment, and the patient's condition worsened after receiving mannitol treatment at the rehabilitation hospital. After timely skull repair, the paradoxical herniation was resolved, and the patient regained consciousness and had a good recovery as observed at the follow-up visit. CONCLUSION: Paradoxical herniation is rare and may be caused by HBOT. However, the underlying mechanism is unknown, and the understanding of this phenomenon is insufficient. The use of mannitol may worsen this condition. Timely skull repair can treat paradoxical herniation and prevent serious complications.
RESUMEN
INTRODUCTION: Acupuncture and related acupoint therapies have been widely used for smoking cessation. Some relevant systematic reviews (SRs) have been published. There is a need to summarize and update the evidence to inform practice and decision-making. METHODS: Eight databases were searched from their inception to December 2023. SRs, any randomized controlled trials (RCTs) comparing acupuncture therapies with sham acupuncture, pharmacotherapy, behavioral therapy, or no treatment, were included. The primary outcome was the abstinence rate. AMSTAR-2 was employed to assess the quality of SRs. An updated meta-analysis was conducted based on SRs and RCTs. Data were synthesized using risk ratios (RR) with 95% confidence intervals (CIs). The GRADE approach was employed to assess the certainty of the updated evidence. RESULTS: Thirteen SRs and 20 RCTs outside of the SRs were identified. The SRs were of low or very low quality by AMSTAR-2. Sixteen (80%) RCTs were at high risk of performance bias. Eight acupuncture and related acupoint therapies were involved. The short-term (≤6 months) abstinence rate outcome was summarized as follows. Most SRs suggested that filiform needle acupuncture or acupressure had a better effect than sham acupuncture, but the findings were inconsistent. The updated meta-analysis also suggested that filiform needle acupuncture was more effective than sham acupuncture (RR=1.44; 95% CI: 1.02-2.02; I2 = 66%; low certainty; 9 RCTs, n=1358). Filiform needle acupuncture combined with acupressure was comparable to nicotine patches (RR=0.99; 95% CI: 0.74-1.32; low certainty; 6 RCTs, n= 524). Acupressure was superior to counseling (RR=1.46; 95% CI: 1.14-1.87; I2=5%; low certainty; 8 RCTs, n=595). No serious adverse events were reported in these SRs or RCTs. CONCLUSIONS: Low certainty evidence suggests that filiform needle acupuncture and auricular acupressure appear to be safe and effective in achieving short-term smoking cessation. However, long-term follow-up data are needed.
RESUMEN
Emerging clinical evidence suggests that sophisticated associations with circular ribonucleic acids (RNAs) (circRNAs) and microRNAs (miRNAs) are a critical regulatory factor of various pathological processes and play a critical role in most intricate human diseases. Nonetheless, the above correlations via wet experiments are error-prone and labor-intensive, and the underlying novel circRNA-miRNA association (CMA) has been validated by numerous existing computational methods that rely only on single correlation data. Considering the inadequacy of existing machine learning models, we propose a new model named BGF-CMAP, which combines the gradient boosting decision tree with natural language processing and graph embedding methods to infer associations between circRNAs and miRNAs. Specifically, BGF-CMAP extracts sequence attribute features and interaction behavior features by Word2vec and two homogeneous graph embedding algorithms, large-scale information network embedding and graph factorization, respectively. Multitudinous comprehensive experimental analysis revealed that BGF-CMAP successfully predicted the complex relationship between circRNAs and miRNAs with an accuracy of 82.90% and an area under receiver operating characteristic of 0.9075. Furthermore, 23 of the top 30 miRNA-associated circRNAs of the studies on data were confirmed in relevant experiences, showing that the BGF-CMAP model is superior to others. BGF-CMAP can serve as a helpful model to provide a scientific theoretical basis for the study of CMA prediction.
Asunto(s)
MicroARNs , Humanos , MicroARNs/genética , ARN Circular/genética , Curva ROC , Aprendizaje Automático , Algoritmos , Biología Computacional/métodosRESUMEN
Background: Acute respiratory tract infections (ARTIs) are the most common cause of morbidity and mortality worldwide, with most people experiencing at least one episode per year. Current treatment options are mainly symptomatic therapy. Antivirals, antibiotics, and glucocorticoids are of limited benefit for most infections. Traditional Chinese medicine has shown potential benefits in the treatment of ARTIs. Objective: The objective of this study was to determine the efficacy, effectiveness, and safety of Phragmites communis Trin. (P. communis, a synonym of Phragmites australis (Cav.) Trin. ex Steud) as monotherapy or as part of an herb mixture for ARTIs. Method: Eight databases and two clinical trial registries were searched from inception to 8 February 2023 for randomized controlled trials (RCTs) evaluating any preparation involving P. communis without language restrictions. The Risk of Bias Tool 2.0 was used to assess the risk of bias of the included trials. RevMan 5.3 software was used for data analyses with effects estimated as risk ratios (RRs), mean differences (MDs), or standardized mean differences (SMDs) with 95% confidence intervals (CIs). The online GRADEpro tool was used to assess the certainty of the evidence, if available. Results: Forty-two RCTs involving 6,879 patients with ARTIs were included, with all trials investigating P. communis as part of an herbal mixture. Of the included trials, the majority (38/42) were considered high risk. Compared to the placebo, P. communis preparations improved the cure rate [RR = 1.60, 95% CI (1.13, 2.26)] and fever clearance time [MD = -2.73 h, 95% CI (-4.85, -0.61)]. Compared to usual care alone, P. communis preparations also significantly improved the cure rate [RR = 1.57, 95% CI (1.36, 1.81)] and fever clearance time [SMD = -1.24, 95% CI (-2.37, -0.11)]. P. communis preparations plus usual care compared to usual care alone increased the cure rate [RR = 1.55, 95% CI (1.35, 1.78)], shortened the fever clearance time [MD = -19.31 h, 95% CI (-33.35, -5.27)], and improved FEV1 [ MD = 0.19 L, 95% CI (0.13, 0.26)] and FVC [ MD = 0.16 L, 95% CI (0.03, 0.28)]. Conclusion: Low- or very low-certainty evidence suggests that P. communis preparations may improve the cure rate of ARTIs, shorten the fever clearance time in febrile patients, and improve the pulmonary function of patients with acute exacerbation of chronic obstructive pulmonary disease or chronic bronchitis. However, these findings are inconclusive and need to be confirmed in rigorously designed trials. Systematic review registration: PROSPERO, identifier CRD42021239936.
RESUMEN
Connections between circular RNAs (circRNAs) and microRNAs (miRNAs) assume a pivotal position in the onset, evolution, diagnosis and treatment of diseases and tumors. Selecting the most potential circRNA-related miRNAs and taking advantage of them as the biological markers or drug targets could be conducive to dealing with complex human diseases through preventive strategies, diagnostic procedures and therapeutic approaches. Compared to traditional biological experiments, leveraging computational models to integrate diverse biological data in order to infer potential associations proves to be a more efficient and cost-effective approach. This paper developed a model of Convolutional Autoencoder for CircRNA-MiRNA Associations (CA-CMA) prediction. Initially, this model merged the natural language characteristics of the circRNA and miRNA sequence with the features of circRNA-miRNA interactions. Subsequently, it utilized all circRNA-miRNA pairs to construct a molecular association network, which was then fine-tuned by labeled samples to optimize the network parameters. Finally, the prediction outcome is obtained by utilizing the deep neural networks classifier. This model innovatively combines the likelihood objective that preserves the neighborhood through optimization, to learn the continuous feature representation of words and preserve the spatial information of two-dimensional signals. During the process of 5-fold cross-validation, CA-CMA exhibited exceptional performance compared to numerous prior computational approaches, as evidenced by its mean area under the receiver operating characteristic curve of 0.9138 and a minimal SD of 0.0024. Furthermore, recent literature has confirmed the accuracy of 25 out of the top 30 circRNA-miRNA pairs identified with the highest CA-CMA scores during case studies. The results of these experiments highlight the robustness and versatility of our model.
Asunto(s)
MicroARNs , Neoplasias , Humanos , MicroARNs/genética , ARN Circular/genética , Funciones de Verosimilitud , Redes Neurales de la Computación , Neoplasias/genética , Biología Computacional/métodosRESUMEN
According to the expression of miRNA in pathological processes, miRNAs can be divided into oncogenes or tumor suppressors. Prediction of the regulation relations between miRNAs and small molecules (SMs) becomes a vital goal for miRNA-target therapy. But traditional biological approaches are laborious and expensive. Thus, there is an urgent need to develop a computational model. In this study, we proposed a computational model to predict whether the regulatory relationship between miRNAs and SMs is up-regulated or down-regulated. Specifically, we first use the Large-scale Information Network Embedding (LINE) algorithm to construct the node features from the self-similarity networks, then use the General Attributed Multiplex Heterogeneous Network Embedding (GATNE) algorithm to extract the topological information from the attribute network, and finally utilize the Light Gradient Boosting Machine (LightGBM) algorithm to predict the regulatory relationship between miRNAs and SMs. In the fivefold cross-validation experiment, the average accuracies of the proposed model on the SM2miR dataset reached 79.59% and 80.37% for up-regulation pairs and down-regulation pairs, respectively. In addition, we compared our model with another published model. Moreover, in the case study for 5-FU, 7 of 10 candidate miRNAs are confirmed by related literature. Therefore, we believe that our model can promote the research of miRNA-targeted therapy.
Asunto(s)
MicroARNs , MicroARNs/genética , MicroARNs/metabolismo , Biología Computacional , Algoritmos , OncogenesRESUMEN
Drug repositioning plays a key role in disease treatment. With the large-scale chemical data increasing, many computational methods are utilized for drug-disease association prediction. However, most of the existing models neglect the positive influence of non-Euclidean data and multisource information, and there is still a critical issue for graph neural networks regarding how to set the feature diffuse distance. To solve the problems, we proposed SiSGC, which makes full use of the biological knowledge information as initial features and learns the structure information from the constructed heterogeneous graph with the adaptive selection of the information diffuse distance. Then, the structural features are fused with the denoised similarity information and fed to the advanced classifier of CatBoost to make predictions. Three different data sets are used to confirm the robustness and generalization of SiSGC under two splitting strategies. Experiment results demonstrate that the proposed model achieves superior performance compared with the six leading methods and four variants. Our case study on breast neoplasms further indicates that SiSGC is trustworthy and robust yet simple. We also present four drugs for breast cancer treatment with high confidence and further give an explanation for demonstrating the rationality. There is no doubt that SiSGC can be used as a beneficial supplement for drug repositioning.
Asunto(s)
Reposicionamiento de Medicamentos , Redes Neurales de la ComputaciónRESUMEN
Growing studies reveal that Circular RNAs (circRNAs) are broadly engaged in physiological processes of cell proliferation, differentiation, aging, apoptosis, and are closely associated with the pathogenesis of numerous diseases. Clarification of the correlation among diseases and circRNAs is of great clinical importance to provide new therapeutic strategies for complex diseases. However, previous circRNA-disease association prediction methods rely excessively on the graph network, and the model performance is dramatically reduced when noisy connections occur in the graph structure. To address this problem, this paper proposes an unsupervised deep graph structure learning method GSLCDA to predict potential CDAs. Concretely, we first integrate circRNA and disease multi-source data to constitute the CDA heterogeneous network. Then the network topology is learned using the graph structure, and the original graph is enhanced in an unsupervised manner by maximize the inter information of the learned and original graphs to uncover their essential features. Finally, graph space sensitive k-nearest neighbor (KNN) algorithm is employed to search for latent CDAs. In the benchmark dataset, GSLCDA obtained 92.67% accuracy with 0.9279 AUC. GSLCDA also exhibits exceptional performance on independent datasets. Furthermore, 14, 12 and 14 of the top 16 circRNAs with the most points GSLCDA prediction scores were confirmed in the relevant literature in the breast cancer, colorectal cancer and lung cancer case studies, respectively. Such results demonstrated that GSLCDA can validly reveal underlying CDA and offer new perspectives for the diagnosis and therapy of complex human diseases.
Asunto(s)
Neoplasias de la Mama , Neoplasias Pulmonares , Humanos , Femenino , ARN Circular/genética , Neoplasias de la Mama/genética , Algoritmos , Envejecimiento , Biología Computacional/métodosRESUMEN
With a growing body of evidence establishing circular RNAs (circRNAs) are widely exploited in eukaryotic cells and have a significant contribution in the occurrence and development of many complex human diseases. Disease-associated circRNAs can serve as clinical diagnostic biomarkers and therapeutic targets, providing novel ideas for biopharmaceutical research. However, available computation methods for predicting circRNA-disease associations (CDAs) do not sufficiently consider the contextual information of biological network nodes, making their performance limited. In this work, we propose a multi-hop attention graph neural network-based approach MAGCDA to infer potential CDAs. Specifically, we first construct a multi-source attribute heterogeneous network of circRNAs and diseases, then use a multi-hop strategy of graph nodes to deeply aggregate node context information through attention diffusion, thus enhancing topological structure information and mining data hidden features, and finally use random forest to accurately infer potential CDAs. In the four gold standard data sets, MAGCDA achieved prediction accuracy of 92.58%, 91.42%, 83.46% and 91.12%, respectively. MAGCDA has also presented prominent achievements in ablation experiments and in comparisons with other models. Additionally, 18 and 17 potential circRNAs in top 20 predicted scores for MAGCDA prediction scores were confirmed in case studies of the complex diseases breast cancer and Almozheimer's disease, respectively. These results suggest that MAGCDA can be a practical tool to explore potential disease-associated circRNAs and provide a theoretical basis for disease diagnosis and treatment.
Asunto(s)
Neoplasias de la Mama , ARN Circular , Humanos , Femenino , ARN Circular/genética , Redes Neurales de la Computación , Biomarcadores , Biología Computacional/métodosRESUMEN
Recent developments in single-cell technology have enabled the exploration of cellular heterogeneity at an unprecedented level, providing invaluable insights into various fields, including medicine and disease research. Cell type annotation is an essential step in its omics research. The mainstream approach is to utilize well-annotated single-cell data to supervised learning for cell type annotation of new singlecell data. However, existing methods lack good generalization and robustness in cell annotation tasks, partially due to difficulties in dealing with technical differences between datasets, as well as not considering the heterogeneous associations of genes in regulatory mechanism levels. Here, we propose the scPML model, which utilizes various gene signaling pathway data to partition the genetic features of cells, thus characterizing different interaction maps between cells. Extensive experiments demonstrate that scPML performs better in cell type annotation and detection of unknown cell types from different species, platforms, and tissues.
Asunto(s)
Medicina , Análisis de Expresión Génica de una Sola Célula , Transducción de Señal , TecnologíaRESUMEN
MOTIVATION: Accumulating clinical evidence shows that circular RNA (circRNA) plays an important regulatory role in the occurrence and development of human diseases, which is expected to provide a new perspective for the diagnosis and treatment of related diseases. Using computational methods can provide high probability preselection for wet experiments to save resources. However, due to the lack of neighborhood structure in sparse biological networks, the model based on network embedding and graph embedding is difficult to achieve ideal results. RESULTS: In this paper, we propose BioDGW-CMI, which combines biological text mining and wavelet diffusion-based sparse network structure embedding to predict circRNA-miRNA interaction (CMI). In detail, BioDGW-CMI first uses the Bidirectional Encoder Representations from Transformers (BERT) for biological text mining to mine hidden features in RNA sequences, then constructs a CMI network, obtains the topological structure embedding of nodes in the network through heat wavelet diffusion patterns. Next, the Denoising autoencoder organically combines the structural features and Gaussian kernel similarity, finally, the feature is sent to lightGBM for training and prediction. BioDGW-CMI achieves the highest prediction performance in all three datasets in the field of CMI prediction. In the case study, all the 8 pairs of CMI based on circ-ITCH were successfully predicted. AVAILABILITY: The data and source code can be found at https://github.com/1axin/BioDGW-CMI-model.
RESUMEN
Recently, the role of competing endogenous RNAs in regulating gene expression through the interaction of microRNAs has been closely associated with the expression of circular RNAs (circRNAs) in various biological processes such as reproduction and apoptosis. While the number of confirmed circRNA-miRNA interactions (CMIs) continues to increase, the conventional in vitro approaches for discovery are expensive, labor intensive, and time consuming. Therefore, there is an urgent need for effective prediction of potential CMIs through appropriate data modeling and prediction based on known information. In this study, we proposed a novel model, called DeepCMI, that utilizes multi-source information on circRNA/miRNA to predict potential CMIs. Comprehensive evaluations on the CMI-9905 and CMI-9589 datasets demonstrated that DeepCMI successfully infers potential CMIs. Specifically, DeepCMI achieved AUC values of 90.54% and 94.8% on the CMI-9905 and CMI-9589 datasets, respectively. These results suggest that DeepCMI is an effective model for predicting potential CMIs and has the potential to significantly reduce the need for downstream in vitro studies. To facilitate the use of our trained model and data, we have constructed a computational platform, which is available at http://120.77.11.78/DeepCMI/. The source code and datasets used in this work are available at https://github.com/LiYuechao1998/DeepCMI.
RESUMEN
Circular RNA (circRNA) plays an important role in the diagnosis, treatment, and prognosis of human diseases. The discovery of potential circRNA-miRNA interactions (CMI) is of guiding significance for subsequent biological experiments. Limited by the small amount of experimentally supported data and high randomness, existing models are difficult to accomplish the CMI prediction task based on real cases. In this paper, we propose KS-CMI, a novel method for effectively accomplishing CMI prediction in real cases. KS-CMI enriches the 'behavior relationships' of molecules by constructing circRNA-miRNA-cancer (CMCI) networks and extracts the behavior relationship attribute of molecules based on balance theory. Next, the denoising autoencoder (DAE) is used to enhance the feature representation of molecules. Finally, the CatBoost classifier was used for prediction. KS-CMI achieved the most reliable prediction results in real cases and achieved competitive performance in all datasets in the CMI prediction.
RESUMEN
More and more evidence suggests that circRNA plays a vital role in generating and treating diseases by interacting with miRNA. Therefore, accurate prediction of potential circRNA-miRNA interaction (CMI) has become urgent. However, traditional wet experiments are time-consuming and costly, and the results will be affected by objective factors. In this paper, we propose a computational model BCMCMI, which combines three features to predict CMI. Specifically, BCMCMI utilizes the bidirectional encoding capability of the BERT algorithm to extract sequence features from the semantic information of circRNA and miRNA. Then, a heterogeneous network is constructed based on cosine similarity and known CMI information. The Metapath2vec is employed to conduct random walks following meta-paths in the network to capture topological features, including similarity features. Finally, potential CMIs are predicted using the XGBoost classifier. BCMCMI achieves superior results compared to other state-of-the-art models on two benchmark datasets for CMI prediction. We also utilize t-SNE to visually observe the distribution of the extracted features on a randomly selected dataset. The remarkable prediction results show that BCMCMI can serve as a valuable complement to the wet experiment process.