disease-reversal-prediction

name	disease-reversal-prediction
description	Predict a molecule's ability to reverse disease states using DLEPS (Disease-Ligand Embedding Projection Score) for drug repositioning and discovery.
license	MIT license
metadata	{"skill-author":"PJLab"}
i18n	{"zh":{"description":"预测分子逆转疾病能力。"}}

Disease State Reversal Prediction

Usage

1. MCP Server Definition

Use the same DrugSDAClient class as defined in the drug-screening-docking skill.

2. Disease State Reversal Prediction Workflow

This workflow validates SMILES strings and predicts their ability to reverse disease states, useful for drug repositioning and therapeutic discovery.

Workflow Steps:

1. Validate SMILES - Check if input SMILES strings are chemically valid
2. Calculate DLEPS Score - Predict disease state reversal scores for valid molecules

Implementation:

tool_client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool")
model_client = DrugSDAClient()

   tool_client.connect()    model_client.connect():
    ()
    


smiles_list = [
    ,
    ,
      
]


result =  tool_client.session.call_tool(
    ,
    arguments={: smiles_list}
)
result_data = tool_client.parse_result(result)
valid_smiles_list = [x[]  x  result_data[]  x[]  ]

()


disease_name =   

result =  model_client.session.call_tool(
    ,
    arguments={
        : valid_smiles_list,
        : disease_name
    }
)
result_data = model_client.parse_result(result)


pred_scores = (result_data[], key= x: x[], reverse=)
 item  pred_scores:
    ()
    ()

 tool_client.disconnect()
 model_client.disconnect()