Package index • bixverse.gpu

Single cell GPU kNN

You need kNN graphs on large single cell data sets and you have some VRAM to spare? Look no further.

find_neighbours_gpu_sc(): Find GPU-accelerated neighbours for single cells (exhaustive / IVF)
params_sc_ivf(): Default parameters for IVF-GPU kNN search
find_neighbours_cagra_sc(): Find CAGRA GPU-accelerated neighbours for single cells
params_sc_cagra(): Default parameters for CAGRA-style kNN search

Parametric UMAP

Want to train a neural net to do your UMAP embeddings? Want to train flexibly on CPU or GPU? Here’s what you need.

parametric_umap(): Parametric UMAP
params_parametric_umap(): Wrapper function to generate parametric UMAP parameters
predict(<ParametricUmapModel>): Predict embeddings for new data using a trained parametric UMAP model

Rust wrappers

Everything rusty - only use this if you know what you are doing… Maybe useful for your own package? Use with care and read the documentation!

rs_cagra_gpu_knn(): Generate a CAGRA-style GPU-accelerated kNN graph
rs_exhaustive_gpu_knn(): Generate an GPU-accelerated kNN graph from an exhaustive search
rs_ivf_gpu_knn(): Generate an IVF-GPU-accelerated kNN graph
rs_parametric_umap_predict(): Predict new data using a trained parametric UMAP model
rs_parametric_umap(): Parametric UMAP implementation