optCluster

optCluster is an R package that offers a solution to the problem of determining the optimal clustering algorithm for a given dataset. It uses a single function to compare multiple clustering partitions created by different algorithms and numbers of clusters and then selects the "best" option by utilizing a weighted rank aggregation method to aggregate the various performance measure scores objectively. This package is handy for genomic clustering data, containing biological validation measures and clustering algorithms specifically developed for RNA sequencing data. optCluster thus allows users to take the guesswork out of determining the optimal clustering algorithm.

Topic

Applied mathematics;Statistics and probability;Computational biology;Bioinformatics

Detail

  • Operation: Clustering

  • Software interface: Library

  • Language: R

  • License: GNU General Public License v2

  • Cost: Free

  • Version name: 1.3.2

  • Credit: The National Institutes of Health (NIH).

  • Input: -

  • Output: -

  • Contact: michael.sekula@louisville.edu;somnath.datta@louisville.edu;susmita.datta@louisville.edu

  • Collection: -

  • Maturity: -

Publications

  • optCluster: An R Package for Determining the Optimal Clustering Algorithm.
  • Sekula M, et al. optCluster: An R Package for Determining the Optimal Clustering Algorithm. optCluster: An R Package for Determining the Optimal Clustering Algorithm. 2017; 13:101-103. doi: 10.6026/97320630013101
  • https://doi.org/10.6026/97320630013101
  • PMID: 28584451
  • PMC: PMC5450252

Download and documentation


< Back to DB search