1 - 17 of 17 results

IRWRLDA / Improved Random Walk with Restart for LncRNA-Disease Association prediction

Allows users to foresee novel lncRNA-disease associations. IRLWRLDA integrates various lncRNA similarity measures, disease semantic similarity, and known lncRNA-disease associations. It incorporates lncRNA expression similarity and disease semantic similarity to set the initial probability vector of Random walk with restart (RWR). This tool can be applied to any diseases without known related lncRNAs.


Infers long non-coding RNA (lncRNA) functional similarity (LFS) by modeling the information flow in an integrated network that comprises both lncRNA-related transcriptional and post-transcriptional information. IntNetLncSim integrated network involves lncRNA regulatory network, miRNA-mRNA interaction network, and mRNA-mRNA interaction network. The performance of IntNetLncSim was evaluated by investigating the relationship of LFS with the similarity of lncRNA-related mRNA sets (LmRSets) and miRNA sets (LmiRSets). Furthermore, highly-ranked lncRNA-disease associations confirmed by literature mining demonstrated the performance of IntNetLncSim. A web-accessible system was provided for querying LFS and potential lncRNA-disease relationships.

MFLDA / Matrix Factorization based LncRNA-Disease Association

Allows identification of lncRNA-disease associations. MFLDA is a matrix factorization based data fusion model that integrates various heterogenous data sources to predict associations between different types of entities, such as RNA-protein interactions, associations between genes and Gene Ontology terms. The software can selectively and differentially fuse heterogenous data sources by assigning large weights to relevant data sources and small (or zero) weights to less relevant (or noisy) data sources.

FMLNCSIM / Fuzzy Measure-based LNCRNA functional SIMilarity calculation model

A calculation model based on the assumption that functionally similar long noncoding RNAs (lncRNAs) tend to be associated with similar diseases. FMLNCSIM performance improvement comes from the combination of information content and the concept of fuzzy measure, which was applied to the directed acyclic graphs of disease MeSH descriptors. FMLNCSIM web server mainly carries out four functions. The function 1 and 2 enable visitors obtain functional similarities calculated by FMLNCSIM model based on two lncRNA-disease association databases (i.e. LncRNADisease and MNDR). The function 3 and 4 provide functional similarity calculation for new lncRNAs as long as users provided its associated diseases. When visitors provide a specific lncRNA with its associated diseases, function 3 and 4 could calculate the functional similarities between this query lncRNA and all lncRNAs in LncRNADisease and MNDR databases, and then list the results on the webpage.

KATZLDA / KATZ measure for LncRNA-Disease Association prediction

Predicts potential lncRNA-disease associations. KATZLDA was developed for predicting potential disease-related Long non-coding RNA (lncRNAs) by measuring the importance of candidate nodes relative to given seed nodes, and identifying nodes similar to seed nodes. The software integrates known lncRNA-disease associations, lncRNA expression profiles, lncRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for diseases and lncRNAs. It has been used to predict potential colon cancer-related lncRNAs.


Aims to address the unique opportunity of comprehensively discovering cancer driver lncRNAs within and across tumour types using mutation data generated by projects such as TCGA (The Cancer Genome Atlas) and ICGC (International Cancer Genome Consortium). ExInAtor is specifically designed to identify cancer driver lncRNAs from tumour genome cohorts. The ExInAtor workflow can be divided into the following steps: exon and background definition, mutations mapping, sub-sampling of background region, gene filtering by mutation counts and statistical analysis.

TPGLDA / Tripartite Graph for potential LncRNA-Disease Association identification

Identifies potential long non-coding RNAs (lncRNA)-disease associations. TPGLDA is a computational method that integrates experimentally verified gene-disease associations and lncRNA-disease associations. The lncRNA-disease-gene tripartite graph allows delineation of the heterogeneity of coding-non-coding genes-disease associations. The software can be applied to the isolated nodes by integrating lncRNA similarities and disease similarities.

LDAP / LncRNA-Disease Association Prediction

A web server for long noncoding RNA-disease (lncRNA-disease) association prediction. LDAP predicts potential lncRNA-disease associations by using a bagging SVM classifier based on lncRNA similarity and disease similarity. The sequence similarity between input lncRNA and database is calculated by using Smith-Waterman algorithm. In addition, LDAP uses LncR_Gip for lncRNA similarity and five methods (Dis_Icod, Dis_Top, Dis_Gf, Dis_GO and Dis_Gip) for disease similarity measurement. Then, the karcher mean of matrixes is employed to fuse similarity matrixes of lncRNA and disease and the bagging SVM is used to identify potential lncRNA-disease interactions.

Lncin / lncRNA interaction

Identifies long non-coding RNAs (lncRNAs)-associated modules from protein interaction networks and predicts the function of lncRNAs based on the protein functions in the modules. Lncin utilizes not only the lncRNA-mRNA co-expression networks based on the rank of correlation which is a better measure of similarity than the correlation value, but also protein-protein interactions among co-expressed mRNAs to identify a set of mRNAs that may be modulated by lncRNA.

ILNCSIM / Improved LNCRNA functional SIMilarity calculation model

Quantifies long non-coding RNAs (lncRNA) functional similarity by combining known disease Directed Acyclic Graphs (DAGs) and known lncRNA-disease associations. ILNCSIM is implemented in a web server that provides similarity calculation function for new lncRNAs with associated diseases provided by users. For a given lncRNA with its associated diseases, the functional similarity between this query lncRNA and all lncRNAs in two databases are computed and listed.

LRLSLDA / Laplacian Regularized Least Squares for LncRNA-Disease Association

A computational model in the semisupervised learning framework. LRLSLDA method prioritizes the entire long-non-coding RNAome (lncRNAome) for disease of interest by integrating known phenome-lncRNAome network obtained from the database of LncRNADisease, disease similarity network and lncRNA similarity network. LRLSLDA is a global approach that can rank candidate disease-lncRNA pairs for all the diseases simultaneously. In the leave-one-out cross validation (LOOCV), LRLSLDA obtained the reliable AUC of 0.7760, demonstrating superiority performance of LRLSLDA to previous methods and potential value for disease-related lncRNA prediction and biomarker detection in the diagnosis, treatment, prognosis and prevention of human disease.