MicroRNAs and complex diseases: from experimental results to computational models

Briefings in Bioinformatics, Journal Year: 2017, Volume and Issue: 20(2), P. 515 - 539

Published: Sept. 15, 2017

Plenty of microRNAs (miRNAs) were discovered at a rapid pace in plants, green algae, viruses and animals. As one the most important components cell, miRNAs play growing role various essential biological processes. For recent few decades, amounts experimental methods computational models have been designed implemented to identify novel miRNA-disease associations. In this review, functions miRNAs, miRNA-target interactions, associations some publicly available miRNA-related databases discussed detail. Specially, considering fact that an increasing number experimentally confirmed, we selected five human diseases crucial disease-related provided corresponding introductions. Identifying has become goal biomedical research, which will accelerate understanding disease pathogenesis molecular level tools design for diagnosis, treatment prevention. Computational means association identification, could select promising pairs validation significantly reduce time cost experiments. Here, reviewed 20 state-of-the-art predicting from different perspectives. Finally, summarized four factors difficulties potential framework constructing powerful predict including feasible research schemas, future directions further development models.

Language: Английский

---

Circular RNAs and complex diseases: from experimental results to computational models

Briefings in Bioinformatics, Journal Year: 2021, Volume and Issue: 22(6)

Published: July 5, 2021

Abstract Circular RNAs (circRNAs) are a class of single-stranded, covalently closed RNA molecules with variety biological functions. Studies have shown that circRNAs involved in processes and play an important role the development various complex diseases, so identification circRNA-disease associations would contribute to diagnosis treatment diseases. In this review, we summarize discovery, classifications functions introduce four diseases associated circRNAs. Then, list some significant publicly accessible databases containing comprehensive annotation resources experimentally validated associations. Next, state-of-the-art computational models for predicting novel divide them into two categories, namely network algorithm-based machine learning-based models. Subsequently, several evaluation methods prediction performance these summarized. Finally, analyze advantages disadvantages different types provide suggestions promote association from perspective construction new accumulation circRNA-related data.

Language: Английский

---

GMNN2CD: identification of circRNA–disease associations based on variational inference and graph Markov neural networks

Bioinformatics, Journal Year: 2022, Volume and Issue: 38(8), P. 2246 - 2253

Published: Feb. 9, 2022

Abstract Motivation With the analysis of characteristic and function circular RNAs (circRNAs), people have realized that they play a critical role in diseases. Exploring relationship between circRNAs diseases is far-reaching significance for searching etiopathogenesis treatment Nevertheless, it inefficient to learn new associations only through biotechnology. Results Consequently, we present computational method, GMNN2CD, which employs graph Markov neural network (GMNN) algorithm predict unknown circRNA–disease associations. First, used verified associations, calculate semantic similarity Gaussian interactive profile kernel (GIPs) disease GIPs circRNA then merge them form unified descriptor. After that, GMNN2CD uses fusion feature variational map autoencoder deep features label propagation propagate tags based on known Based inference, GMNN alternate training enhances ability obtain high-efficiency high-dimensional from low-dimensional representations. Finally, 5-fold cross-validation five benchmark datasets shows superior state-of-the-art methods. Furthermore, case studies shown can detect potential Availability implementation The source code data are available at https://github.com/nmt315320/GMNN2CD.git.

Language: Английский

---

BioSeq-Diabolo: Biological sequence similarity analysis using Diabolo

PLoS Computational Biology, Journal Year: 2023, Volume and Issue: 19(6), P. e1011214 - e1011214

Published: June 20, 2023

As the key for biological sequence structure and function prediction, disease diagnosis treatment, similarity analysis has attracted more attentions. However, exiting computational methods failed to accurately analyse similarities because of various data types (DNA, RNA, protein, disease, etc) their low (remote homology). Therefore, new concepts techniques are desired solve this challenging problem. Biological sequences RNA protein sequences) can be considered as sentences "the book life", language semantics (BLS). In study, we seeking derived from natural processing (NLP) comprehensively similarities. 27 NLP were introduced similarities, bringing analysis. Experimental results show that these able facilitate development remote homology detection, circRNA-disease associations identification annotation, achieving better performance than other state-of-the-art predictors in related fields. Based on methods, a platform called BioSeq-Diabolo been constructed, which is named after popular traditional sport China. The users only need input embeddings data. will intelligently identify task, then based semantics. integrate different supervised manner by using Learning Rank (LTR), constructed evaluated analysed so recommend best users. web server stand-alone package accessed at http://bliulab.net/BioSeq-Diabolo/server/.

Language: Английский

---

iCircDA-MF: identification of circRNA-disease associations based on matrix factorization

Briefings in Bioinformatics, Journal Year: 2019, Volume and Issue: 21(4), P. 1356 - 1367

Published: April 19, 2019

Abstract Circular RNAs (circRNAs) are a group of novel discovered non-coding with closed-loop structure, which play critical roles in various biological processes. Identifying associations between circRNAs and diseases is for exploring the complex disease mechanism facilitating disease-targeted therapy. Although several computational predictors have been proposed, their performance still limited. In this study, method called iCircDA-MF proposed. Because circRNA-disease experimental validation very limited, potential calculated based on circRNA similarity extracted from semantic information known circRNA-gene, gene-disease circRNA-disease. The interaction profiles then updated by neighbour so as to correct false negative associations. Finally, matrix factorization performed predict results widely used benchmark dataset showed that outperforms other state-of-the-art can identify new effectively.

Language: Английский

---

An efficient approach based on multi-sources information to predict circRNA–disease associations using deep convolutional neural network

Bioinformatics, Journal Year: 2019, Volume and Issue: 36(13), P. 4038 - 4046

Published: Nov. 21, 2019

Emerging evidence indicates that circular RNA (circRNA) plays a crucial role in human disease. Using circRNA as biomarker gives rise to new perspective regarding our diagnosing of diseases and understanding disease pathogenesis. However, detection circRNA-disease associations by biological experiments alone is often blind, limited small scale, high cost time consuming. Therefore, there an urgent need for reliable computational methods rapidly infer the potential on large scale provide most promising candidates experiments.In this article, we propose efficient method based multi-source information combined with deep convolutional neural network (CNN) predict associations. The first fuses including semantic similarity, Gaussian interaction profile kernel similarity then extracts its hidden feature through CNN finally sends them extreme learning machine classifier prediction. 5-fold cross-validation results show proposed achieves 87.21% prediction accuracy 88.50% sensitivity at area under curve 86.67% CIRCR2Disease dataset. In comparison state-of-the-art SVM other extraction same dataset, model best results. addition, also obtained experimental support searching published literature. As result, 7 top 15 pairs highest scores were confirmed These demonstrate suitable predicting can experiments.The source code datasets explored work are available https://github.com/look0012/circRNA-Disease-association.Supplementary data Bioinformatics online.

Language: Английский

---

GCNCDA: A new method for predicting circRNA-disease associations based on Graph Convolutional Network Algorithm

PLoS Computational Biology, Journal Year: 2020, Volume and Issue: 16(5), P. e1007568 - e1007568

Published: May 20, 2020

Numerous evidences indicate that Circular RNAs (circRNAs) are widely involved in the occurrence and development of diseases. Identifying association between circRNAs diseases plays a crucial role exploring pathogenesis complex improving diagnosis treatment However, due to mechanisms diseases, it is expensive time-consuming discover new circRNA-disease associations by biological experiment. Therefore, there increasingly urgent need for utilizing computational methods predict novel associations. In this study, we propose method called GCNCDA based on deep learning Fast with Graph Convolutional Networks (FastGCN) algorithm potential disease-associated circRNAs. Specifically, first forms unified descriptor fusing disease semantic similarity information, circRNA Gaussian Interaction Profile (GIP) kernel information known The FastGCN then used objectively extract high-level features contained fusion descriptor. Finally, accurately predicted Forest Penalizing Attributes (Forest PA) classifier. 5-fold cross-validation experiment achieved 91.2% accuracy 92.78% sensitivity at AUC 90.90% circR2Disease benchmark dataset. comparison different classifier models, feature extraction models other state-of-the-art methods, shows strong competitiveness. Furthermore, conducted case study experiments including breast cancer, glioma colorectal cancer. results showed 16, 15 17 top 20 candidate highest prediction scores were respectively confirmed relevant literature databases. These suggest can effectively provide highly credible candidates experiments.

Language: Английский

---

Integrating Bipartite Network Projection and KATZ Measure to Identify Novel CircRNA-Disease Associations

IEEE Transactions on NanoBioscience, Journal Year: 2019, Volume and Issue: 18(4), P. 578 - 584

Published: June 12, 2019

Accumulating biological experiments have shown that circRNAs are closely related to the occurrence and development of many complex human diseases. During recent years, associations circRNA with disease caused more researchers pay attention analyze their correlation mechanisms. However, experimental methods for determining a particular still expensive, difficult, time consuming. Moreover, available databases circRNA-disease correlations only recently been updated, few computational constructed predict potential correlations. Taking into account limitations studies, we develop novel method, named IBNPKATZ, predicting associations, which integrates bipartite network projection algorithm KATZ measure. This model is based on known combining similarity similarity. Specifically, derived from average semantic Gaussian interaction profile (GIP) kernel circRNA. Similarly, mean GIP disease. Furthermore, it semi-supervised does not require negative samples. Finally, IBNPKATZ achieves reliable AUC 0.9352 in leave-one-out cross validation, case studies show predicted by our method can be successfully demonstrated relevant experiments. The expected useful biomedical research tool associations.

Language: Английский

---

Deep Matrix Factorization Improves Prediction of Human CircRNA-Disease Associations

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2020, Volume and Issue: 25(3), P. 891 - 899

Published: June 3, 2020

In recent years, more and evidence indicates that circular RNAs (circRNAs) with covalently closed loop play various roles in biological processes. Dysregulation mutation of circRNAs may be implicated diseases. Due to its stable structure resistance degradation, provide great potential diagnostic biomarkers. Therefore, predicting circRNA-disease associations is helpful disease diagnosis. However, there are few experimentally validated between Although several computational methods have been proposed, precisely representing underlying features grasping the complex structures data still challenging. this paper, we design a new method, called DMFCDA (Deep Matrix Factorization CircRNA-Disease Association), infer associations. takes both explicit implicit feedback into account. Then, it uses projection layer automatically learn latent representations With multi-layer neural networks, can model non-linear grasp data. We assess performance using leave-one cross-validation 5-fold on two datasets. Computational results show efficiently infers according AUC values, percentage retrieved top ranks, statistical comparison. also conduct case studies evaluate DMFCDA. All provides accurate predictions.

Language: Английский

---

KGANCDA: predicting circRNA-disease associations based on knowledge graph attention network

Briefings in Bioinformatics, Journal Year: 2021, Volume and Issue: 23(1)

Published: Oct. 27, 2021

Abstract Increasing evidences have proved that circRNA plays a significant role in the development of many diseases. In addition, researches shown can be considered as potential biomarker for clinical diagnosis and treatment disease. Some computational methods been proposed to predict circRNA-disease associations. However, performance these is limited sparsity low-order interaction information. this paper, we propose new method (KGANCDA) associations based on knowledge graph attention network. The graphs are constructed by collecting multiple relationship data among circRNA, disease, miRNA lncRNA. Then, network designed obtain embeddings each entity distinguishing importance information from neighbors. Besides neighbor information, it also capture high-order multisource associations, which alleviates problem sparsity. Finally, multilayer perceptron applied affinity score experiment results show KGANCDA outperforms than other state-of-the-art 5-fold cross validation. Furthermore, case study demonstrates an effective tool

Language: Английский

---