- CFLARE.predict(use=None, percentile=98, method='leiden', cluster_key=None, n_clusters_kmeans=None, n_neighbors=20, resolution=0.1, n_matches_min=0, n_neighbors_filtering=15, basis=None, n_comps=5, scale=None)¶
Find approximate recurrent classes of the Markov chain.
Filter to obtain recurrent states in left eigenvectors. Cluster to obtain approximate recurrent classes in right eigenvectors.
int]) – Threshold used for filtering out cells which are most likely transient states. Cells which are in the lower
percentilepercent of each eigenvector will be removed from the data matrix.
Literal[‘leiden’, ‘means’]) –
Method to be used for clustering. Valid option are:
int) – Number of neighbors in a KNN graph. This is the \(K\) parameter for that, the number of neighbors for each cell. Only used when
method = 'leiden'.
int) – Filters out cells which don’t have at least
n_matches_minneighbors from the same category. This filters out some cells which are transient but have been misassigned.
int) – Parameter for filtering cells. Cells are filtered out if they don’t have at least
n_matches_minneighbors among their
int) – Number of embedding components to be use when
basis != None.
- Return type
Nothing, just updates the following fields: