FMSM: a novel computational model for predicting potential miRNA biomarkers for various human diseases.
Ontology highlight
ABSTRACT: Background
MicroRNA (miRNA) plays a key role in regulation mechanism of human biological processes, including the development of disease and disorder. It is necessary to identify potential miRNA biomarkers for various human diseases. Computational prediction model is expected to accelerate the process of identification.Results
Considering the limitations of previously proposed models, we present a novel computational model called FMSM. It infers latent miRNA biomarkers involved in the mechanism of various diseases based on the known miRNA-disease association network, miRNA expression similarity, disease semantic similarity and Gaussian interaction profile kernel similarity. FMSM achieves reliable prediction performance in 5-fold and leave-one-out cross validations with area under ROC curve (AUC) values of 0.9629+/- 0.0127 and 0.9433, respectively, which outperforms the state-of-the-art competitors and classical algorithms. In addition, 19 of top 25 predicted miRNAs have been validated to have associations with Colonic Neoplasms in case study.Conclusions
A factored miRNA similarity based model and miRNA expression similarity substantially contribute to the well-performing prediction. The list of the predicted most latent miRNA biomarkers of various human diseases is publicized. It is anticipated that FMSM could serve as a useful tool guiding the future experimental validation for those promising miRNA biomarker candidates.
SUBMITTER: Sun Y
PROVIDER: S-EPMC6311922 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundA growing proportion of research has proved that microRNAs (miRNAs) can regulate the function of target genes and have close relations with various diseases. Developing computational methods to exploit more potential miRNA-disease associations can provide clues for further functional research.ResultsInspired by the work of predecessors, we discover that the noise hiding in the data can affect the prediction performance and then propose an anti-noise algorithm (ANMDA) to predict potential miRNA-disease associations. Firstly, we calculate the similarity in miRNAs and diseases to construct features and obtain positive samples according to the Human MicroRNA Disease Database version 2.0 (HMDD v2.0). Then, we apply k-means on the undetected miRNA-disease associations and sample the negative examples equally from the k-cluster. Further, we construct several data subsets through sampling with replacement to feed on the light gradient boosting machine (LightGBM) method. Finally, the voting method is applied to predict potential miRNA-disease relationships. As a result, ANMDA can achieve an area under the receiver operating characteristic curve (AUROC) of 0.9373 ± 0.0005 in five-fold cross-validation, which is superior to several published methods. In addition, we analyze the predicted miRNA-disease associations with high probability and compare them with the data in HMDD v3.0 in the case study. The results show ANMDA is a novel and practical algorithm that can be used to infer potential miRNA-disease associations.ConclusionThe results indicate the noise hiding in the data has an obvious impact on predicting potential miRNA-disease associations. We believe ANMDA can achieve better results from this task with more methods used in dealing with the data noise.
| S-EPMC8254275 | biostudies-literature
Project description:BackgroundA large body of evidence shows that miRNA regulates the expression of its target genes at post-transcriptional level and the dysregulation of miRNA is related to many complex human diseases. Accurately discovering disease-related miRNAs is conductive to the exploring of the pathogenesis and treatment of diseases. However, because of the limitation of time-consuming and expensive experimental methods, predicting miRNA-disease associations by computational models has become a more economical and effective mean.ResultsInspired by the work of predecessors, we proposed an improved computational model based on random forest (RF) for identifying miRNA-disease associations (IRFMDA). First, the integrated similarity of diseases and the integrated similarity of miRNAs were calculated by combining the semantic similarity and Gaussian interaction profile kernel (GIPK) similarity of diseases, the functional similarity and GIPK similarity of miRNAs, respectively. Then, the integrated similarity of diseases and the integrated similarity of miRNAs were combined to represent each miRNA-disease relationship pair. Next, the miRNA-disease relationship pairs contained in the HMDD (v2.0) database were considered positive samples, and the randomly constructed miRNA-disease relationship pairs not included in HMDD (v2.0) were considered negative samples. Next, the feature selection based on the variable importance score of RF was performed to choose more useful features to represent samples to optimize the model's ability of inferring miRNA-disease associations. Finally, a RF regression model was trained on reduced sample space to score the unknown miRNA-disease associations. The AUCs of IRFMDA under local leave-one-out cross-validation (LOOCV), global LOOCV and 5-fold cross-validation achieved 0.8728, 0.9398 and 0.9363, which were better than several excellent models for predicting miRNA-disease associations. Moreover, case studies on oesophageal cancer, lymphoma and lung cancer showed that 94 (oesophageal cancer), 98 (lymphoma) and 100 (lung cancer) of the top 100 disease-associated miRNAs predicted by IRFMDA were supported by the experimental data in the dbDEMC (v2.0) database.ConclusionsCross-validation and case studies demonstrated that IRFMDA is an excellent miRNA-disease association prediction model, and can provide guidance and help for experimental studies on the regulatory mechanism of miRNAs in complex human diseases in the future.
| S-EPMC6889672 | biostudies-literature
Project description:In recent years, more and more studies have shown that miRNAs can affect a variety of biological processes. It is important for disease prevention, treatment, diagnosis, and prognosis to study the relationships between human diseases and miRNAs. However, traditional experimental methods are time-consuming and labour-intensive. Hence, in this paper, a novel neighborhood-based computational model called NBMDA is proposed for predicting potential miRNA-disease associations. Due to the fact that known miRNA-disease associations are very rare and many diseases (or miRNAs) are associated with only one or a few miRNAs (or diseases), in NBMDA, the K-nearest neighbor (KNN) method is utilized as a recommendation algorithm based on known miRNA-disease associations, miRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for miRNAs and diseases to improve its prediction accuracy. And simulation results demonstrate that NBMDA can effectively infer miRNA-disease associations with higher accuracy compared with previous state-of-the-art methods. Moreover, independent case studies of esophageal neoplasms, breast neoplasms and colon neoplasms are further implemented, and as a result, there are 47, 48, and 48 out of the top 50 predicted miRNAs having been successfully confirmed by the previously published literatures, which also indicates that NBMDA can be utilized as a powerful tool to study the relationships between miRNAs and diseases.
| S-EPMC6360053 | biostudies-literature
Project description:BackgroundMultiple myeloma is a cancer which has a high occurrence rate and causes great injury to people worldwide. In recent years, many studies reported the effects of miRNA on the appearance of multiple myeloma. However, due to the differences of samples and sequencing platforms, a large number of inconsistent results have been generated among these studies, which limited the cure of multiple myeloma at the miRNA level.MethodsWe performed meta-analyses to identify the key miRNA biomarkers which could be applied on the treatment of multiple myeloma. The key miRNAs were determined by overlap comparisons of seven datasets in multiple myeloma. Then, the target genes for key miRNAs were predicted by the software TargetScan. Additionally, functional enrichments and binding TFs were investigated by DAVID database and Tfacts database, respectively.ResultsFirstly, comparing the normal tissues, 13 miRNAs were differently expressed miRNAs (DEMs) for at least three datasets. They were considered as key miRNAs, with 12 up-regulated (hsa-miR-106b, hsa-miR-125b, hsa-miR-130b, hsa-miR-138, hsa-miR-15b, hsa-miR-181a, hsa-miR-183, hsa-miR-191, hsa-miR-19a, hsa-miR-20a, hsa-miR-221 and hsa-miR-25) and one down-regulated (hsa-miR-223). Secondly, functional enrichment analyses indicated that target genes of the upregulated miRNAs were mainly transcript factors and enriched in transcription regulation. Besides, these genes were enriched in multiple pathways: the cancer signal pathway, insulin signal metabolic pathway, cell binding molecules, melanin generation, long-term regression and P53 signaling pathway. However, no significant enrichment was found for target genes of the down-regulated genes. Due to the distinct regulation function, four miRNAs (hsa-miR-19a has-miR-221 has-miR25 and has-miR223) were ascertained as the potential prognostic and diagnostic markers in MM. Thirdly, transcript factors analysis unveiled that there were 148 TFs and 60 TFs which bind target genes of the up-regulated miRNAs and target genes of the down-regulated miRNAs, respectively. They respectively generated 652 and 139 reactions of TFs and target genes. Additionally, 50 (31.6%) TFs were shared, while higher specificity was found in TFs of target genes for the upregulated miRNAs.DiscussionsTogether, our findings provided the key miRNAs which affected occurrence of multiple myeloma and regulation function of these miRNAs. It is valuable for the prognosis and diagnosis of multiple myeloma.
| S-EPMC5289111 | biostudies-literature
Project description:Motivation:Increasing studies have demonstrated that many human complex diseases are associated with not only microRNAs, but also long-noncoding RNAs (lncRNAs). LncRNAs and microRNA play significant roles in various biological processes. Therefore, developing effective computational models for predicting novel associations between diseases and lncRNA-miRNA pairs (LMPairs) will be beneficial to not only the understanding of disease mechanisms at lncRNA-miRNA level and the detection of disease biomarkers for disease diagnosis, treatment, prognosis, and prevention, but also the understanding of interactions between diseases and LMPairs at disease level. Results:It is well known that genes with similar functions are often associated with similar diseases. In this article, a novel model named PADLMP for predicting associations between diseases and LMPairs is proposed. In this model, a Disease-LncRNA-miRNA (DLM) tripartite network was designed firstly by integrating the lncRNA-disease association network and miRNA-disease association network; then we constructed the disease-LMPairs bipartite association network based on the DLM network and lncRNA-miRNA association network; finally, we predicted potential associations between diseases and LMPairs based on the newly constructed disease-LMPair network. Simulation results show that PADLMP can achieve AUCs of 0.9318, 0.9090 ± 0.0264, and 0.8950 ± 0.0027 in the LOOCV, 2-fold, and 5-fold cross validation framework, respectively, which demonstrate the reliable prediction performance of PADLMP.
| S-EPMC5960578 | biostudies-literature
Project description:Biomarkers are of tremendous importance for the prediction, diagnosis, and observation of the therapeutic success of common complex multifactorial metabolic diseases, such as type II diabetes and obesity. However, the predictive power of the traditional biomarkers used (eg, plasma metabolites and cytokines, body parameters) is apparently not sufficient for reliable monitoring of stage-dependent pathogenesis starting with the healthy state via its initiation and development to the established disease and further progression to late clinical outcomes. Moreover, the elucidation of putative considerable differences in the underlying pathogenetic pathways (eg, related to cellular/tissue origin, epigenetic and environmental effects) within the patient population and, consequently, the differentiation between individual options for disease prevention and therapy - hallmarks of personalized medicine - plays only a minor role in the traditional biomarker concept of metabolic diseases. In contrast, multidimensional and interdependent patterns of genetic, epigenetic, and phenotypic markers presumably will add a novel quality to predictive values, provided they can be followed routinely along the complete individual disease pathway with sufficient precision. These requirements may be fulfilled by small membrane vesicles, which are so-called exosomes and microvesicles (EMVs) that are released via two distinct molecular mechanisms from a wide variety of tissue and blood cells into the circulation in response to normal and stress/pathogenic conditions and are equipped with a multitude of transmembrane, soluble and glycosylphosphatidylinositol-anchored proteins, mRNAs, and microRNAs. Based on the currently available data, EMVs seem to reflect the diverse functional and dysfunctional states of the releasing cells and tissues along the complete individual pathogenetic pathways underlying metabolic diseases. A critical step in further validation of EMVs as biomarkers will rely on the identification of unequivocal correlations between critical disease states and specific EMV signatures, which in future may be determined in rapid and convenient fashion using nanoparticle-driven biosensors.
| S-EPMC3422911 | biostudies-literature
Project description:We have developed a detailed mathematical model for Ca handling and ionic currents in the human ventricular myocyte. Our aims were to: (1) simulate basic excitation-contraction coupling phenomena; (2) use realistic repolarizing K current densities; (3) reach steady-state. The model relies on the framework of the rabbit myocyte model previously developed by our group, with subsarcolemmal and junctional compartments where ion channels sense higher [Ca] vs. bulk cytosol. Ion channels and transporters have been modeled on the basis of the most recent experimental data from human ventricular myocytes. Rapidly and slowly inactivating components of I(to) have been formulated to differentiate between endocardial and epicardial myocytes. Transmural gradients of Ca handling proteins and Na pump were also simulated. The model has been validated against a wide set of experimental data including action potential duration (APD) adaptation and restitution, frequency-dependent increase in Ca transient peak and [Na](i). Interestingly, Na accumulation at fast heart rate is a major determinant of APD shortening, via outward shifts in Na pump and Na-Ca exchange currents. We investigated the effects of blocking K currents on APD and repolarization reserve: I(Ks) block does not affect the former and slightly reduces the latter; I(K1) blockade modestly increases APD and more strongly reduces repolarization reserve; I(Kr) blockers significantly prolong APD, an effect exacerbated as pacing frequency is decreased, in good agreement with experimental results in human myocytes. We conclude that this model provides a useful framework to explore excitation-contraction coupling mechanisms and repolarization abnormalities at the single myocyte level.
| S-EPMC2813400 | biostudies-literature
Project description:MicroRNAs (miRNAs) play important roles in the occurrence and development of diseases. However, it is still challenging to identify the effective miRNA biomarkers for improving the disease diagnosis and prognosis. In this study, we proposed the miRNA data analysis method based on multi-view miRNA networks and reinforcement learning, miRMarker, to define the potential miRNA disease biomarkers. miRMarker constructs the cooperative regulation network and functional similarity network based on the expression data and known miRNA-disease relations, respectively. The cooperative regulation of miRNAs was evaluated by measuring the changes of relative expression. Natural language processing was introduced for calculating the miRNA functional similarity. Then, miRMarker integrates the multi-view miRNA networks and defines the informative miRNA modules through a reinforcement learning strategy. We compared miRMarker with eight efficient data analysis methods on nine transcriptomics datasets to show its superiority in disease sample discrimination. The comparison results suggested that miRMarker outperformed other data analysis methods in receiver operating characteristic analysis. Furthermore, the defined miRNA modules of miRMarker on colorectal cancer data not only show the excellent performance of cancer sample discrimination but also play significant roles in the cancer-related pathway disturbances. The experimental results indicate that miRMarker can build the robust miRNA interaction network by integrating the multi-view networks. Besides, exploring the miRNA interaction network using reinforcement learning favors defining the important miRNA modules. In summary, miRMarker can be a hopeful tool in biomarker identification for human diseases.
| S-EPMC10753537 | biostudies-literature
Project description:Multiple sclerosis (MS) is a debilitating autoimmune disease affecting over 2.3 million people worldwide, and it is characterized by inflammation and demyelination of nerve cells. The currently available biomarkers for the diagnosis and management of MS have inherent limitations, therefore, additional new biomarkers are needed. We studied the microRNA (miRNA) profile of splenocytes of mice having experimental autoimmune encephalomyelitis (EAE), a model of human MS. A miRNA-microarray analysis revealed increased expression of nine miRNAs (let-7e, miR-23b, miR-31, miR-99b, miR-125a, miR-146b, miR-155, miR-193b, and miR-221) following EAE development. Interestingly, serum levels of miR-99b, miR-125a, and miR-146b were significantly higher in EAE mice compared to normal mice. Bioinformatics analysis revealed the experimentally validated as well as predicted gene targets of specific miRNAs that are important for disease progression in MS. Specifically, we observed inverse correlation in the levels of miR-99b versus LIF, and between miR-125a versus BDNF and LIF. Our results suggest that above-mentioned miRNAs may play a crucial role in the pathogenesis of MS, and that miR-99b, miR-125a, and miR-146b in particular may serve as useful biomarkers for disease activity.
| S-EPMC6321564 | biostudies-literature
Project description:BackgroundAccumulated evidence shows that the abnormal regulation of long non-coding RNA (lncRNA) is associated with various human diseases. Accurately identifying disease-associated lncRNAs is helpful to study the mechanism of lncRNAs in diseases and explore new therapies of diseases. Many lncRNA-disease association (LDA) prediction models have been implemented by integrating multiple kinds of data resources. However, most of the existing models ignore the interference of noisy and redundancy information among these data resources.ResultsTo improve the ability of LDA prediction models, we implemented a random forest and feature selection based LDA prediction model (RFLDA in short). First, the RFLDA integrates the experiment-supported miRNA-disease associations (MDAs) and LDAs, the disease semantic similarity (DSS), the lncRNA functional similarity (LFS) and the lncRNA-miRNA interactions (LMI) as input features. Then, the RFLDA chooses the most useful features to train prediction model by feature selection based on the random forest variable importance score that takes into account not only the effect of individual feature on prediction results but also the joint effects of multiple features on prediction results. Finally, a random forest regression model is trained to score potential lncRNA-disease associations. In terms of the area under the receiver operating characteristic curve (AUC) of 0.976 and the area under the precision-recall curve (AUPR) of 0.779 under 5-fold cross-validation, the performance of the RFLDA is better than several state-of-the-art LDA prediction models. Moreover, case studies on three cancers demonstrate that 43 of the 45 lncRNAs predicted by the RFLDA are validated by experimental data, and the other two predicted lncRNAs are supported by other LDA prediction models.ConclusionsCross-validation and case studies indicate that the RFLDA has excellent ability to identify potential disease-associated lncRNAs.
| S-EPMC7099795 | biostudies-literature