annotate/singler

Description

SingleR performs reference-based cell type annotation for single-cell RNA-seq data
by computing Spearman correlations between test cells and reference samples with known labels,
using marker genes to assign the most similar cell type label to each new cell.

Inputs

Name	Type & Properties	Description
--input -i	file required	The input (query) data to be labeled. Should be a .h5mu file.
--modality	string	Which modality to process.
--input_layer	string	The layer in the input data containing log normalized counts to be used for cell type annotation if .X is not to be used.
--input_var_gene_names	string	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.
--input_obs_clusters	string	The name of the adata .obs column containing cluster identities of the observations. If provided, annoation is performed on the aggregated cluster profiles, otherwise it defaults to annotation per observation.
--input_reference_gene_overlap	integer	The minimum number of genes present in both the reference and query datasets.

Name

Type & Properties

--input

-i

file

required

--modality

string

--input_layer

string

--input_var_gene_names

string

--input_obs_clusters

string

--input_reference_gene_overlap

integer

Reference

Name	Type & Properties	Description
--reference	file required	The reference data to train the CellTypist classifiers on. Only required if a pre-trained --model is not provided.
--reference_layer	string	The layer in the reference data containing lognormalized couns to be used for cell type annotation if .X is not to be used. Data are expected to be processed in the same way as the --input query dataset.
--reference_obs_target	string required	The name of the adata obs column in the reference data containing cell type annotations.
--reference_var_gene_names	string	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.
--reference_var_input	string	.var column containing a boolean mask corresponding to genes to be used for marker selection. By default, do not subset genes.

Name

Type & Properties

--reference

file

required

--reference_layer

string

--reference_obs_target

string

required

--reference_var_gene_names

string

--reference_var_input

string

Arguments

Name	Type & Properties	Description
--de_n_genes	integer	The number of differentially expressed genes across labels to be calculated from the reference. Defaults to 500 * (2/3) ^ log2(N) where N is the number of unique labels when if `--de_method` is set to `classic`, otherwise, defaults to 10.
--de_method	string	Method to detect differentially expressed genes between pairs of labels.
--quantile	double	The quantile of the correlation distribution to use to compute the score per label.
--fine_tune	boolean	Whether finetuning should be performed to improve the resolution. If set to True, an additional finetuning step is performed after initial classification, new marker genes are calculated based on all cells with a score higher then the maximum score minus `--fine_tuning_thershold`, and the calculation of the scores is repeated.
--fine_tuning_threshold	double	The maximum difference from the maximum correlation to use in fine-tuning
--prune	boolean	Whether label pruning should be performed. If set to True, an additional output .obs field `--output_obs_pruned_predictions` will be added to the `--output`, containing labels where 'low-quality' labels are replaced with NA's. Labels are considered 'low-quality' when their delta score (stored in `--output_obs_delta_next`) fall more than 3 median absolute deviations below the median for that label type.
--sanitize_ensembl_ids	boolean	Whether to sanitize ensembl ids by removing version numbers.

Name

Type & Properties

--de_n_genes

integer

--de_method

string

--quantile

double

--fine_tune

boolean

--fine_tuning_threshold

double

--prune

boolean

--sanitize_ensembl_ids

boolean

Outputs

Name	Type & Properties	Description
--output	file output	Output h5mu file.
--output_obs_predictions	string	In which `.obs` slot to store the predicted labels. If `--fine_tune False`, this is based only on the maximum entry in `--output_obsm_scores`.
--output_obs_probability	string	In which `.obs` slots to store the probability of the predicted labels.
--output_obs_delta_next	string	In which `.obs` slot to store the delta between the best and next-best score. If `--fine_tune True`, this is reported for scores after fine-tuning.
--output_obs_pruned_predictions	string	In which `.obs` slot to store the pruned labels, where low-quality labels are replaced with NA's. Only added if `--prune True`.
--output_obsm_scores	string	In which `.obsm` slot to store the matrix of prediction correlations at the specified quantile for each label (column) in each cell (row).
--output_compression	string	Compression format to use for the output AnnData and/or Mudata objects. By default no compression is applied.

Name

Type & Properties

--output

file

output

--output_obs_predictions

string

--output_obs_probability

string

--output_obs_delta_next

string

--output_obs_pruned_predictions

string

--output_obsm_scores

string

--output_compression

string

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
modality: [ "rna" ]  
input_reference_gene_overlap: [ 100 ]  
de_method: [ "classic" ]  
quantile: [ 0.8 ]  
fine_tune: [ true ]  
fine_tuning_threshold: [ 0.05 ]  
prune: [ true ]  
sanitize_ensembl_ids: [ true ]  
output: "$id.$key.output.h5mu"  
output_obs_predictions: [ "singler_pred" ]  
output_obs_probability: [ "singler_probability" ]  
output_obs_delta_next: [ "singler_delta_next" ]  
output_obs_pruned_predictions: [ "singler_pruned_labels" ]  
output_obsm_scores: [ "singler_scores" ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision v4.0.2 \  
  -main-script target/nextflow/annotate/singler/main.nf \  
  -params-file params.yaml

annotate/singler

Inputs

Reference

Arguments

Outputs

Run this component

Relationships

Used by

Uses