Beta release 2

This is the beta release of R toolbox for Archetypal Analysis and Pareto Task Inference on single cell data.

Minor changes:

• added c matrix for kmeans method (data %*% c computes cluster averages)
• bug fix: fit_pch now returns c matrix correctly (which is almost never used)
• updated website

Beta release

This is the beta release of R toolbox for Archetypal Analysis and Pareto Task Inference on single cell data.

New features:

• Projecting archetypes to and from Principal component space
• Poisson deviance for variable/gene selection
• Using archetype weights as distance metric for finding archetype marker genes (find_decreasing_wilcox())
• Visualise the structure in how genes are reused across archetypes with plot_arch_struct()

Minor changes:

• removed large and unneeded files
• updated documentation: python 3 dependency modules rather than python 2 should be used from now on
• minor bug fixes

Expect improvements of usability by integration with Seurat & scater, probabilistic version of the Archetypal Analysis and the bug fixes within the next few months.

First release

This is the first release of R toolbox for Archetypal Analysis and Pareto Task Inference on single cell data (to start archiving with Zenodo). Expect improvements and updates within the next few months.