Exploring the relationship between circular RNA (circRNA) and disease is beneficial for revealing mechanisms of pathogenesis. However, a blind search all possible associations circRNAs diseases through biological experiments time-consuming. Although some prediction methods have been proposed, they still limitations. In this study, novel computational framework, called GATCL2CD, proposed to forecast unknown circRNA-disease (CDAs). First, we calculate Gaussian interactive profile kernel (GIP)...

Abstract Circular RNAs (circRNAs) are a class of structurally stable endogenous noncoding RNA molecules. Increasing studies indicate that circRNAs play vital roles in human diseases. However, validating disease-related vivo is costly and time-consuming. A reliable effective computational method to identify circRNA–disease associations deserves further studies. In this study, we propose called RNMFLP combines robust nonnegative matrix factorization (RNMF) label propagation algorithm (LP)...

Circular RNA (circRNA) is closely associated with human diseases. Accordingly, identifying the associations between diseases and circRNA can help in disease prevention, diagnosis treatment. Traditional methods are time consuming laborious. Meanwhile, computational models effectively predict potential circRNA-disease (CDAs), but restricted by limited data, resulting data high dimension imbalance. In this study, we propose a model based on automatically selected meta-path contrastive learning,...

Predicting potential microbe-drug associations (MDA) can help study pathogenesis, expedite pharmaceutical innovation, and enhance targeted therapeutics. Given the time labor intensity of traditional biological experiments, an increasing number computational approaches are being employed to predict MDA. The method based on graph embedding is one most widely used. However, these methods only consider node or structure information in isolation, which leads restricted predictive accuracy. In...

Circular RNAs (CircRNAs) play critical roles in gene expression regulation and disease development. Understanding the mechanism of CircRNAs formation can help reveal role various biological processes mentioned above. Back-splicing is important for formation. sites prediction helps uncover mysteries Several methods were proposed back-splicing or circRNA-realted tasks. Model performance was constrained by poor feature learning using ability.In this study, CircCNN to predict pre-mRNA sites....

Cuckoo search (CS) is a new meta-heuristic optimization algorithm that based on the obligate brood parasitic behavior of some cuckoo species in combination with Lévy flight birds and fruit flies. It has been found to be efficient solving global problems. An application CS presented solve visual tracking problem. The relationship between comparatively studied parameters' sensitivity adjustment system are experimentally studied. To demonstrate ability CS-based tracker, comparative study...

New technologies and advanced methods are the important basis for continuous development of laboratory medicine. Although labeling analysis has become an research method in medicine, label-free showed unique advantages, such as high sensitivity, small working volumes, low damage to analytes easy on-chip integrations. Label-free mainly based on molecular biophysical properties without conjugated labels, which can largely avoid false positives provide more reliable reproducible detection...

Growing evidence shows that microbes in human body and surface play critical roles the development of many diseases. Predicting underlying associations between diseases is essential for deeply understanding pathogenesis However, biological experiments to find relationship usually laborious time-consuming, which presents need effective computational tools. In this study, we propose a model node-information-based Link Propagation Human Microbe-Disease Association prediction (LPHMDA) prioritize...

The advent of single-cell RNA sequencing (scRNA-seq) technology has revolutionized gene expression studies at the level. However, presence technical noise and data sparsity in scRNA-seq often undermines accuracy subsequent analyses. Existing methods for denoising imputing rely on stringent assumptions about distribution, limiting effectiveness recovery. In this study, we propose scDMAE model recovery data. First, fuses features topological to discern primary patterns genes cells. Then, an...

Biclustering of the gene expressing data is an important task in bioinformatics. By clustering obtained under different experimental conditions, function and regulatory elements sequence can be analyzed recognized. A parallel biclustering algorithm for presented. Based on anti-monotones property quality sets with their sizes, starts from containing all 2*2 submatrices matrix, gets final biclusters by gradually adding columns rows sets. Experimental results show that our has superiority over...

In this paper, we investigate the multi-attribute group decision making (MAGDM) problems in which attribute preference values take form of interval-valued intuitionistic uncertain linguistic number (IVIULN) and experts have different priority level. To aggregate information given by all makers, some new prioritized aggregation operators are proposed at first, such as weighted average (IVIULPWA) operator geometric (IVIULPWG) operator. Then desirable properties studied, idempotency...

Biclustering the gene expressing data is an important task in bioinformatics. A parallel biclustering algorithm for presented. The starts from sets containing pair of rows and columns matrix, gets biclusters by gradually adding on sets. pruning technique also proposed to reduce computing time. Experimental results show that our has superiority other similar algorithms terms processing speed quality clustering.

A biclustering algorithm for gene expressing data is presented. Based on the anti-monotones property of quality sets with their sizes, can get final biclusters by gradually adding columns and rows sets. Experimental results show that our has higher processing speed clustering than other similar algorithms.