pca
Perform principal component analysis on single-cell RNA sequencing data to reduce dimensionality, extract key patterns, and enable efficient visualization and analysis.
Instructions
Principal component analysis
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| chunk_size | No | Number of observations to include in each chunk. | |
| chunked | No | If True, perform an incremental PCA on segments. | |
| dtype | No | Numpy data type string for the result. | float32 |
| layer | No | If provided, which element of layers to use for PCA. | |
| mask_var | No | Boolean mask or string referring to var column for subsetting genes. | |
| n_comps | No | Number of principal components to compute. Defaults to 50 or 1 - minimum dimension size. | |
| svd_solver | No | SVD solver to use. | |
| zero_center | No | If True, compute standard PCA from covariance matrix. |
Input Schema (JSON Schema)
{
"description": "Input schema for the PCA preprocessing tool.",
"properties": {
"chunk_size": {
"anyOf": [
{
"exclusiveMinimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Number of observations to include in each chunk.",
"title": "Chunk Size"
},
"chunked": {
"default": false,
"description": "If True, perform an incremental PCA on segments.",
"title": "Chunked",
"type": "boolean"
},
"dtype": {
"default": "float32",
"description": "Numpy data type string for the result.",
"title": "Dtype",
"type": "string"
},
"layer": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "If provided, which element of layers to use for PCA.",
"title": "Layer"
},
"mask_var": {
"anyOf": [
{
"type": "string"
},
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": null,
"description": "Boolean mask or string referring to var column for subsetting genes.",
"title": "Mask Var"
},
"n_comps": {
"anyOf": [
{
"exclusiveMinimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Number of principal components to compute. Defaults to 50 or 1 - minimum dimension size.",
"title": "N Comps"
},
"svd_solver": {
"anyOf": [
{
"enum": [
"arpack",
"randomized",
"auto",
"lobpcg",
"tsqr"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "SVD solver to use.",
"title": "Svd Solver"
},
"zero_center": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": true,
"description": "If True, compute standard PCA from covariance matrix.",
"title": "Zero Center"
}
},
"title": "PCAModel",
"type": "object"
}