ingest
Map labels and embeddings from reference data to new data using specified labeling and embedding methods, supported by the SCMCP server for single-cell RNA sequencing analysis.
Instructions
Map labels and embeddings from reference data to new data
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| embedding_method | No | Embeddings in adata_ref which need to be mapped to adata. The only supported values are 'umap' and 'pca'. | |
| labeling_method | No | The method to map labels in adata_ref.obs to adata.obs. The only supported value is 'knn'. | knn |
| neighbors_key | No | If specified, ingest looks adata_ref.uns[neighbors_key] for neighbors settings and uses the corresponding distances. | |
| obs | No | Labels' keys in adata_ref.obs which need to be mapped to adata.obs (inferred for observation of adata). |
Input Schema (JSON Schema)
{
"description": "Input schema for the ingest tool that maps labels and embeddings from reference data to new data.",
"properties": {
"embedding_method": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"default": [
"umap",
"pca"
],
"description": "Embeddings in adata_ref which need to be mapped to adata. The only supported values are 'umap' and 'pca'.",
"title": "Embedding Method"
},
"labeling_method": {
"default": "knn",
"description": "The method to map labels in adata_ref.obs to adata.obs. The only supported value is 'knn'.",
"title": "Labeling Method",
"type": "string"
},
"neighbors_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "If specified, ingest looks adata_ref.uns[neighbors_key] for neighbors settings and uses the corresponding distances.",
"title": "Neighbors Key"
},
"obs": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Labels' keys in adata_ref.obs which need to be mapped to adata.obs (inferred for observation of adata).",
"title": "Obs"
}
},
"title": "IngestModel",
"type": "object"
}