CI
cd0af18851
Build pipeline: vsh-ci-dev-k8tz4
Source commit: 2dbe3b7231
Source message: Fix pointers to test resources
270 lines
9.9 KiB
JSON
270 lines
9.9 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-07/schema",
|
|
"title": "onclass",
|
|
"description": "OnClass is a python package for single-cell cell type annotation. It uses the Cell Ontology to capture the cell type similarity. \nThese similarities enable OnClass to annotate cell types that are never seen in the training data.\n",
|
|
"type": "object",
|
|
"definitions": {
|
|
|
|
|
|
|
|
"inputs" : {
|
|
"title": "Inputs",
|
|
"type": "object",
|
|
"description": "Input dataset (query) arguments",
|
|
"properties": {
|
|
|
|
|
|
"input": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, required, example: `input.h5mu`. The input (query) data to be labeled",
|
|
"help_text": "Type: `file`, required, example: `input.h5mu`. The input (query) data to be labeled. Should be a .h5mu file."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"modality": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, default: `rna`. Which modality to process",
|
|
"help_text": "Type: `string`, default: `rna`. Which modality to process."
|
|
,
|
|
"default": "rna"
|
|
}
|
|
|
|
|
|
,
|
|
"input_layer": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`. The layer in the input data to be used for cell type annotation if ",
|
|
"help_text": "Type: `string`. The layer in the input data to be used for cell type annotation if .X is not to be used."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"cl_nlp_emb_file": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, required. The ",
|
|
"help_text": "Type: `file`, required. The .nlp.emb file with the cell type embeddings."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"cl_ontology_file": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, required. The ",
|
|
"help_text": "Type: `file`, required. The .ontology file with the cell type ontology."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"cl_obo_file": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, required. The ",
|
|
"help_text": "Type: `file`, required. The .obo file with the cell type ontology."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"var_query_gene_names": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `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",
|
|
"help_text": "Type: `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.\n"
|
|
|
|
}
|
|
|
|
|
|
}
|
|
},
|
|
|
|
|
|
"outputs" : {
|
|
"title": "Outputs",
|
|
"type": "object",
|
|
"description": "Output arguments.",
|
|
"properties": {
|
|
|
|
|
|
"output": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, default: `$id.$key.output.h5mu`, example: `output.h5mu`. Output h5mu file",
|
|
"help_text": "Type: `file`, default: `$id.$key.output.h5mu`, example: `output.h5mu`. Output h5mu file."
|
|
,
|
|
"default": "$id.$key.output.h5mu"
|
|
}
|
|
|
|
|
|
,
|
|
"output_compression": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, example: `gzip`, choices: ``gzip`, `lzf``. ",
|
|
"help_text": "Type: `string`, example: `gzip`, choices: ``gzip`, `lzf``. ",
|
|
"enum": ["gzip", "lzf"]
|
|
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"output_obs_predictions": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, default: `onclass_pred`. In which `",
|
|
"help_text": "Type: `string`, default: `onclass_pred`. In which `.obs` slots to store the predicted information.\n"
|
|
,
|
|
"default": "onclass_pred"
|
|
}
|
|
|
|
|
|
,
|
|
"output_obs_probability": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, default: `onclass_prob`. In which `",
|
|
"help_text": "Type: `string`, default: `onclass_prob`. In which `.obs` slots to store the probability of the predictions.\n"
|
|
,
|
|
"default": "onclass_prob"
|
|
}
|
|
|
|
|
|
}
|
|
},
|
|
|
|
|
|
"reference" : {
|
|
"title": "Reference",
|
|
"type": "object",
|
|
"description": "Arguments related to the reference dataset.",
|
|
"properties": {
|
|
|
|
|
|
"reference": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `file`, example: `reference.h5mu`. The reference data to train the CellTypist classifiers on",
|
|
"help_text": "Type: `file`, example: `reference.h5mu`. The reference data to train the CellTypist classifiers on. Only required if a pre-trained --model is not provided."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"reference_layer": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`. The layer in the reference data to be used for cell type annotation if ",
|
|
"help_text": "Type: `string`. The layer in the reference data to be used for cell type annotation if .X is not to be used."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"reference_obs_target": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, required, example: `cell_ontology_class`. The name of the adata obs column in the reference data containing cell type annotations",
|
|
"help_text": "Type: `string`, required, example: `cell_ontology_class`. The name of the adata obs column in the reference data containing cell type annotations."
|
|
|
|
}
|
|
|
|
|
|
}
|
|
},
|
|
|
|
|
|
"model arguments" : {
|
|
"title": "Model arguments",
|
|
"type": "object",
|
|
"description": "Model arguments",
|
|
"properties": {
|
|
|
|
|
|
"model": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`. \"Pretrained model path without a file extension",
|
|
"help_text": "Type: `string`. \"Pretrained model path without a file extension. If not provided, the model will be trained \non the reference data and --reference should be provided. The path namespace should contain:\n - a .npz or .pkl file\n - a .data file\n - a .meta file\n - a .index file\ne.g. /path/to/model/pretrained_model_target1 as saved by OnClass.\"\n"
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"max_iter": {
|
|
"type":
|
|
"integer",
|
|
"description": "Type: `integer`, default: `30`. Maximum number of iterations for training the model",
|
|
"help_text": "Type: `integer`, default: `30`. Maximum number of iterations for training the model."
|
|
,
|
|
"default": "30"
|
|
}
|
|
|
|
|
|
}
|
|
},
|
|
|
|
|
|
"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": "Type: `string`, required, example: `output/`. Path to an output directory",
|
|
"help_text": "Type: `string`, required, example: `output/`. Path to an output directory."
|
|
|
|
}
|
|
|
|
|
|
,
|
|
"param_list": {
|
|
"type":
|
|
"string",
|
|
"description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel",
|
|
"help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.",
|
|
"hidden": true
|
|
|
|
}
|
|
|
|
|
|
}
|
|
}
|
|
},
|
|
"allOf": [
|
|
|
|
{
|
|
"$ref": "#/definitions/inputs"
|
|
},
|
|
|
|
{
|
|
"$ref": "#/definitions/outputs"
|
|
},
|
|
|
|
{
|
|
"$ref": "#/definitions/reference"
|
|
},
|
|
|
|
{
|
|
"$ref": "#/definitions/model arguments"
|
|
},
|
|
|
|
{
|
|
"$ref": "#/definitions/nextflow input-output arguments"
|
|
}
|
|
]
|
|
}
|