scgpt/cell_type_annotation

Description

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

Type

python_script

Links

Repository

Contributors

Launch

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
finetuned_checkpoints_key: [ "model_state_dict" ]  
label_mapper_key: [ "id_to_class" ]  
modality: [ "rna" ]  
obsm_gene_tokens: [ "gene_id_tokens" ]  
obsm_tokenized_values: [ "values_tokenized" ]  
output: "$id.$key.output.h5mu"  
output_compression: [ "gzip" ]  
output_obs_predictions: [ "scgpt_pred" ]  
output_obs_probability: [ "scgpt_probability" ]  
pad_token: [ "<pad>" ]  
pad_value: [ -2 ]  
n_input_bins: [ 51 ]  
batch_size: [ 64 ]  
dsbn: [ true ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision 2.0.0 \  
  -main-script target/nextflow/scgpt/cell_type_annotation/main.nf \  
  -params-file params.yaml

Model input

Name	Type & Properties	Description
--model	file required	The model file containing checkpoints and cell type label mapper.
--model_config	file required	The model configuration file.
--model_vocab	file required	Model vocabulary file directory.
--finetuned_checkpoints_key	string	Key in the model file containing the pretrained checkpoints.
--label_mapper_key	string	Key in the model file containing the cell type class to label mapper dictionary.

Name

Type & Properties

--model

file

required

--model_config

file

required

--model_vocab

file

required

--finetuned_checkpoints_key

string

--label_mapper_key

string

Query input

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

Name

Type & Properties

--input

file

required

--modality

string

--obs_batch_label

string

--obsm_gene_tokens

string

--obsm_tokenized_values

string

Outputs

Name	Type & Properties	Description
--output	file required output	The output mudata file.
--output_compression	string	The compression algorithm to use for the output h5mu file.
--output_obs_predictions	string	The name of the adata.obs column to write predicted cell type labels to.
--output_obs_probability	string	The name of the adata.obs column to write the probabilities of the predicted cell type labels to.

Name

Type & Properties

--output

file

required

output

--output_compression

string

--output_obs_predictions

string

--output_obs_probability

string

Arguments

Name	Type & Properties	Description
--pad_token	string	The padding token used in the model.
--pad_value	integer	The value of the padding.
--n_input_bins	integer	The number of input bins.
--batch_size	integer	The batch size.
--dsbn	boolean	Whether to use domain-specific batch normalization.
--seed	integer	Seed for random number generation. If not specified, no seed is used.

Name

Type & Properties

--pad_token

string

--pad_value

integer

--n_input_bins

integer

--batch_size

integer

--dsbn

boolean

--seed

integer