https://github.com/cbg-ethz/graphclust_neurips

Network-Based Clustering of Pan-Cancer Data Accounting for Clinical Covariates

https://github.com/cbg-ethz/graphclust_neurips

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (10.6%) to scientific vocabulary

Keywords

clustering genomics graphs networks
Last synced: 5 months ago · JSON representation

Repository

Network-Based Clustering of Pan-Cancer Data Accounting for Clinical Covariates

Basic Info
  • Host: GitHub
  • Owner: cbg-ethz
  • License: gpl-3.0
  • Language: R
  • Default Branch: main
  • Homepage:
  • Size: 23.6 MB
Statistics
  • Stars: 3
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
clustering genomics graphs networks
Created over 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Network-Based Clustering of Pan-Cancer Data Accounting for Clinical Covariates

License: GPL v3

This repository contains the code to reproduce the results of the NeurIPS 2022 LMRL workshop paper "Network-Based Clustering of Pan-Cancer Data Accounting for Clinical Covariates".

Installation

In order to install the package, it suffices to launch R CMD INSTALL path/to/graphClust from a terminal, or make install from within the package source folder.

Being hosted on GitHub, it is possible to use the install_github tool from an R session:

``` if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install(c("Rgraphviz", "RBGL"))

library("devtools") installgithub("cbg-ethz/graphClustNeurIPS") ```

graphClust requires R >= 3.5, and depends on pcalg, reshape2, BiDAG (>= 2.0.2), RBGL, clue and grDevices.

Simulations

Figure 2 can be reproduced by running the script simulations/figure_2-simulation.R. Analogously, Figure 4 in the appendix can be reproduced by running the script simulations/figure_4-simulation.R. The simulations can be modified and executed in the simulations/cluster-scripts folder.

Pan-Cancer Data

Figure 3 can be reproduced by runnign the script tcga_analysis/figure_3-km_plot.R. The results of Table 1 can be reproduced by runnign the script tcga_analysis/table_1-cox_analysis.R. A reproducability analysis for a range of different seeds can be found in tcga_analysis/reproducability_different_seeds. The hyperparameters of the cluster algorithms can be modified and executed in the tcga_analysis/clustering folder folder.

Example

```{r eval=FALSE} library(graphClust)

Simulate binary data from 3 clusters

kclust <- 3 ss <- c(400, 500, 600) # samples in each cluster simulationdata <- sampleData(kclust = kclust, nvars = 20, nsamples = ss) sampleddata <- simulationdata$sampled_data

Network-based clustering

clusterres <- getclusters(sampleddata, kclust = k_clust)

Calculate the ARI

library(mclust) adjustedRandIndex(simulationdata$clustermembership, clusterrest$clustermembership)

Visualize the networks

library(ggplot2) library(ggraph) library(igraph) library(ggpubr)

graphClust::plotclusters(clusterres_t)

Visualize a single network

mygraph <- igraph::graphfromadjacencymatrix(clusterrest$DAGs[[1]], mode="directed") graphClust::niceDAGplot(my_graph)

```

Owner

  • Name: Computational Biology Group (CBG)
  • Login: cbg-ethz
  • Kind: organization
  • Location: Basel, Switzerland

Beerenwinkel Lab at ETH Zurich

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels