load_datasetLABSCO SUMMARY
Pharmacogenomics datasets you can ask about rather than script against.
It carries the loading, normalisation and caching that usually take a page of R at the top of every analysis, so a question about a drug-omics association starts at the question.
What it is
An MCP server for DROMA, the Drug Response Omics association MAp. It sits in front of the DROMA.R and DROMA.Set R packages over rpy2, loading pharmacogenomics datasets such as CCLE and gCSI into memory and answering questions against them.
What you get
- A DROMA dataset loaded from the SQLite database and held in memory
- Several projects loaded at once and worked with together
- Molecular profiles loaded with z-score normalisation applied
- Treatment response data loaded with the same normalisation
- The active dataset switched, the loaded ones listed, and any of them unloaded to free memory
- Results exported to CSV, Excel or JSON
- Transport over STDIO, HTTP or SSE
Requirements
Python 3.10 or newer, a recent R with the DROMA.Set and DROMA.R packages installed, and a DROMA SQLite database. Without the R side in place the server has nothing to call.
Setup effort
Build from source — git clone https://github.com/mugpeng/DROMA_MCP
USE CASES
01
Getting a public cell-line dataset ready to work with
Load CCLE or gCSI from the database and confirm what is currently in memory before you start asking.
02
Comparing drug response across two research projects
Load several projects together and switch which one questions resolve against.
03
Pulling expression data that is already on a common scale
Molecular profiles come back z-score normalised, so a comparison across datasets does not start with a normalisation step.
04
Lining up treatment response against omics
Load both sides with the same normalisation applied, so the association is measured on comparable numbers.
05
Freeing memory after a long session
See what is still resident and drop the datasets you have finished with.
17 tools
Listed in project docs. Your client may show a different list.
list_loaded_datasetsset_active_datasetunload_datasetload_molecular_profiles_normalizedload_treatment_response_normalizedload_multi_project_molecular_profiles_normalizedload_multi_project_treatment_response_normalizedcheck_zscore_normalizationget_cached_data_infoexport_cached_dataget_droma_annotationlist_droma_sampleslist_droma_featureslist_droma_projectsplot_drug_sensitivity_rankanalyze_drug_omic_pairBEFORE YOU INSTALL
What to know first
Tools you get
17 tools named in the project's documentation.
Requires
Python 3.10+
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/mugpeng/DROMA_MCP
cd DROMA_MCP
pip install -e .MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"droma-mcp": {
"command": "droma-mcp",
"args": [
"run",
"--db-path",
"<YOUR_PATH_TO_DROMA>"
]
}
}
}