Onclass

OnClass is a python package for single-cell cell type annotation.

Info

ID: onclass
Namespace: annotate

Links

Source

It uses the Cell Ontology to capture the cell type similarity. These similarities enable OnClass to annotate cell types that are never seen in the training data

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/onclass/main.nf \
  --help

Run command

Example of params.yaml

# Inputs
input: # please fill in - example: "input.h5mu"
modality: "rna"
# input_layer: "foo"
# input_var_gene_names: "foo"
input_reference_gene_overlap: 100

# Ongoloty
cl_nlp_emb_file: # please fill in - example: "path/to/file"
cl_ontology_file: # please fill in - example: "path/to/file"
cl_obo_file: # please fill in - example: "path/to/file"

# Reference
# reference: "reference.h5mu"
# reference_layer: "foo"
reference_obs_target: # please fill in - example: "cell_ontology_class"
# reference_var_gene_names: "foo"
# reference_var_input: "foo"
unknown_celltype: "Unknown"

# Outputs
# output: "$id.$key.output.h5mu"
# output_compression: "gzip"
output_obs_predictions: "onclass_pred"
output_obs_probability: "onclass_prob"

# Model arguments
# model: "foo"
max_iter: 30

# 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/onclass/main.nf \
  -params-file params.yaml

Note

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

Argument groups

Inputs

Input dataset (query) arguments

Name	Description	Attributes
--input	The input (query) data to be labeled. Should be a .h5mu file.	file, required, example: "input.h5mu"
--modality	Which modality to process.	string, default: "rna"
--input_layer	The layer in the input data to be used for cell type annotation if .X is not to be used.	string
--input_var_gene_names	The name of the adata var column in the input data containing gene names; when no gene_name_layer is provided, the var index will be used.	string
--input_reference_gene_overlap	The minimum number of genes present in both the reference and query datasets.	integer, default: 100

Ongoloty

Ontology input files

Name	Description	Attributes
--cl_nlp_emb_file	The .nlp.emb file with the cell type embeddings.	file, required
--cl_ontology_file	The .ontology file with the cell type ontology.	file, required
--cl_obo_file	The .obo file with the cell type ontology.	file, required

Reference

Arguments related to the reference dataset.

Name	Description	Attributes
--reference	The reference data to train the CellTypist classifiers on. Only required if a pre-trained –model is not provided.	file, example: "reference.h5mu"
--reference_layer	The layer in the reference data to be used for cell type annotation if .X is not to be used.	string
--reference_obs_target	The name of the adata obs column in the reference data containing cell type annotations.	string, required, example: "cell_ontology_class"
--reference_var_gene_names	The name of the adata var column in the reference data containing gene names; when no gene_name_layer is provided, the var index will be used.	string
--reference_var_input	.var column containing highly variable genes. By default, do not subset genes.	string
--unknown_celltype	Label for unknown cell types.	string, default: "Unknown"

Outputs

Output arguments.

Name	Description	Attributes
--output	Output h5mu file.	file, example: "output.h5mu"
--output_compression		string, example: "gzip"
--output_obs_predictions	In which .obs slots to store the predicted information.	string, default: "onclass_pred"
--output_obs_probability	In which .obs slots to store the probability of the predictions.	string, default: "onclass_prob"

Model arguments

Model arguments

Name	Description	Attributes
--model	“Pretrained model path without a file extension. If not provided, the model will be trained on the reference data and –reference should be provided. The path namespace should contain: - a .npz or .pkl file - a .data file - a .meta file - a .index file e.g. /path/to/model/pretrained_model_target1 as saved by OnClass.”	string
--max_iter	Maximum number of iterations for training the model.	integer, default: 30

Authors

• Jakub Majercik (author)