Cell type annotation

Annotate gene expression data with cell type classes through the scGPT model

Info

ID: cell_type_annotation
Namespace: scgpt

Example commands

You can run the pipeline using nextflow run.

View help

You can use --help as a parameter to get an overview of the possible parameters.

nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -main-script target/nextflow/scgpt/cell_type_annotation/main.nf \
  --help

Run command

Example of params.yaml 
# Model input
model: # please fill in - example: "best_model.pt"
model_config: # please fill in - example: "args.json"
model_vocab: # please fill in - example: "vocab.json"
finetuned_checkpoints_key: "model_state_dict"
label_mapper_key: "id_to_class"

# Query input
input: # please fill in - example: "scgpt_preprocess_ouput.h5mu"
modality: "rna"
# obs_batch_label: "foo"
obsm_gene_tokens: "gene_id_tokens"
obsm_tokenized_values: "values_tokenized"

# Outputs
# output: "$id.$key.output.h5mu"
output_compression: "gzip"
output_obs_predictions: "scgpt_pred"
output_obs_probability: "scgpt_probability"

# Arguments
pad_token: "<pad>"
pad_value: -2
n_input_bins: 51
batch_size: 64
dsbn: true
# seed: 123

# Nextflow input-output arguments
publish_dir: # please fill in - example: "output/"
# param_list: "my_params.yaml"
nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -profile docker \
  -main-script target/nextflow/scgpt/cell_type_annotation/main.nf \
  -params-file params.yaml
Note

Replace -profile docker with -profile podman or -profile singularity depending on the desired backend.

Argument groups

Model input

Name Description Attributes
--model The model file containing checkpoints and cell type label mapper. file, required, example: "best_model.pt"
--model_config The model configuration file. file, required, example: "args.json"
--model_vocab Model vocabulary file directory. file, required, example: "vocab.json"
--finetuned_checkpoints_key Key in the model file containing the pretrained checkpoints. string, default: "model_state_dict"
--label_mapper_key Key in the model file containing the cell type class to label mapper dictionary. string, default: "id_to_class"

Query input

Name Description Attributes
--input The input h5mu file containing of data that have been pre-processed (normalized, binned, genes cross-checked and tokenized). file, required, example: "scgpt_preprocess_ouput.h5mu"
--modality string, default: "rna"
--obs_batch_label The name of the adata.obs column containing the batch labels. Required if dsbn is set to true. string
--obsm_gene_tokens The key of the .obsm array containing the gene token ids string, default: "gene_id_tokens"
--obsm_tokenized_values The key of the .obsm array containing the count values of the tokenized genes string, default: "values_tokenized"

Outputs

Name Description Attributes
--output The output mudata file. file, required, example: "output.h5mu"
--output_compression The compression algorithm to use for the output h5mu file. string, default: "gzip", example: "gzip"
--output_obs_predictions The name of the adata.obs column to write predicted cell type labels to. string, default: "scgpt_pred"
--output_obs_probability The name of the adata.obs column to write the probabilities of the predicted cell type labels to. string, default: "scgpt_probability"

Arguments

Name Description Attributes
--pad_token The padding token used in the model. string, default: "<pad>"
--pad_value The value of the padding. integer, default: -2
--n_input_bins The number of input bins. integer, default: 51
--batch_size The batch size. integer, default: 64
--dsbn Whether to use domain-specific batch normalization. boolean, default: TRUE
--seed Seed for random number generation. If not specified, no seed is used. integer

Authors

  • Dorien Roosen (maintainer, author)

  • Jakub Majercik (author)