labels_transfer/xgboost

Description

Performs label transfer from reference to query using XGBoost classifier

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" ]  
reference_obs_targets:  
  [  
    "ann_level_1",  
    "ann_level_2",  
    "ann_level_3",  
    "ann_level_4",  
    "ann_level_5",  
    "ann_finest_level"  
  ]  
output: "$id.$key.output"  
use_gpu: [ false ]  
verbosity: [ 1 ]  
model_output: "$id.$key.model_output"  
output_uns_parameters: [ "xgboost_parameters" ]  
learning_rate: [ 0.3 ]  
min_split_loss: [ 0 ]  
max_depth: [ 6 ]  
min_child_weight: [ 1 ]  
max_delta_step: [ 0 ]  
subsample: [ 1 ]  
sampling_method: [ "uniform" ]  
colsample_bytree: [ 1 ]  
colsample_bylevel: [ 1 ]  
colsample_bynode: [ 1 ]  
reg_lambda: [ 1 ]  
reg_alpha: [ 0 ]  
scale_pos_weight: [ 1 ]  
id: "run"  
publish_dir: "output/"  
EOM

nextflow run https://packages.viash-hub.com/vsh/openpipeline.git \  
  -revision v4.0.3 \  
  -main-script target/nextflow/labels_transfer/xgboost/main.nf \  
  -params-file params.yaml

Input dataset (query) arguments

Name	Type & Properties	Description
--input	file required	The query data to transfer the labels to. Should be a .h5mu file.
--modality	string	Which modality to use.
--input_obsm_features	string	The `.obsm` key of the embedding to use for the classifier's inference. If not provided, the `.X` slot will be used instead. Make sure that embedding was obtained in the same way as the reference embedding (e.g. by the same model or preprocessing).

Name

Type & Properties

--input

file

required

--modality

string

--input_obsm_features

string

Reference dataset arguments

Name	Type & Properties	Description
--reference	file	The reference data to train classifiers on.
--reference_obsm_features	string	The `.obsm` key of the embedding to use for the classifier's training. If not provided, the `.X` slot will be used instead. Make sure that embedding was obtained in the same way as the query embedding (e.g. by the same model or preprocessing).
--reference_obs_targets	string multiple	The `.obs` key(s) of the target labels to tranfer.

Name

Type & Properties

--reference

file

--reference_obsm_features

string

--reference_obs_targets

string

multiple

Outputs

Name	Type & Properties	Description
--output	file required output	The query data in .h5mu format with predicted labels transfered from the reference.
--output_obs_predictions	string multiple	In which `.obs` slots to store the predicted information. 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_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

required

output

--output_obs_predictions

string

multiple

--output_obs_probability

string

multiple

--output_compression

string

Execution arguments

Name	Type & Properties	Description
--force_retrain -f	boolean_true	Retrain models on the reference even if model_output directory already has trained classifiers. WARNING! It will rewrite existing classifiers for targets in the model_output directory!
--use_gpu	boolean	Use GPU during models training and inference (recommended).
--verbosity -v	integer	The verbosity level for evaluation of the classifier from the range [0,2]
--model_output	file output	Output directory for model
--output_uns_parameters	string	The key in `uns` slot of the output AnnData object to store the parameters of the XGBoost classifier.

Name

Type & Properties

--force_retrain

-f

boolean_true

--use_gpu

boolean

--verbosity

-v

integer

--model_output

file

output

--output_uns_parameters

string

Learning parameters

Name	Type & Properties	Description
--learning_rate --eta	double	Step size shrinkage used in update to prevents overfitting. Range: [0,1]. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--min_split_loss --gamma	double	Minimum loss reduction required to make a further partition on a leaf node of the tree. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--max_depth -d	integer	Maximum depth of a tree. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--min_child_weight	integer	Minimum sum of instance weight (hessian) needed in a child. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--max_delta_step	double	Maximum delta step we allow each leaf output to be. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--subsample	double	Subsample ratio of the training instances. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--sampling_method	string	The method to use to sample the training instances. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--colsample_bytree	double	Fraction of columns to be subsampled. Range (0, 1]. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--colsample_bylevel	double	Subsample ratio of columns for each level. Range (0, 1]. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--colsample_bynode	double	Subsample ratio of columns for each node (split). Range (0, 1]. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--reg_lambda --lambda	double	L2 regularization term on weights. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--reg_alpha --alpha	double	L1 regularization term on weights. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference
--scale_pos_weight	double	Control the balance of positive and negative weights, useful for unbalanced classes. See https://xgboost.readthedocs.io/en/stable/parameter.html#parameters-for-tree-booster for the reference

Name

Type & Properties

--learning_rate

--eta

double

--min_split_loss

--gamma

double

--max_depth

-d

integer

--min_child_weight

integer

--max_delta_step

double

--subsample

double

--sampling_method

string

--colsample_bytree

double

--colsample_bylevel

double

--colsample_bynode

double

--reg_lambda

--lambda

double

--reg_alpha

--alpha

double

--scale_pos_weight

double