workflows/integration/totalvi_scarches_leiden

Description

Run totalVI integration by mapping the query dataset to a reference, followed by neighbour calculations, leiden clustering and run umap on the result.

Inputs

Name	Type & Properties	Description
--id	string required	ID of the sample.
--input	file required	Path to the sample.
--layer	string	use specified layer for expression values instead of the .X object from the modality.
--modality	string	Which modality to process.
--prot_modality	string	Which modality to process.
--reference -r	file required	Input h5mu file with reference data to train the TOTALVI model.

Name

Type & Properties

--id

string

required

--input

file

required

--layer

string

--modality

string

--prot_modality

string

--reference

-r

file

required

Outputs

Name	Type & Properties	Description
--output	file required output	Destination path to the output.
--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

file

required

output

--reference_model_path

file

output

--query_model_path

file

output

General TotalVI Options

Name	Type & Properties	Description
--obs_batch	string	.Obs 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.
--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
--force_retrain	boolean_true	If true, retrain the model and save it to reference_model_path
--var_input	string	Boolean .var column to subset data with (e.g. containing highly variable genes). By default, do not subset genes.

Name

Type & Properties

--obs_batch

string

--obs_size_factor

string

--obs_categorical_covariate

string

multiple

--obs_continuous_covariate

string

multiple

--max_epochs

integer

--max_query_epochs

integer

--weight_decay

double

--force_retrain

boolean_true

--var_input

string

TotalVI integration options RNA

Name	Type & Properties	Description
--rna_reference_modality	string
--rna_obsm_output	string	In which .obsm slot to store the normalized RNA from TOTALVI.

Name

Type & Properties

--rna_reference_modality

string

--rna_obsm_output

string

TotalVI integration options ADT

Name	Type & Properties	Description
--prot_reference_modality	string	Name of the modality containing proteins in the reference
--prot_obsm_output	string	In which .obsm slot to store the normalized protein data from TOTALVI.

Name

Type & Properties

--prot_reference_modality

string

--prot_obsm_output

string

Neighbour calculation RNA

Name	Type & Properties	Description
--rna_uns_neighbors	string	In which .uns slot to store various neighbor output objects.
--rna_obsp_neighbor_distances	string	In which .obsp slot to store the distance matrix between the resulting neighbors.
--rna_obsp_neighbor_connectivities	string	In which .obsp slot to store the connectivities matrix between the resulting neighbors.

Name

Type & Properties

--rna_uns_neighbors

string

--rna_obsp_neighbor_distances

string

--rna_obsp_neighbor_connectivities

string

Neighbour calculation ADT

Name	Type & Properties	Description
--prot_uns_neighbors	string	In which .uns slot to store various neighbor output objects.
--prot_obsp_neighbor_distances	string	In which .obsp slot to store the distance matrix between the resulting neighbors.
--prot_obsp_neighbor_connectivities	string	In which .obsp slot to store the connectivities matrix between the resulting neighbors.

Name

Type & Properties

--prot_uns_neighbors

string

--prot_obsp_neighbor_distances

string

--prot_obsp_neighbor_connectivities

string

Clustering options RNA

Name	Type & Properties	Description
--rna_obs_cluster	string	Prefix for the .obs keys under which to add the cluster labels. Newly created columns in .obs will be created from the specified value for '--obs_cluster' suffixed with an underscore and one of the resolutions resolutions specified in '--leiden_resolution'.
--rna_leiden_resolution	double multiple	Control the coarseness of the clustering. Higher values lead to more clusters.

Name

Type & Properties

--rna_obs_cluster

string

--rna_leiden_resolution

double

multiple

Clustering options ADT

Name	Type & Properties	Description
--prot_obs_cluster	string	Prefix for the .obs keys under which to add the cluster labels. Newly created columns in .obs will be created from the specified value for '--obs_cluster' suffixed with an underscore and one of the resolutions resolutions specified in '--leiden_resolution'.
--prot_leiden_resolution	double multiple	Control the coarseness of the clustering. Higher values lead to more clusters.

Name

Type & Properties

--prot_obs_cluster

string

--prot_leiden_resolution

double

multiple

Umap options

Name	Type & Properties	Description
--obsm_umap	string	In which .obsm slot to store the resulting UMAP embedding.

Name

Type & Properties

--obsm_umap

string

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
id: "run"  
modality: [ "rna" ]  
prot_modality: [ "prot" ]  
output: "$id.$key.output.h5mu"  
reference_model_path: "$id.$key.reference_model_path"  
query_model_path: "$id.$key.query_model_path"  
obs_batch: [ "sample_id" ]  
max_epochs: [ 400 ]  
max_query_epochs: [ 200 ]  
weight_decay: [ 0 ]  
rna_reference_modality: [ "rna" ]  
rna_obsm_output: [ "X_totalvi" ]  
prot_reference_modality: [ "prot" ]  
prot_obsm_output: [ "X_totalvi" ]  
rna_uns_neighbors: [ "totalvi_integration_neighbors" ]  
rna_obsp_neighbor_distances: [ "totalvi_integration_distances" ]  
rna_obsp_neighbor_connectivities: [ "totalvi_integration_connectivities" ]  
prot_uns_neighbors: [ "totalvi_integration_neighbors" ]  
prot_obsp_neighbor_distances: [ "totalvi_integration_distances" ]  
prot_obsp_neighbor_connectivities: [ "totalvi_integration_connectivities" ]  
rna_obs_cluster: [ "totalvi_integration_leiden" ]  
rna_leiden_resolution: [ 1 ]  
prot_obs_cluster: [ "totalvi_integration_leiden" ]  
prot_leiden_resolution: [ 1 ]  
obsm_umap: [ "X_totalvi_umap" ]  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision v4.0.0 \  
  -main-script target/nextflow/workflows/integration/totalvi_scarches_leiden/main.nf \  
  -params-file params.yaml

workflows/integration/totalvi_scarches_leiden

Inputs

Outputs

General TotalVI Options

TotalVI integration options RNA

TotalVI integration options ADT

Neighbour calculation RNA

Neighbour calculation ADT

Clustering options RNA

Clustering options ADT

Umap options

Run this component

Relationships

Used by

Uses