read_tool
Extract and process single-cell RNA sequencing data from multiple file formats (h5ad, 10x, text files) or directories. Supports memory-efficient backed modes, URL retrieval, and customizable parsing options for analysis.
Instructions
Read data from various file formats (h5ad, 10x, text files, etc.) or directory path.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| backed | No | If 'r', load AnnData in 'backed' mode instead of fully loading it into memory ('memory' mode). If you want to modify backed attributes of the AnnData object, you need to choose 'r+'. | |
| backup_url | No | Retrieve the file from an URL if not present on disk. | |
| cache | No | If False, read from source, if True, read from fast 'h5ad' cache. | |
| cache_compression | No | See the h5py dataset_compression. (Default: settings.cache_compression) | |
| delimiter | No | Delimiter that separates data within text file. If None, will split at arbitrary number of white spaces, which is different from enforcing splitting at any single white space. | |
| ext | No | Extension that indicates the file type. If None, uses extension of filename. | |
| filename | Yes | Path to the file to read. | |
| first_column_names | No | Assume the first column stores row names. This is only necessary if these are not strings: strings in the first column are automatically assumed to be row names. | |
| first_column_obs | No | If True, assume the first column stores observations (cell or barcode) names when provide text file. If False, the data will be transposed. | |
| gex_only | No | Only keep 'Gene Expression' data and ignore other feature types, e.g. 'Antibody Capture', 'CRISPR Guide Capture', or 'Custom'. Used for 10x formats. | |
| make_unique | No | Whether to make the variables index unique by appending '-1', '-2' etc. or not. Used for 10x mtx format. | |
| prefix | No | Any prefix before matrix.mtx, genes.tsv and barcodes.tsv. For instance, if the files are named patientA_matrix.mtx, patientA_genes.tsv and patientA_barcodes.tsv the prefix is patientA_. Used for 10x mtx format. | |
| sampleid | No | Sample identifier to mark and distinguish different samples. | |
| sheet | No | Name of sheet/table in hdf5 or Excel file. | |
| var_names | No | The variables index for 10x mtx format. Either 'gene_symbols' or 'gene_ids'. | gene_symbols |