workflows/annotation/scvi_knn

Description

"Cell type annotation workflow that performs scVI integration of reference and query dataset followed by KNN label transfer.
The query and reference datasets are expected to be pre-processed in the same way, for example with the process_samples workflow of OpenPipeline.
Note that this workflow will integrate the reference dataset from scratch and integrate the query dataset in the same embedding space.
The workflow does not currently output the trained SCVI reference model."

Query Input

Name	Type & Properties	Description
--id	string required	ID of the sample.
--input	file required	Input dataset consisting of the (unlabeled) query observations.
--modality	string	Which modality to process. Should match the modality of the --reference dataset.
--input_layer	string	The layer of the input dataset containing the raw counts if .X is not to be used.
--input_layer_lognormalized	string	The layer of the input dataset containing the lognormalized counts if .X is not to be used.
--input_obs_batch_label	string required	The .obs field in the input (query) dataset containing the batch labels.
--input_var_gene_names	string	The .var field in the input (query) dataset containing gene names; if not provided, the .var index will be used.
--input_reference_gene_overlap	integer	The minimum number of genes present in both the reference and query datasets.
--overwrite_existing_key	boolean_true	If provided, will overwrite existing fields in the input dataset when data are copied during the reference alignment process.
--sanitize_ensembl_ids	boolean	Whether to sanitize ensembl ids by removing version numbers.

Name

Type & Properties

--id

string

required

--input

file

required

--modality

string

--input_layer

string

--input_layer_lognormalized

string

--input_obs_batch_label

string

required

--input_var_gene_names

string

--input_reference_gene_overlap

integer

--overwrite_existing_key

boolean_true

--sanitize_ensembl_ids

boolean

Reference input

Name	Type & Properties	Description
--reference	file required	Reference dataset consisting of the labeled observations.
--reference_layer	string	The layer of the reference dataset containing the raw counts if .X is not to be used.
--reference_layer_lognormalized	string	The layer of the reference dataset containing the lognormalized counts if .X is not to be used.
--reference_obs_target	string required	The `.obs` key(s) of the target labels to transfer.
--reference_var_gene_names	string	The .var field in the reference dataset containing gene names; if not provided, the .var index will be used.
--reference_obs_batch_label	string required	The .obs field in the reference dataset containing the batch labels.

Name

Type & Properties

--reference

file

required

--reference_layer

string

--reference_layer_lognormalized

string

--reference_obs_target

string

required

--reference_var_gene_names

string

--reference_obs_batch_label

string

required

HVG subset arguments

Name	Type & Properties	Description
--n_hvg	integer	Number of highly variable genes to subset for.

Name

Type & Properties

--n_hvg

integer

scVI integration options

Name	Type & Properties	Description
--scvi_early_stopping	boolean	Whether to perform early stopping with respect to the validation set.
--scvi_early_stopping_monitor	string	Metric logged during validation set epoch.
--scvi_early_stopping_patience	integer	Number of validation epochs with no improvement after which training will be stopped.
--scvi_early_stopping_min_delta	double	Minimum change in the monitored quantity to qualify as an improvement, i.e. an absolute change of less than min_delta, will count as no improvement.
--scvi_max_epochs	integer	Number of passes through the dataset, defaults to (20000 / number of cells) * 400 or 400; whichever is smallest.
--scvi_reduce_lr_on_plateau	boolean	Whether to monitor validation loss and reduce learning rate when validation set `lr_scheduler_metric` plateaus.
--scvi_lr_factor	double	Factor to reduce learning rate.
--scvi_lr_patience	double	Number of epochs with no improvement after which learning rate will be reduced.

Name

Type & Properties

--scvi_early_stopping

boolean

--scvi_early_stopping_monitor

string

--scvi_early_stopping_patience

integer

--scvi_early_stopping_min_delta

double

--scvi_max_epochs

integer

--scvi_reduce_lr_on_plateau

boolean

--scvi_lr_factor

double

--scvi_lr_patience

double

Leiden clustering options

Name	Type & Properties	Description
--leiden_resolution	double multiple	Control the coarseness of the clustering. Higher values lead to more clusters.

Name

Type & Properties

--leiden_resolution

double

multiple

Neighbor classifier arguments

Name	Type & Properties	Description
--knn_weights	string	Weight function used in prediction. Possible values are: `uniform` (all points in each neighborhood are weighted equally) or `distance` (weight points by the inverse of their distance)
--knn_n_neighbors	integer	The number of neighbors to use in k-neighbor graph structure used for fast approximate nearest neighbor search with PyNNDescent. Larger values will result in more accurate search results at the cost of computation time.

Name

Type & Properties

--knn_weights

string

--knn_n_neighbors

integer

Outputs

Name	Type & Properties	Description
--output	file required output	The query data in .h5mu format with predicted labels predicted from the classifier trained on the reference.
--output_obs_predictions	string multiple	In which `.obs` slots to store the predicted cell labels. If provided, must have the same length as `--reference_obs_targets`. If empty, will default to the `reference_obs_targets` combined with the `"_pred"` suffix.
--output_obs_probability	string multiple	In which `.obs` slots to store the probability of the predictions. If provided, must have the same length as `--reference_obs_targets`. If empty, will default to the `reference_obs_targets` combined with the `"_probability"` suffix.
--output_obsm_integrated	string	In which .obsm slot to store the integrated embedding.

Name

Type & Properties

--output

file

required

output

--output_obs_predictions

string

multiple

--output_obs_probability

string

multiple

--output_obsm_integrated

string

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
id: "run"  
modality: [ "rna" ]  
input_reference_gene_overlap: [ 100 ]  
sanitize_ensembl_ids: [ true ]  
n_hvg: [ 2000 ]  
scvi_early_stopping_monitor: [ "elbo_validation" ]  
scvi_early_stopping_patience: [ 45 ]  
scvi_early_stopping_min_delta: [ 0 ]  
scvi_reduce_lr_on_plateau: [ true ]  
scvi_lr_factor: [ 0.6 ]  
scvi_lr_patience: [ 30 ]  
leiden_resolution: [ 1 ]  
knn_weights: [ "uniform" ]  
knn_n_neighbors: [ 15 ]  
output: "$id.$key.output.h5mu"  
output_obsm_integrated: [ "X_integrated_scvi" ]  
publish_dir: "output/"  
EOM

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

workflows/annotation/scvi_knn

Query Input

Reference input

HVG subset arguments

scVI integration options

Leiden clustering options

Neighbor classifier arguments

Outputs

Run this component

Relationships

Used by

Uses