highly_variable_genes
Identify and annotate highly variable genes from single-cell RNA sequencing data, enabling focused analysis on key genes using configurable dispersion and expression cutoffs.
Instructions
Annotate highly variable genes
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| batch_key | No | Key in adata.obs for batch information. | |
| check_values | No | Check if counts are integers for seurat_v3 flavor. | |
| flavor | No | Method for identifying highly variable genes. | seurat |
| layer | No | If provided, use adata.layers[layer] for expression values. | |
| max_disp | No | Maximum dispersion cutoff for gene selection. | |
| max_mean | No | Maximum mean expression cutoff for gene selection. | |
| min_disp | No | Minimum dispersion cutoff for gene selection. | |
| min_mean | No | Minimum mean expression cutoff for gene selection. | |
| n_bins | No | Number of bins for mean expression binning. | |
| n_top_genes | No | Number of highly-variable genes to keep. Mandatory if `flavor='seurat_v3' | |
| span | No | Fraction of data used for loess model fit in seurat_v3. | |
| subset | No | Inplace subset to highly-variable genes if True. |
Input Schema (JSON Schema)
{
"description": "Input schema for the highly_variable_genes preprocessing tool.",
"properties": {
"batch_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Key in adata.obs for batch information.",
"title": "Batch Key"
},
"check_values": {
"default": true,
"description": "Check if counts are integers for seurat_v3 flavor.",
"title": "Check Values",
"type": "boolean"
},
"flavor": {
"default": "seurat",
"description": "Method for identifying highly variable genes.",
"enum": [
"seurat",
"cell_ranger",
"seurat_v3",
"seurat_v3_paper"
],
"title": "Flavor",
"type": "string"
},
"layer": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "If provided, use adata.layers[layer] for expression values.",
"title": "Layer"
},
"max_disp": {
"default": null,
"description": "Maximum dispersion cutoff for gene selection.",
"title": "Max Disp",
"type": "number"
},
"max_mean": {
"default": 3,
"description": "Maximum mean expression cutoff for gene selection.",
"title": "Max Mean",
"type": "number"
},
"min_disp": {
"default": 0.5,
"description": "Minimum dispersion cutoff for gene selection.",
"title": "Min Disp",
"type": "number"
},
"min_mean": {
"default": 0.0125,
"description": "Minimum mean expression cutoff for gene selection.",
"title": "Min Mean",
"type": "number"
},
"n_bins": {
"default": 20,
"description": "Number of bins for mean expression binning.",
"exclusiveMinimum": 0,
"title": "N Bins",
"type": "integer"
},
"n_top_genes": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Number of highly-variable genes to keep. Mandatory if `flavor='seurat_v3'",
"title": "N Top Genes"
},
"span": {
"default": 0.3,
"description": "Fraction of data used for loess model fit in seurat_v3.",
"exclusiveMaximum": 1,
"exclusiveMinimum": 0,
"title": "Span",
"type": "number"
},
"subset": {
"default": false,
"description": "Inplace subset to highly-variable genes if True.",
"title": "Subset",
"type": "boolean"
}
},
"title": "HighlyVariableGenesModel",
"type": "object"
}