Search for similar molecules using Tanimoto similarity with Morgan fingerprints to identify structurally related compounds.
import asyncio
import json
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession
class DrugSDAClient:
"""DrugSDA-Tool MCP Client"""
def __init__(self, server_url: str, api_key: str):
self.server_url = server_url
self.api_key = api_key
self.session = None
async def connect(self):
"""Establish connection and initialize session"""
print(f"server url: {self.server_url}")
try:
self.transport = streamablehttp_client(
url=self.server_url,
headers={"SCP-HUB-API-KEY": self.api_key}
)
self.read, self.write, self.get_session_id = await self.transport.__aenter__()
self.session_ctx = ClientSession(self.read, self.write)
self.session = await self.session_ctx.__aenter__()
await self.session.initialize()
session_id = self.get_session_id()
print(f"✓ connect success")
return True
except Exception as e:
print(f"✗ connect failure: {e}")
return False
async def disconnect(self):
"""Disconnect from server"""
try:
if self.session:
await self.session_ctx.__aexit__(None, None, None)
if hasattr(self, 'transport'):
await self.transport.__aexit__(None, None, None)
print("✓ already disconnect")
except Exception as e:
print(f"✗ disconnect error: {e}")
def parse_result(self, result):
"""Parse MCP tool call result"""
try:
if hasattr(result, 'content') and result.content:
content = result.content[0]
if hasattr(content, 'text'):
return json.loads(content.text)
return str(result)
except Exception as e:
return {"error": f"parse error: {e}", "raw": str(result)}
This workflow searches for similar molecules using Tanimoto similarity calculated from Morgan fingerprints.
Workflow Steps:
Implementation:
## Initialize client
client = DrugSDAClient(
"https://scp.intern-ai.org.cn/api/v1/mcp/2/DrugSDA-Tool",
"<your-api-key>"
)
if not await client.connect():
print("connection failed")
exit()
## Input: Target molecule and candidate library
target = "CCO" # Ethanol
candidates = [
"CCCO", # Propanol
"CCCCO", # Butanol
"CC(C)O", # Isopropanol
"CCC(C)O", # sec-Butanol
"C1CC1", # Cyclopropane
"CC=O", # Acetaldehyde
"CCCOO" # Propanoic acid
]
## Execute similarity calculation
result = await client.session.call_tool(
"calculate_smiles_similarity",
arguments={
"target_smiles": target,
"candidate_smiles_list": candidates
}
)
result_data = client.parse_result(result)
similarities = result_data['similarities']
## Sort and display top 3 most similar molecules
top3_smiles = sorted(similarities, key=lambda x: x['score'], reverse=True)[:3]
print(f"Target molecule: {target}\n")
print("Top 3 most similar molecules:")
for i, item in enumerate(top3_smiles, 1):
print(f"{i}. {item['smiles']} - Tanimoto score: {item['score']:.4f}")
await client.disconnect()
DrugSDA-Tool Server:
calculate_smiles_similarity: Compute molecular similarity using Morgan fingerprints
target_smiles (str): Query molecule SMILES stringcandidate_smiles_list (list): List of candidate molecule SMILES stringssimilarities (list): List of similarity scores
smiles (str): Candidate SMILES stringscore (float): Tanimoto similarity (0-1)Input:
target_smiles: SMILES string of the query moleculecandidate_smiles_list: List of SMILES strings to compare againstOutput:
smiles: Candidate molecule SMILESscore: Tanimoto similarity coefficient (0-1)
0.7 = highly similar