# Single-drug response data

This folder is a cleaned data layout for single-drug response prediction.
The bundled legacy collaborator reference package is located at this repository-relative path:

```text
data/downstream/final_data/drug_response_pytorch/drug_response_pytorch
```

## Runnable data path

From the repository root, use this directory as `--data_path` for `BioMod/drug_response/train.py`:

```text
data/downstream/final_data/single_drug_response/data
```

Expected layout:

```text
data/
|-- GDSC/
|   |-- 1.Drug_listMon Jun 24 09_00_55 2019.csv
|   `-- drug_graph_feat/*.hkl
`-- CCLE/
    |-- Cell_lines_annotations_20181226.txt
    |-- GDSC_IC50.csv
    `-- genomic_expression_561celllines_697genes_demap_features.csv
```

## Previously recorded statistics

The figures below are retained from the existing dataset documentation; this path/comment audit did not recompute them.

- Drug information table: (266, 8)
- Drug graph files: 223
- IC50 matrix: (266, 969)
- Cell-line expression matrix: (561, 697)
- Cell-line annotation table: (1461, 33)

## Optional reference files

`optional_reference/` contains files from the original package that are not used by the current BioMod single-drug response script, including mutation, copy-number, methylation, threshold and DeepCDR reference outputs. Keep them for provenance or future multi-omics experiments.

## Files

See `MANIFEST.csv` for file sizes and checksums. See `SUMMARY.json` for machine-readable shape checks.