1 - 27 of 27 results

WBSMDA / Within and Between Score for MiRNA-Disease Association prediction

Includes different types of information. WBSMDA predicts potential miRNAs associated with various complex diseases. It integrates miRNA functional similarity network, miRNA-disease associations, disease semantic similarity network, or Gaussian interaction profile kernel similarity network. This allows users to uncover the potential disease-miRNA associations. However, this tool is applicable for diseases without any known related miRNAs.

SDMMDA / Super-Disease and MiRNA for potential MiRNA-Disease Association prediction

Allows users to predict potential miRNA-disease associations. SDMMDA combines known associations, disease semantic similarity, miRNA functional similarity, and Gaussian interaction profile kernel similarity for diseases and miRNAs. It also can be used for detecting new diseases without any known associated miRNAs or new miRNAs without any known associated diseases. It obtained areas under the curves (AUCs) of 0.9032, 0.8323, 8970 based on leave-one-out cross validation and local leave-one-out cross validation, and 5-fold cross validation.

DRMDA / deep representations-based miRNA-disease association

Provides an efficient computational model that offers deep representations-based miRNA–disease association prediction. DRMDA is an algorithm that calculates the score of each miRNA–disease sample by analysing known miRNA–disease interactions, disease semantic similarity and miRNA functional similarity. Then, potential associations were selected according to the score. It finds out deep representation under the surface of disease semantic similarity.

RLSMDA / Regularized Least Squares for MiRNA-Disease Association

Predicts novel miRNAs for diseases which do not have any known related miRNAs. RLSMDA is able to reconstruct the missing associations for all the diseases simultaneously. It integrates disease-disease semantic similarity information, miRNA-miRNA functional similarity information, and known human miRNA-disease associations on a large scale. This tool can obtain negative disease-miRNA associations samples in practical problems.

IRWRMDA / Improved Random Walk with Restart for MiRNA-Disease Association prediction

Prioritizes candidate miRNA-disease pairs for further biological experiment validation. IRWRMDA is a computational model developed to infer potential associations between miRNAs and investigated diseases. This method achieves reliable prediction performance with under the curve in leave one out cross validation framework. It can also provide data sources such as miRNA expression data, disease-related miRNA-environmental factor interactions, and disease-related miRNA-target interactions to enhance the robustness of SPYSMDA.

NARRMDA / Negative-Aware and rating-based Recommendation algorithm for miRNA–Disease Association prediction

Allows prediction of potential miRNA–disease associations. NARRMDA is able to score and rank candidate miRNAs. It is based on a combination of a negative-aware algorithm and a rating-based recommendation algorithm. This tool can be useful for miRNA–disease association prediction and can be valuable for users interested in human disease diagnosis, treatment, prevention and prognosis.

NCPMDA / Network Consistency Projection for miRNA-Disease Associations

Allows users to predict potential miRNA-disease associations. NCPMDA intends to discover the potential associations by calculating the score of each miRNA-disease pair using the miRNA functional similarity network, the disease semantic similarity network, the known miRNA-disease associations, and the miRNA family information. It does not require negative samples and can also confirm the presence of miRNAs in isolated diseases.


A web-based tool for inferring novel miRNA-disease associations based on a complex heterogeneous network (CHN) involving 402 miRNAs and 5080 diseases. CHNmiRD integrates multiple genomic and phenotype data, including protein-protein interaction data, gene ontology data, experimentally verified miRNA-target relationships, disease phenotype information and known miRNA-disease connections. In particular, CHNmiRD displays excellent performance for diseases without any known related miRNAs. Given a disease, CHNmiRD provides a candidate miRNA list and assigns each miRNA a probability score which reflects the correlation between the miRNA and the disease.

DMPred / Disease-related MiRNAs Prediction

Predicts disease-related miRNAs. DMPred is a method based on non-negative matrix factorization with sparseness constraints. This resource integrates multiple kinds of information within the miRNA-disease bilayer network seamless, which exploits the consensus relationship between them completely. It takes the correlation between the candidates of various diseases into account and predicts their respective candidates for all diseases at the same time.

KBMF-MDI / Kernelized Bayesian matrix factorization with multiple-kernel learning for miRNA-disease association inference

Assists users to study the associations between miRNAs and diseases based on their similarities. KBMF-MDI uses sequence and function information of miRNAs to estimate similarity in miRNAs. This algorithm can be used to deduce potential miRNA-disease associations thanks to integration of several types of data sources. This method can be useful for researchers that desire to find and predict unknown miRNA-disease associations.


Assists in identifying a set of ranked micro-RNA (miRNAs) playing a role in diseases of a specific profile. mirfluence is an online program that can detect key influential miRNAs in the categories of Gastrointestinal cancers, Leukemia, Brain cancers and Endocrine cancers. Users can display the influential miRNAs in the miRNA-miRNA networks of existing categories and diseases. It can also visualize the miRNAs and the topological placement of these miRNAs in the disease network.

LRSSLMDA / Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction

Infers potential miRNA-disease associations. LRSSLMDA is a computational model for predicting disease-miRNA associations. It adopts sparse subspace learning with Laplacian regularization on the known miRNA-disease association network and the informative feature profiles extracted from the integrated miRNA/disease similarity networks. It was developed to make reliable predictions and guide future experimental studies on miRNA-disease associations.

PBMDA / Path-Based MiRNA-Disease Association

Constructs a heterogeneous graph consisting of three interlinked sub-graphs and further adopted depth-first search algorithm to infer potential miRNA-disease associations. PBMDA is a prediction model that could serve as a powerful computational tool to accelerate the identification of disease-miRNA associations. Integrating different types of heterogeneous biological datasets allows that PBMDA could be applied to the new diseases with no known associated miRNAs and the new miRNAs with no known associated diseases.