Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

metasnf: Meta Clustering with Similarity Network Fusion in R

Prashanth S Velayudhan, Xiaoqiao Xu, Prajkta Kallurkar, Ana Patricia Balbon, Maria T Secara, Adam Taback, Denise Sabac, Nicholas Chan, Shihao Ma, Bo Wang, Daniel Felsky, Stephanie H Ameis, Brian Cox, Colin Hawco, Lauren Erdman, Anne L Wheeler

Abstract

metasnf is an R package that enables users to apply meta clustering, a method for efficiently searching a broad space of cluster solutions by clustering the solutions themselves, to clustering workflows based on similarity network fusion (SNF). SNF is a multi-modal data integration algorithm commonly used for biomedical subtype discovery. The package also contains functions to assist with cluster visualization, characterization, and validation. This package can help researchers identify SNF-derived cluster solutions that are guided by context-specific utility over context-agnostic measures of quality.

metasnf: Meta Clustering with Similarity Network Fusion in R

Abstract

metasnf is an R package that enables users to apply meta clustering, a method for efficiently searching a broad space of cluster solutions by clustering the solutions themselves, to clustering workflows based on similarity network fusion (SNF). SNF is a multi-modal data integration algorithm commonly used for biomedical subtype discovery. The package also contains functions to assist with cluster visualization, characterization, and validation. This package can help researchers identify SNF-derived cluster solutions that are guided by context-specific utility over context-agnostic measures of quality.

Paper Structure

This paper contains 62 sections, 1 equation, 21 figures.

Table of Contents

  1. Introduction
  2. Installation
  3. Package overview
  4. Data set-up
  5. Formatting raw data
  6. Creating a data list
  7. Partitioning features into components for a data list
  8. Target lists
  9. Defining hyperparameters for clustering
  10. An overview of the settings matrix
  11. Building the settings matrix
  12. Basic random population
  13. Specifying ranges of variation
  14. Controlling data type dropout
  15. Piecewise construction and manual editing
  16. ...and 47 more sections

Figures (21)

  • Figure 1: Heatmap of adjusted Rand indices between 20 generated cluster solutions.
  • Figure 2: Heatmap of adjusted Rand indices, partitioned into meta clusters A-E.
  • Figure 3: Annotated heatmap of adjusted Rand indices.
  • Figure 4: Annotated heatmap of adjusted Rand indices with a manually generated annotation indicating if two specific subjects clustered together.
  • Figure 5: Manhattan plot showing separation of all features for representative cluster solutions from each meta cluster. Input and target features are along the x-axis. A small vertical line separates the features provided through the data list (left) from those provided through the target list (right). Y-axis values represent $-log_{10}(\text{p-values})$ calculated for the extended solutions matrix. Colours of the points reflect the domains that the features belong to.
  • ...and 16 more figures