You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
k-NN-based mapping of cells across representations to tranfer labels, embeddings and expression values. Works for millions of cells, on CPU and GPU, across molecular modalities, between spatial and non-spatial data, for arbitrary query and reference datasets. Using [faiss][] to compute k-NN graphs, CellMapper takes about 30 seconds to transfer cell type labels from 1.5M cells to 1.5M cells on a single RTX 4090 with 60 GB CPU memory.
14
16
15
-
Inspired by scanpy's [ingest][] and the [HNOCA-tools][] packages.
17
+
Inspired by scanpy's [ingest][] and the [HNOCA-tools][] packages. Check out the [docs][] to learn more.
This will transfer data from the reference to the query dataset, including celltype labels stored in ``ref.obs``, a UMAP embedding stored in ``ref.obsm``, and expression values stored in ``ref.X``.
50
52
51
-
There are many ways to customize this, e.g. use different ways to compute k-NN graphs and to turn them into mapping matrices, and we implement a few methods to evaluate whether your k-NN transfer was sucessful.
53
+
There are many ways to customize this, e.g. use different ways to compute k-NN graphs and to turn them into mapping matrices, and we implement a few methods to evaluate whether your k-NN transfer was sucessful. Check out the [docs][] to learn more.
52
54
53
55
## Release notes
54
56
@@ -66,7 +68,7 @@ Please cite this GitHub repo if you find CellMapper useful for your research.
0 commit comments