Genome-wide data is used to stratify large complex datasets into classes using class discovery algorithms. A widely applied technique is consensus clustering, however; the approach is prone to overfitting and false positives. These issues arise from not considering reference distributions while selecting the number of classes (K). As a solution, we developed Monte Carlo reference-based consensus clustering (M3C). M3C uses a multi-core enabled Monte Carlo simulation to generate null distributions along the range of K which are used to select its value. Using a reference, that maintains the correlation structure of the input features, eliminates the limitations of consensus clustering. M3C uses the Relative Cluster Stability Index (RCSI) and p values to decide on the value of K and reject the null hypothesis, K=1. M3C can also quantify structural relationships between clusters, and uses spectral clustering to deal with non-Gaussian and complex structures. M3C can automatically analyse biological or clinical data with respect to the discovered classes.
|Author||Christopher John [aut, cre]|
|Bioconductor views||Clustering GeneExpression RNASeq Sequencing Transcription|
|Maintainer||Christopher John <[email protected]>|
|Package repository||View on Bioconductor|
Install the latest version of this package by entering the following in R:
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.