> For the complete documentation index, see [llms.txt](https://help.connected.illumina.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.connected.illumina.com/dragen-stratamap/dragen-spatial-transcriptome/outputs/results-folder/data-for-icm.md).

# Data for ICM

This page describes the files located in {SampleID}\_ICM.tar.gz.

Each set of binned data (cell, grid, and optionally nuclei) for each sample has the following files for import into ICM. Each sample has a Manifest file that contains all the file information for loading into ICM.

* .h5ad (main output file; see [format](#h5ad-format) below)
* clustered.row\.annotation \*
* pca.col.matrix \*
* pca.h5ad \* (see [format](#pca-h5ad) below)
* pca.row\.annotation \*
* filtered.effective\_lib\_sizes.txt
* filtered.row\.index
* raw\.row\.annotation
* raw\.col.matrix
* raw\.col.annotation
* raw\_stats.txt
* raw\.effective\_lib\_sizes.txt
* normalized.h5ad (see [format](#normalized-h5ad) below)
* umap.col.matrix
* umap.h5ad (see [format](#umap-h5ad) below)

\* These are not produced when the "Skip Tertiary" option is selected.

### H5AD format

H5AD is an HDF5 file storing AnnData objects. The detailed format definition can be found at <https://github.com/scverse/anndata/blob/main/docs/fileformat-prose.md>.

<table data-header-hidden><thead><tr><th></th></tr></thead><tbody><tr><td><pre><code>H5AD file hierarchy
Duodenum_A_Rep1_cell_binned.h5ad
├── X (required; Compressed Sparse Column(CSC) matrix)
│   ├── data (Nonzero counts)
│   ├── indices (Zero-based row index of corresponding element in data)
│   ├── indptr (Zero-based index into data and indices of the start of each column)
├── obs (required; information labeling each observation/barcode)
│   ├── _index (barcode values)
│   ├── Expressed genes (Partek QAQC metric; # expressed features (count > 0) of this row)
│   ├── Total count (Partek QAQC metric; total count of this row)
│   ├── Lib size (Effective library size; used for Partek downstream analysis)
│   ├── UMAP1
│   ├── UMAP2
│   ├── Leiden
├── var (required; information labeling each variable/feature)
│   ├── _index (feature primary identifier)
│   ├── Feature type (optional; feature type of the counts data. i.e., "Gene Expression")
├── uns (required; unstructured annotations)
│   ├── stats (statistics information of the matrix)
│   │   ├── Min (matrix min value)
│   │   ├── 2nd min (matrix 2nd min value)
│   │   ├── Max (matrix max value)
│   │   ├── Mean (matrix mean value)
├── obsm (optional; key-indexed multi-dimensional observations annotation of length of observations/barcodes; currently empty)
├── obsp (optional: pairwise annotation of observations/barcodes, a mutable mapping with array-like values; currently empty)
├── varm (optional; key-indexed multi-dimensional variables annotation of length of variables/features; currently empty)
├── varp (optional: pairwise annotation of variables/features, a mutable mapping with array-like values; currently empty)
├── layers (optional: dictionary-like object with values of the same dimensions as X; currently empty)
</code></pre></td></tr></tbody></table>

H5AD has specific requirements for file, group, and dataset attributes so that third-party tools can recognize it. Here is the current implementation.

<table data-header-hidden><thead><tr><th></th></tr></thead><tbody><tr><td><pre><code>H5AD attributes:
Duodenum_A_Rep1_cell_binned.h5ad ("encoding-type": "anndata"; "encoding-version": "0.1.0")
├── X ("encoding-type": "csc_matrix"; "encoding-version": "0.1.0"; "shape": "[barcode count],[feature count]")
│   ├── data
│   ├── indices
│   ├── indptr
├── obs ("_index": "_index"; "column-order": "Expressed genes", "Total count", "Lib size", "UMAP1", "UMAP2", "Leiden"; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
│   ├── _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
│   ├── Expressed genes ("encoding-type": "array"; "encoding-version": "0.2.0")
│   ├── Total count ("encoding-type": "array"; "encoding-version": "0.2.0")
│   ├── Lib size ("encoding-type": "array"; "encoding-version": "0.2.0")
│   ├── UMAP1 ("encoding-type": "array"; "encoding-version": "0.2.0")
│   ├── UMAP2 ("encoding-type": "array"; "encoding-version": "0.2.0")
│   ├── Leiden ("encoding-type": "array"; "encoding-version": "0.2.0")
├── var ("_index": "_index"; "column-order": "Feature type"; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
│   ├── _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
│   ├── Feature type ("encoding-type": "array"; "encoding-version": "0.2.0")
├── uns ("encoding-type": "dict"; "encoding-version": "0.1.0")
│   ├── stats ("encoding-type": "dict"; "encoding-version": "0.1.0")
│   │   ├── Min ("encoding-type": "array"; "encoding-version": "0.2.0")
│   │   ├── 2nd min ("encoding-type": "array"; "encoding-version": "0.2.0")
│   │   ├── Max ("encoding-type": "array"; "encoding-version": "0.2.0")
│   │   ├── Mean ("encoding-type": "array"; "encoding-version": "0.2.0")
├── obsm ("encoding-type": "dict"; "encoding-version": "0.1.0")
├── obsp ("encoding-type": "dict"; "encoding-version": "0.1.0")
├── varm ("encoding-type": "dict"; "encoding-version": "0.1.0")
├── varp ("encoding-type": "dict"; "encoding-version": "0.1.0")
├── layers ("encoding-type": "dict"; "encoding-version": "0.1.0")
</code></pre></td></tr></tbody></table>

### Normalized H5AD

```
normalized.h5ad hierarchy

X (required; Compressed Sparse Column(CSC) matrix)
    --- data (Nonzero counts)
    --- indices (Zero-based row index of corresponding element in data)
    --- indptr (Zero-based index into data and indices of the start of each column)
obs (required; information labeling each observation/barcode)
      --- _index (barcode values)
      --- n_genes_by_counts (optional)
      --- pct_counts_mt (optional)
      --- summed (optional)
      --- total_counts (optional)
      --- total_counts_mt (optional)
      --- xpos (optional)
      --- ypos (optional)
var (required; information labeling each variable/feature)
      --- _index (feature primary identifier)
      --- feature_types (optional)
      --- gene_ids (optional)
      --- mean_counts (optional)
      --- mt (optional)
      --- n_cells_by_counts (optional)
      --- pct_dropout_by_counts (optional)
      --- total_counts (optional)
uns (optional; unstructured annotations)
     --- log1p (optional)
obsm (optional; key-indexed multi-dimensional observations annotation of length of observations/barcodes)
     --- spatial (optional)
obsp (optional: pairwise annotation of observations/barcodes, a mutable mapping with array-like values; currently empty)
varm (optional; key-indexed multi-dimensional variables annotation of length of variables/features; currently empty)
varp (optional: pairwise annotation of variables/features, a mutable mapping with array-like values; currently empty)
layers (optional: dictionary-like object with values of the same dimensions as X; currently empty)

```

```
normalized.h5ad attributes

X ("encoding-type": "csc_matrix"; "encoding-version": "0.1.0"; "shape": "[barcode count],[feature count]")
obs ("_index": "_index"; "column-order": “n_genes_by_counts”, “total_counts”, “xpos”, “ypos”, “total_counts_mt”, “pct_counts_mt”, “summed”; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
      --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- n_genes_by_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- pct_counts_mt ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- summed ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- total_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- total_counts_mt ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- xpos ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- ypos ("encoding-type": "string-array"; "encoding-version": "0.2.0")
var ("_index": "_index"; "column-order": “gene_ids”, “feature_types”, “n_cells_by_counts”, “mean_counts”, “pct_dropout_by_counts”, “total_counts”, “mt”; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
      --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- feature_types ("encoding-type": "categorical"; "encoding-version": "0.2.0"; “ordered”: “FALSE”)
      --- gene_ids ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- mean_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- mt ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- n_cells_by_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- pct_dropout_by_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
      --- total_counts ("encoding-type": "string-array"; "encoding-version": "0.2.0")
uns ("encoding-type": "dict"; "encoding-version": "0.1.0")
      --- log1p ("encoding-type": "dict"; "encoding-version": "0.1.0")
obsm ("encoding-type": "dict"; "encoding-version": "0.1.0")
      --- spatial ("encoding-type": "string-array"; "encoding-version": "0.2.0")
obsp ("encoding-type": "dict"; "encoding-version": "0.1.0")
varm ("encoding-type": "dict"; "encoding-version": "0.1.0")
varp ("encoding-type": "dict"; "encoding-version": "0.1.0")
layers ("encoding-type": "dict"; "encoding-version": "0.1.0")

```

### PCA H5AD

<pre><code>pca.h5ad hierarchy

<strong>X (required; a dense matrix)
</strong>obs (required; information labeling each observation/barcode)
      --- _index (barcode values)
var (required; information labeling each variable/feature)
     --- _index (PC labels: PC1 [variance ratio], PC2 [variance ratio], ... PC50 [variance ratio] )
uns (optional; unstructured annotations; currently empty)
obsm (optional; key-indexed multi-dimensional observations annotation of length of observations/barcodes; currently empty)
obsp (optional: pairwise annotation of observations/barcodes, a mutable mapping with array-like values; currently empty)
varm (optional; key-indexed multi-dimensional variables annotation of length of variables/features; currently empty)
varp (optional: pairwise annotation of variables/features, a mutable mapping with array-like values; currently empty)
layers (optional: dictionary-like object with values of the same dimensions as X; currently empty)

</code></pre>

```
pca.h5ad attributes

X ("encoding-type": "array"; "encoding-version": "0.2.0")
obs ("_index": "_index"; "column-order": null; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
      --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
var ("_index": "_index"; "column-order": null; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
     --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
uns ("encoding-type": "dict"; "encoding-version": "0.1.0")
obsm ("encoding-type": "dict"; "encoding-version": "0.1.0")
obsp ("encoding-type": "dict"; "encoding-version": "0.1.0")
varm ("encoding-type": "dict"; "encoding-version": "0.1.0")
varp ("encoding-type": "dict"; "encoding-version": "0.1.0")
layers ("encoding-type": "dict"; "encoding-version": "0.1.0")

```

### UMAP H5AD

```
umap.h5ad hierarchy

X (required; a dense matrix)
obs (required; information labeling each observation/barcode)
      --- _index (barcode values)
var (required; information labeling each variable/feature)
     --- _index (UMAP labels: 2D MAP 1, 2D UMAP 2)
uns (optional; unstructured annotations; currently empty)
obsm (optional; key-indexed multi-dimensional observations annotation of length of observations/barcodes; currently empty)
obsp (optional: pairwise annotation of observations/barcodes, a mutable mapping with array-like values; currently empty)
varm (optional; key-indexed multi-dimensional variables annotation of length of variables/features; currently empty)
varp (optional: pairwise annotation of variables/features, a mutable mapping with array-like values; currently empty)
layers (optional: dictionary-like object with values of the same dimensions as X; currently empty)

```

```
umap.h5ad attributes

X ("encoding-type": "array"; "encoding-version": "0.2.0")
obs ("_index": "_index"; "column-order": null; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
      --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
var ("_index": "_index"; "column-order": null; "encoding-type": "dataframe"; "encoding-version": "0.2.0")
     --- _index ("encoding-type": "string-array"; "encoding-version": "0.2.0")
uns ("encoding-type": "dict"; "encoding-version": "0.1.0")
obsm ("encoding-type": "dict"; "encoding-version": "0.1.0")
obsp ("encoding-type": "dict"; "encoding-version": "0.1.0")
varm ("encoding-type": "dict"; "encoding-version": "0.1.0")
varp ("encoding-type": "dict"; "encoding-version": "0.1.0")
layers ("encoding-type": "dict"; "encoding-version": "0.1.0")

```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.connected.illumina.com/dragen-stratamap/dragen-spatial-transcriptome/outputs/results-folder/data-for-icm.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.