Label projection

Automated cell type annotation from rich, labeled reference data

Repository: openproblems-bio/task_label_projection

Description

A major challenge for integrating single cell datasets is creating matching cell type annotations for each cell. One of the most common strategies for annotating cell types is referred to as “cluster-then-annotate” whereby cells are aggregated into clusters based on feature similarity and then manually characterized based on differential gene expression or previously identified marker genes. Recently, methods have emerged to build on this strategy and annotate cells using known marker genes. However, these strategies pose a difficulty for integrating atlas-scale datasets as the particular annotations may not match.

To ensure that the cell type labels in newly generated datasets match existing reference datasets, some methods align cells to a previously annotated reference dataset and then project labels from the reference to the new dataset.

Here, we compare methods for annotation based on a reference dataset. The datasets consist of two or more samples of single cell profiles that have been manually annotated with matching labels. These datasets are then split into training and test batches, and the task of each method is to train a cell type classifer on the training set and project those labels onto the test set.

Authors & contributors

API

flowchart LR
  file_common_dataset("Common Dataset")
  comp_process_dataset[/"Data processor"/]
  file_solution("Solution")
  file_test("Test data")
  file_train("Training data")
  comp_control_method[/"Control method"/]
  comp_metric[/"Metric"/]
  comp_method[/"Method"/]
  file_prediction("Prediction")
  file_score("Score")
  file_common_dataset---comp_process_dataset
  comp_process_dataset-->file_solution
  comp_process_dataset-->file_test
  comp_process_dataset-->file_train
  file_solution---comp_control_method
  file_solution---comp_metric
  file_test---comp_control_method
  file_test---comp_method
  file_train---comp_control_method
  file_train---comp_method
  comp_control_method-->file_prediction
  comp_metric-->file_score
  comp_method-->file_prediction
  file_prediction---comp_metric

File format: Common Dataset

A subset of the common dataset.

Example file: resources_test/common/pancreas/dataset.h5ad

Format:

Data structure:

Component type: Data processor

A label projection dataset processor.

Arguments:

File format: Solution

The solution for the test data

Example file: resources_test/task_label_projection/pancreas/solution.h5ad

Format:

Data structure:

File format: Test data

The test data (without labels)

Example file: resources_test/task_label_projection/pancreas/test.h5ad

Format:

Data structure:

File format: Training data

The training data

Example file: resources_test/task_label_projection/pancreas/train.h5ad

Format:

Data structure:

Component type: Control method

Quality control methods for verifying the pipeline.

Arguments:

Component type: Metric

A label projection metric.

Arguments:

Component type: Method

A label projection method.

Arguments:

File format: Prediction

The prediction file

Example file: resources_test/task_label_projection/pancreas/prediction.h5ad

Format:

Data structure:

File format: Score

Metric score file

Example file: resources_test/task_label_projection/pancreas/score.h5ad

Format:

Data structure: