annotate/consensus_vote

Description

Combines cell type predictions from multiple annotation methods into a single consensus prediction using a weighted majority vote.
For each cell, each method votes for its predicted cell type, optionally weighted by the probability score and/or a per-method weight.
The consensus prediction is the cell type with the highest total weighted vote.
Note that this method does not leverage pre-existing ontology or perform any reconciliation of cell type labels across methods, so the same cell type may be represented by different labels in different methods and will be treated as distinct cell types in the vote.

Type

python_script

License

MIT

Links

Repository

Contributors

Launch

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
modality: [ "rna" ]  
output: "$id.$key.output.h5mu"  
output_obs_predictions: [ "consensus_pred" ]  
output_obs_score: [ "consensus_score" ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision v4.2.0 \  
  -main-script target/nextflow/annotate/consensus_vote/main.nf \  
  -params-file params.yaml

Inputs

Name	Type & Properties	Description
--input	file required	Input h5mu file containing cell type predictions in .obs.
--modality	string	Which modality to process.
--input_obs_predictions	string required multiple	One or more .obs column names containing cell type predictions (labels) from different annotation methods.
--input_obs_probabilities	string multiple	One or more .obs column names containing prediction probability scores, one per method in --input_obs_predictions. When provided, each method's vote is scaled by the probability score for that cell (in addition to any per-method --weights). Must be the same length as --input_obs_predictions.
--tie_label	string	Label to assign when two or more cell types receive equal votes. If not provided, tied cells are assigned None (missing value).
--weights	double multiple	Per-method weights for the consensus vote. Must be the same length as --input_obs_predictions when provided. Weights are normalized to sum to 1 before use. If not provided, all methods are weighted equally.

Name

Type & Properties

--input

file

required

--modality

string

--input_obs_predictions

string

required

multiple

--input_obs_probabilities

string

multiple

--tie_label

string

--weights

double

multiple

Outputs

Name	Type & Properties	Description
--output -o	file output	Output h5mu file.
--output_obs_predictions	string	In which `.obs` slot to store the consensus predicted cell type.
--output_obs_score	string	In which `.obs` slot to store the consensus score, defined as the fraction of total weight assigned to the winning cell type.
--output_compression	string	Compression format to use for the output AnnData and/or Mudata H5 files. By default no compression is applied.

Name

Type & Properties

--output

-o

file

output

--output_obs_predictions

string

--output_obs_score

string

--output_compression

string