Functional API (Low-level)#
Data#
Built-in Data#
|
Used to download data for tutorials. |
Tools#
|
Class used to convert numerical torch tensors into categorical equivalents. |
|
Class used to convert tensor datasets into an |
|
Function to generate conditional labels for the various models included. |
|
Function that distributes the |
|
Function to preprocess the inputted |
Models#
|
Patches, the multi-attribute model. |
|
scVI (https://www.nature.com/articles/s41592-018-0229-2), implemented through |
|
Supervised scANVI (https://www.embopress.org/doi/full/10.15252/msb.20209620), implemented through |
Scripts#
Metrics#
|
Used to get library-size normalized pseudobulk profile from group of cells. |
|
Used to generate new points by performing a full pass through the models. |
|
Calculates the model generative error for the given metric. |
|
Calculates the normalized Average Silhouette Width (ASW). |
|
Calculates the K-Means ARI for latent representations. |
|
Calculates the K-Means NMI for latent representations. |
|
Calculates KNN classifier accuracy on embeddings. |
Training#
Prints currently used device. |
|
|
Runner for basic Pyro models. |
|
Runner for Patches, but can be used for other adversarial models. |