Scanvi

scANVI () is a semi-supervised model for single-cell transcriptomics data.

Info

ID: scanvi
Namespace: annotate

scANVI is an scVI extension that can leverage the cell type knowledge for a subset of the cells present in the data sets to infer the states of the rest of the cells. This component will instantiate a scANVI model from a pre-trained scVI model, integrate the data and perform label prediction

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/annotate/scanvi/main.nf \
  --help

Run command

Example of params.yaml 
# Inputs
input: # please fill in - example: "path/to/file"
modality: "rna"
# input_layer: "foo"
# var_input: "foo"
# var_gene_names: "foo"
obs_labels: # please fill in - example: "foo"
unlabeled_category: "Unknown"

# scVI Model
scvi_model: # please fill in - example: "scvi_model.pt"

# Outputs
# output: "$id.$key.output"
# output_model: "$id.$key.output_model"
# output_compression: "gzip"
obsm_output: "X_scanvi_integrated"
obs_output_predictions: "scanvi_pred"
obs_output_probabilities: "scanvi_proba"

# scANVI training arguments
# early_stopping: true
early_stopping_monitor: "elbo_validation"
early_stopping_patience: 45
early_stopping_min_delta: 0.0
# max_epochs: 123
reduce_lr_on_plateau: true
lr_factor: 0.6
lr_patience: 30.0

# Nextflow input-output arguments
publish_dir: # please fill in - example: "output/"
# param_list: "my_params.yaml"

# Arguments
nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -profile docker \
  -main-script target/nextflow/annotate/scanvi/main.nf \
  -params-file params.yaml
Note

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

Argument groups

Inputs

Name Description Attributes
--input Input h5mu file. Note that this needs to be the exact same dataset as the –scvi_model was trained on. file, required
--modality string, default: "rna"
--input_layer Input layer to use. If None, X is used string
--var_input .var column containing highly variable genes that were used to train the scVi model. By default, do not subset genes. string
--var_gene_names .var column containing gene names. By default, use the index. string
--obs_labels .obs field containing the labels string, required
--unlabeled_category Value in the –obs_labels field that indicates unlabeled observations string, default: "Unknown"

scVI Model

Name Description Attributes
--scvi_model Pretrained SCVI reference model to initialize the SCANVI model with. file, required, example: "scvi_model.pt"

Outputs

Name Description Attributes
--output Output h5mu file. file, required
--output_model Folder where the state of the trained model will be saved to. file
--output_compression The compression format to be used on the output h5mu object. string, example: "gzip"
--obsm_output In which .obsm slot to store the resulting integrated embedding. string, default: "X_scanvi_integrated"
--obs_output_predictions In which .obs slot to store the predicted labels. string, default: "scanvi_pred"
--obs_output_probabilities In which. obs slot to store the probabilities of the predicted labels. string, default: "scanvi_proba"

scANVI training arguments

Name Description Attributes
--early_stopping Whether to perform early stopping with respect to the validation set. boolean
--early_stopping_monitor Metric logged during validation set epoch. string, default: "elbo_validation"
--early_stopping_patience Number of validation epochs with no improvement after which training will be stopped. integer, default: 45
--early_stopping_min_delta 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. double, default: 0
--max_epochs Number of passes through the dataset, defaults to (20000 / number of cells) * 400 or 400; whichever is smallest. integer
--reduce_lr_on_plateau Whether to monitor validation loss and reduce learning rate when validation set lr_scheduler_metric plateaus. boolean, default: TRUE
--lr_factor Factor to reduce learning rate. double, default: 0.6
--lr_patience Number of epochs with no improvement after which learning rate will be reduced. double, default: 30

Authors

  • Dorien Roosen (maintainer)

  • Jakub Majercik (author)

  • Weiwei Schultz (contributor)