MicroRNA-disease association detection software tools | Non-coding RNA data analysis
In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one of pathogenetic factors, the molecular mechanisms underlying human complex diseases still have not been completely understood from the perspective of miRNA. Predicting potential miRNA-disease associations makes important contributions to understanding the pathogenesis of diseases, developing new drugs, and formulating individualized diagnosis and treatment for diverse human complex diseases.
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.
An approach in which miRNAs are linked to diseases via proteins, thereby directly providing biological hypotheses. Specifically, we infer miRNA–disease associations by network analysis of known or predicted miRNA–protein associations and text-mined protein–disease associations. To account for the variable reliability of both types of associations, we provide a scoring scheme that allows for ranking of the inferences by confidence.
Allows users to deduce microRNA– gene interactions with paired expression profiles. MCMG is a standalone software that is able to detect interactions relative to a specific cancer type or common to multiple cancers. It can be used for (i) determining common interactions, (ii) identifying specific miRNA regulations for each cancer; (iii) exploring the possible hidden links among cancers thanks to a quantitative estimate.
Investigates miRNA dysregulation in cancer. OncomiR is composed of three distinct parts: (1) a database of statistically dysregulated miRNAs associated with clinical characteristics of cancer; (2) miRNA-target expression correlation and determination across cancer types; and (3) tools for dynamic study of miRNA-derived survival signatures and clustering of cancer types. It assists users to understand the involvement of miRNAs in cancer progression.
Deduces miRNA-disease associations. IMCMDA is Matlab application intending to consider both known miRNA-disease associations as well as similarities for miRNA and disease including disease semantic and Gaussian interaction profile kernel ones. This program can be used to discover novel diseases without any known related miRNAs. It was tested on three types of case studies involving five high-risk human diseases and validated with a leave-one-out cross validation (LOOCV).
Predicts potential microRNAs (miRNA)-disease associations. BNPMDA is a model based on known miRNA-disease associations, miRNA functional similarity, disease semantic similarity and Gaussian interaction profile kernel similarity. The algorithm was assessed through three types of cross validation and several case studies on important human diseases. It is not suitable for the prediction of diseases without any known associated miRNAs.
Infers the unknown miRNA-disease associations in heterogeneous omics data. GRNMF is a graph regularized non-negative matrix factorization framework which could work for both new diseases and miRNAs. It fully exploits the semantic associations between diseases, weighted gene network, and experimentally validated miRNA-target gene interactions to quantify the similarities for diseases and miRNAs.
Identifies lncRNA related miRNA sponge regulatory network. LncmiRSRN is a causality-based method that integrates expression data, clinical information and miRNA-target interactions. This application was developed to study how the expression levels of the released mRNAs activate. It complements the ceRNA hypothesis and permits users to study the functions and regulatory mechanism of lncRNAs in human cancers.
Consists of an extreme gradient boosting machine for micro-RNA (miRNA)-disease association prediction. It includes features for determining different types of miRNA-disease association. EGBMMDA integrates miRNA functional similarities, disease semantic similarities, and known miRNA-disease associations for working.
Allows users to realize miRNA-disease association prediction. HGIMDA serves to discover potential miRNA-disease associations thanks to integration of disease semantic similarity, miRNA functional similarity, Gaussian interaction profile kernel similarity, and experimentally verified miRNA-disease associations into a heterogeneous graph. This algorithm can be applied to different types of human cancer.
Allows users to predict the potential miRNAs related to human diseases. MCMDA uses a matrix completion procedure by using the known miRNA-disease associations in Human miRNA Disease Database (HMDD). Predicted miRNAs associated with colon neoplasms, kidney neoplasms, lymphoma and prostate neoplasms, were verified by the experimental literatures.
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.
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.
Predicts miRNA-disease associations by exploiting advantages of matrix factorization and network algorithm. MDHGI decomposes original data into two parts, noise and clean, to obtain a clean data about miRNAs and diseases associations. Predictions for new diseases with no known related miRNAs is possible. It can also uncover missing miRNA-disease associations for all diseases in a simultaneous way.
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.
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.
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.
Allows users to predict the microRNA-disease associations thanks to a combinatorial prioritization algorithm. M2DMiners contains six inference methods which aim to infer the novel associations between microRNAs and diseases by modifying the existing maximizing information flow method. It also can be used to detect novel microRNAs for diseases without the known related microRNAs.
Allows users to predict miRNA-disease associations. ILRMR predicts several diseases at once including those without known link to miRNAs. ILRMR integrates miRNA-miRNA similarity information, disease-disease similarity information, and miRNA family information to matrix recovery.
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.