Repository files navigation

visxhclust is a package that includes a Shiny application forvisualexploration ofhierarchicalclustering. It is aimed atfacilitating iterative workflows of hierarchical clustering on numericdata. For that, the app allows users to quickly change parameters andanalyse and evaluate results with typical heatmaps with dendrograms andother charts. Additionally, it includes lightweight data overview plotssuch as correlation heatmaps, annotated MDS and PCA plots. On theevaluation side, it builds on existing packages to compute internalvalidation scores and Gap statistic, as well as Dunn’s test to evaluatesignificant differences between clusters. Many of the functions are alsoexported to facilitate documenting a complete analysis cycle.

NEW! A live demo of the app is runninghere.

The latest release can be installed from CRAN:

install.packages("visxhclust")

The latest development version can be installed from GitHub:

remotes::install_github("rhenkin/visxhclust")

Most dependencies are found in CRAN. However, the heatmap drawingpackage is part ofBioconductor and mayrequire a separate installation:

install.packages("BiocManager")BiocManager::install("ComplexHeatmap")

To run the app once the package is installed, use the followingcommands:

library(visxhclust)# Increases max file size to 30 MBoptions(shiny.maxRequestSize=30*1024^2)run_app()

The app includes multiple help points in the interface (look for thequestion marks), and there are also three guides on how to use tool:

• Ananimatedguideon loading data and the basic clustering loop. It’s also accessiblein R by using the commandvignette("visxhclust").
• An example of how toreproduce ananalysisan analysis using the functions exported by the package. See withvignette("clusterworkflow") in R.
• An example of how toreproduce the evaluationworkflowusing the functions exported by the package. See withvignette("clusterevaluation") in R.

To use your data with the tool, you can save a data frame or tibble inan RDS file, or use comma or tab-delimited files, with .csv, .tsv or.txt extensions. The clustering method supported by the tool works onlyon numeric values; columns containing text will be set aside to annotatethe heatmap if so desired. If a column namedID exists, it will beused as an internal identifier for rows.

Clustering requires complete datasets with no missing values, NULLs orNAs. If any column contains missing values, it will be set aside to beused as a heatmap annotation. Badly formatted data will also lead tounexpected results in the tool. As an alternative, imputation packagescan be used to fill missing data and faulty rows (e.g. text in numericcolumns) should be removed before loading the file into the tool. Thetool provides limited abilities to help with diagnosing issues andpreprocessing data.

Please see theguidefor code contribution and suggestions.