Run Pan-human Azimuth annotation locally

This function runs the Pan-human Azimuth model on a Seurat object to annotate cell types, via reticulate and the panhumanpy Python package. We recommend using the CloudAzimuth function, which runs cloud-based annotation, can handle large datasets, and performs robust error handling.

Usage

ANNotate(
  query_obj,
  feature_names_col = NULL,
  annotation_pipeline = "supervised",
  eval_batch_size = 8192L,
  normalization_override = FALSE,
  norm_check_batch_size = 100L,
  output_mode = "minimal",
  refine_labels = TRUE,
  map_to_cl = NULL,
  include_cl_id = FALSE,
  extract_embeddings = TRUE,
  umap_embeddings = TRUE,
  n_neighbors = 30L,
  n_components = 2L,
  metric = "cosine",
  min_dist = 0.3,
  umap_lr = 1,
  umap_seed = 42L,
  spread = 1,
  verbose = TRUE,
  init = "spectral",
  model_version = "v1",
  process_obj = TRUE,
  cutoff_abs = 5,
  cutoff_frac = 0.001,
  assay = NULL
)

Arguments

• query_obj:

  Seurat object to annotate

• feature_names_col:

  Column name for feature names

• annotation_pipeline:

  Set to ‘supervised’ as a default

• eval_batch_size:

  Evaluation batch size

• normalization_override:

  Whether to override normalization

• norm_check_batch_size:

  Batch size to inspect normalization of data

• output_mode:

  Output mode for annotated cell metadata

• refine_labels:

  Whether to refine labels

• map_to_cl:

  One or more annotation columns to map to Cell Ontology labels

• include_cl_id:

  Whether to add Cell Ontology IDs to the output metadata

• extract_embeddings:

  Whether to extract Azimuth embeddings

• umap_embeddings:

  Whether to include UMAP of Azimuth embeddings

• n_neighbors:

  Number of neighbors for UMAP

• n_components:

  Number of components for UMAP

• metric:

  Distance metric for UMAP

• min_dist:

  Minimum distance for UMAP

• umap_lr:

  Learning rate for UMAP

• umap_seed:

  Seed for UMAP

• spread:

  Spread parameter for UMAP

• verbose:

  Whether to show progress

• init:

  Initialization method for UMAP

• model_version:

  Version of the model to use (default: ‘v1’)

• process_obj:

  Whether to process the object

• cutoff_abs:

  Absolute cutoff for label filtering

• cutoff_frac:

  Fractional cutoff for label filtering

• assay:

  Assay to use for annotation

Value

Annotated Seurat object

Details

This function requires the panhumanpy Python package to be installed and accessible via reticulate.