metasnf: Meta Clustering with Similarity Network Fusion

Framework to facilitate patient subtyping with similarity network fusion and meta clustering. The similarity network fusion (SNF) algorithm was introduced by Wang et al. (2014) in <doi:10.1038/nmeth.2810>. SNF is a data integration approach that can transform high-dimensional and diverse data types into a single similarity network suitable for clustering with minimal loss of information from each initial data source. The meta clustering approach was introduced by Caruana et al. (2006) in <doi:10.1109/ICDM.2006.103>. Meta clustering involves generating a wide range of cluster solutions by adjusting clustering hyperparameters, then clustering the solutions themselves into a manageable number of qualitatively similar solutions, and finally characterizing representative solutions to find ones that are best for the user's specific context. This package provides a framework to easily transform multi-modal data into a wide range of similarity network fusion-derived cluster solutions as well as to visualize, characterize, and validate those solutions. Core package functionality includes easy customization of distance metrics, clustering algorithms, and SNF hyperparameters to generate diverse clustering solutions; calculation and plotting of associations between features, between patients, and between cluster solutions; and standard cluster validation approaches including resampled measures of cluster stability, standard metrics of cluster quality, and label propagation to evaluate generalizability in unseen data. Associated vignettes guide the user through using the package to identify patient subtypes while adhering to best practices for unsupervised learning.

Version:	1.1.2
Depends:	R (≥ 4.1.0)
Imports:	cluster, digest, dplyr, ggplot2, grDevices, MASS, mclust, methods, progressr, purrr, rlang, SNFtool, stats, tidyr, utils
Suggests:	circlize, ComplexHeatmap, InteractiveComplexHeatmap, clv, future, future.apply, knitr, rmarkdown, testthat (≥ 3.0.0), ggalluvial, dbscan
Published:	2024-11-08
DOI:	10.32614/CRAN.package.metasnf
Author:	Prashanth S Velayudhan [aut, cre], Xiaoqiao Xu [aut], Prajkta Kallurkar [aut], Ana Patricia Balbon [aut], Maria T Secara [aut], Adam Taback [aut], Denise Sabac [aut], Nicholas Chan [aut], Shihao Ma [aut], Bo Wang [aut], Daniel Felsky [aut], Stephanie H Ameis [aut], Brian Cox [aut], Colin Hawco [aut], Lauren Erdman [aut], Anne L Wheeler [aut, ths]
Maintainer:	Prashanth S Velayudhan <psvelayu at gmail.com>
BugReports:	https://github.com/BRANCHlab/metasnf/issues
License:	GPL (≥ 3)
URL:	https://branchlab.github.io/metasnf/, https://github.com/BRANCHlab/metasnf/
NeedsCompilation:	no
Materials:	README NEWS
CRAN checks:	metasnf results

Documentation:

Reference manual:

metasnf.pdf

Vignettes:

A Complete Example (source, R code) A Simple Example (source, R code) Alluvial Plots (source, R code) Clustering Algorithms (source, R code) Confounders (source, R code) Correlation Plots (source, R code) The Data List (source, R code) Distance Metrics (source, R code) Feature Plots (source, R code) Feature Weighting (source, R code) Getting Started (source, R code) Imputations (source, R code) Label Propagation (source, R code) Manhattan Plots (source, R code) NMI Scores (source, R code) Parallel Processing (source, R code) Quality Measures (source, R code) The Settings Matrix (source, R code) Similarity Matrices (source, R code) SNF Schemes (source, R code) Stability Measures (source, R code) Troubleshooting (source, R code)

Downloads:

Package source:	metasnf_1.1.2.tar.gz
Windows binaries:	r-devel: metasnf_1.1.2.zip, r-release: metasnf_1.1.2.zip, r-oldrel: metasnf_1.1.2.zip
macOS binaries:	r-release (arm64): metasnf_1.1.2.tgz, r-oldrel (arm64): metasnf_1.1.2.tgz, r-release (x86_64): metasnf_1.1.2.tgz, r-oldrel (x86_64): metasnf_1.1.2.tgz
Old sources:	metasnf archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=metasnf to link to this page.