CI
4caaaf68ef
Build pipeline: openpipelines-bio.openpipeline.v4.0.0-kd9qj
Source commit: de02293c9e
Source message: Bump version to v4.0.0
189 lines
7.1 KiB
JSON
189 lines
7.1 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"title": "svm_annotation",
|
|
"description": "Automated cell type annotation tool for scRNA-seq datasets on the basis of SVMs.",
|
|
"type": "object",
|
|
"$defs": {
|
|
"inputs": {
|
|
"title": "Inputs",
|
|
"type": "object",
|
|
"description": "Input dataset (query) arguments",
|
|
"properties": {
|
|
"input": {
|
|
"type": "string",
|
|
"format": "path",
|
|
"exists": true,
|
|
"description": "The input (query) data to be labeled",
|
|
"help_text": "Type: `file`, multiple: `False`, required, direction: `input`, example: `\"input.h5mu\"`. "
|
|
},
|
|
"modality": {
|
|
"type": "string",
|
|
"description": "Which modality to process.",
|
|
"help_text": "Type: `string`, multiple: `False`, default: `\"rna\"`. ",
|
|
"default": "rna"
|
|
},
|
|
"input_layer": {
|
|
"type": "string",
|
|
"description": "The layer in the input data to be used for cell type annotation if .X is not to be used.",
|
|
"help_text": "Type: `string`, multiple: `False`. "
|
|
},
|
|
"input_var_gene_names": {
|
|
"type": "string",
|
|
"description": "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.\n",
|
|
"help_text": "Type: `string`, multiple: `False`. "
|
|
},
|
|
"input_reference_gene_overlap": {
|
|
"type": "integer",
|
|
"description": "The minimum number of genes present in both the reference and query datasets.\n",
|
|
"help_text": "Type: `integer`, multiple: `False`, default: `100`. ",
|
|
"default": 100
|
|
},
|
|
"sanitize_ensembl_ids": {
|
|
"type": "boolean",
|
|
"description": "Whether to sanitize ensembl ids by removing version numbers.",
|
|
"help_text": "Type: `boolean`, multiple: `False`, default: `true`. ",
|
|
"default": true
|
|
}
|
|
}
|
|
},
|
|
"outputs": {
|
|
"title": "Outputs",
|
|
"type": "object",
|
|
"description": "Output arguments.",
|
|
"properties": {
|
|
"output": {
|
|
"type": "string",
|
|
"format": "path",
|
|
"description": "Output h5mu file.",
|
|
"help_text": "Type: `file`, multiple: `False`, default: `\"$id.$key.output.h5mu\"`, direction: `output`, example: `\"output.h5mu\"`. ",
|
|
"default": "$id.$key.output.h5mu"
|
|
},
|
|
"output_obs_prediction": {
|
|
"type": "string",
|
|
"description": "In which `.obs` slots to store the predicted information.\n",
|
|
"help_text": "Type: `string`, multiple: `False`, default: `\"svm_pred\"`. ",
|
|
"default": "svm_pred"
|
|
},
|
|
"output_obs_probability": {
|
|
"type": "string",
|
|
"description": "In which `.obs` slots to store the probability of the predictions.\n",
|
|
"help_text": "Type: `string`, multiple: `False`, default: `\"svm_probability\"`. ",
|
|
"default": "svm_probability"
|
|
},
|
|
"output_compression": {
|
|
"type": "string",
|
|
"description": "Compression format to use for the output AnnData and/or Mudata objects.\nBy default no compression is applied.\n",
|
|
"help_text": "Type: `string`, multiple: `False`, example: `\"gzip\"`, choices: ``gzip`, `lzf``. ",
|
|
"enum": [
|
|
"gzip",
|
|
"lzf"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"reference": {
|
|
"title": "Reference",
|
|
"type": "object",
|
|
"description": "Arguments related to the reference dataset.",
|
|
"properties": {
|
|
"reference": {
|
|
"type": "string",
|
|
"format": "path",
|
|
"description": "The reference data to train the CellTypist classifiers on",
|
|
"help_text": "Type: `file`, multiple: `False`, direction: `input`, example: `\"reference.h5mu\"`. "
|
|
},
|
|
"reference_layer": {
|
|
"type": "string",
|
|
"description": "The layer in the reference data to be used for cell type annotation if .X is not to be used",
|
|
"help_text": "Type: `string`, multiple: `False`. "
|
|
},
|
|
"reference_obs_target": {
|
|
"type": "string",
|
|
"description": "Key in .obs attribute of reference modality with cell-type information.\n",
|
|
"help_text": "Type: `string`, multiple: `False`, required. "
|
|
},
|
|
"reference_var_gene_names": {
|
|
"type": "string",
|
|
"description": "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.\n",
|
|
"help_text": "Type: `string`, multiple: `False`. "
|
|
},
|
|
"reference_var_input": {
|
|
"type": "string",
|
|
"description": ".var column containing highly variable genes",
|
|
"help_text": "Type: `string`, multiple: `False`. "
|
|
}
|
|
}
|
|
},
|
|
"model arguments": {
|
|
"title": "Model arguments",
|
|
"type": "object",
|
|
"description": "Model arguments.",
|
|
"properties": {
|
|
"model": {
|
|
"type": "string",
|
|
"format": "path",
|
|
"description": "Pretrained model in pkl format",
|
|
"help_text": "Type: `file`, multiple: `False`, direction: `input`, example: `\"pretrained_model.pkl\"`. "
|
|
},
|
|
"feature_selection": {
|
|
"type": "boolean",
|
|
"description": "Whether to perform feature selection.",
|
|
"help_text": "Type: `boolean`, multiple: `False`, default: `true`. ",
|
|
"default": true
|
|
},
|
|
"max_iter": {
|
|
"type": "integer",
|
|
"description": "Maximum number of iterations for the SVM.",
|
|
"help_text": "Type: `integer`, multiple: `False`, default: `5000`. ",
|
|
"default": 5000
|
|
},
|
|
"c_reg": {
|
|
"type": "number",
|
|
"description": "Regularization parameter for the SVM.",
|
|
"help_text": "Type: `double`, multiple: `False`, default: `1.0`. ",
|
|
"default": 1.0
|
|
},
|
|
"class_weight": {
|
|
"type": "string",
|
|
"description": "\"Class weights for the SVM",
|
|
"help_text": "Type: `string`, multiple: `False`, default: `\"balanced\"`, choices: ``balanced`, `uniform``. ",
|
|
"enum": [
|
|
"balanced",
|
|
"uniform"
|
|
],
|
|
"default": "balanced"
|
|
}
|
|
}
|
|
},
|
|
"nextflow input-output arguments": {
|
|
"title": "Nextflow input-output arguments",
|
|
"type": "object",
|
|
"description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.",
|
|
"properties": {
|
|
"publish_dir": {
|
|
"type": "string",
|
|
"description": "Path to an output directory.",
|
|
"help_text": "Type: `string`, multiple: `False`, required, example: `\"output/\"`. "
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/$defs/inputs"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/outputs"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/reference"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/model arguments"
|
|
},
|
|
{
|
|
"$ref": "#/$defs/nextflow input-output arguments"
|
|
}
|
|
]
|
|
}
|