integrate/totalvi_scarches

Description

Performs totalVI integration by mapping the query dataset to a reference dataset or model.

Type

python_script

License

MIT

Links

Repository

Contributors

Launch

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
query_modality: [ "rna" ]  
reference_modality: [ "rna" ]  
reference_proteins_modality: [ "prot" ]  
obs_batch: [ "sample_id" ]  
output: "$id.$key.output"  
obsm_output: [ "X_integrated_totalvi" ]  
obsm_normalized_rna_output: [ "X_totalvi_normalized_rna" ]  
obsm_normalized_protein_output: [ "X_totalvi_normalized_protein" ]  
reference_model_path: "$id.$key.reference_model_path"  
query_model_path: "$id.$key.query_model_path"  
max_epochs: [ 400 ]  
max_query_epochs: [ 200 ]  
weight_decay: [ 0 ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision v4.0.3 \  
  -main-script target/nextflow/integrate/totalvi_scarches/main.nf \  
  -params-file params.yaml

Inputs

Name	Type & Properties	Description
--input -i	file required	Input h5mu file with query data to integrate with reference.
--reference -r	file required	Input h5mu file with reference data to train the TOTALVI model.
--force_retrain -f	boolean_true	If true, retrain the model and save it to reference_model_path
--query_modality	string
--query_proteins_modality	string	Name of the modality in the input (query) h5mu file containing protein data
--reference_modality	string
--reference_proteins_modality	string	Name of the modality containing proteins in the reference
--input_layer	string	Input layer to use. If None, X is used
--obs_batch	string	Column name discriminating between your batches.
--obs_size_factor	string	Key in adata.obs for size factor information. Instead of using library size as a size factor, the provided size factor column will be used as offset in the mean of the likelihood. Assumed to be on linear scale.
--obs_categorical_covariate	string multiple	Keys in adata.obs that correspond to categorical data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.
--obs_continuous_covariate	string multiple	Keys in adata.obs that correspond to continuous data. These covariates can be added in addition to the batch covariate and are also treated as nuisance factors (i.e., the model tries to minimize their effects on the latent space). Thus, these should not be used for biologically-relevant factors that you do _not_ want to correct for.
--var_input	string	.var column containing highly variable genes. By default, do not subset genes.

Name

Type & Properties

--input

-i

file

required

--reference

-r

file

required

--force_retrain

-f

boolean_true

--query_modality

string

--query_proteins_modality

string

--reference_modality

string

--reference_proteins_modality

string

--input_layer

string

--obs_batch

string

--obs_size_factor

string

--obs_categorical_covariate

string

multiple

--obs_continuous_covariate

string

multiple

--var_input

string

Outputs

Name	Type & Properties	Description
--output -o	file required output	Output h5mu file.
--obsm_output	string	In which .obsm slot to store the resulting integrated embedding.
--obsm_normalized_rna_output	string	In which .obsm slot to store the normalized RNA from TOTALVI.
--obsm_normalized_protein_output	string	In which .obsm slot to store the normalized protein data from TOTALVI.
--reference_model_path	file output	Directory with the reference model. If not exists, trained model will be saved there
--query_model_path	file output	Directory, where the query model will be saved

Name

Type & Properties

--output

-o

file

required

output

--obsm_output

string

--obsm_normalized_rna_output

string

--obsm_normalized_protein_output

string

--reference_model_path

file

output

--query_model_path

file

output

Learning parameters

Name	Type & Properties	Description
--max_epochs	integer	Number of passes through the dataset
--max_query_epochs	integer	Number of passes through the dataset, when fine-tuning model for query
--weight_decay	double	Weight decay, when fine-tuning model for query

Name

Type & Properties

--max_epochs

integer

--max_query_epochs

integer

--weight_decay

double