API#
Benchmarking pipeline#
Import as:
from scib_metrics.benchmark import Benchmarker
|
Benchmarking pipeline for the single-cell integration task. |
|
Specification of bio conservation metrics to run in the pipeline. |
|
Specification of which batch correction metrics to run in the pipeline. |
Metrics#
Import as:
import scib_metrics
scib_metrics.ilisi_knn(...)
|
Isolated label score [Luecken et al., 2022]. |
|
Compute nmi and ari between k-means clusters and labels. |
|
Compute nmi and ari between leiden clusters and labels. |
|
Principal component regression (PCR) comparison [Büttner et al., 2018]. |
|
Average silhouette width (ASW) [Luecken et al., 2022]. |
|
Average silhouette width (ASW) with respect to batch ids within each label [Luecken et al., 2022]. |
|
Compute the integration local inverse simpson index (iLISI) for each cell [Korsunsky et al., 2019]. |
|
Compute the cell-type local inverse simpson index (cLISI) for each cell [Korsunsky et al., 2019]. |
|
Compute kbet [Büttner et al., 2018]. |
|
Compute kBET score per cell type label as in [Luecken et al., 2022]. |
|
Quantify the connectivity of the subgraph per cell type label. |
Utils#
|
Jax implementation of |
Jax implementation of |
|
|
Compute the Silhouette Coefficient for each observation. |
|
Jax implementation of |
|
Principal component analysis (PCA). |
Principal component regression (PCR) [Büttner et al., 2018]. |
|
|
One-hot encode an array. |
|
Compute the Simpson index for each cell. |
Convert a kNN graph to indices and distances. |
|
Check if a matrix is square. |
|
|
Diffusion-based neighbors. |
Nearest neighbors#
|
Run pynndescent approximate nearest neighbor search. |
|
Run approximate nearest neighbor search using jax. |
|
Nearest neighbors results data store. |
Settings#
An instance of the ScibConfig
is available as scib_metrics.settings
and allows configuring scib_metrics.
Config manager for scib-metrics. |