How chatmed/prompt-to-pill works
Prompt-to-Pill is an ask-driven, multi-agent drug-development simulation. A user submits a task to the AutoGen orchestrator, which the README says uses a planning agent to select tools across drug discovery, preclinical assessment, and clinical feasibility. The documented path spans molecule generation, profiling, docking and optimization, then trial construction, patient matching, and outcome prediction. The graph includes the distinct MCP tool servers and the docking implementation layer. Most server-to-server runtime handoffs are not shown in the excerpts, so the workflow links are cited to the README rather than presented as direct calls.
Main entry points: Prompt_to_pill.py AutoGen orchestrator · name2smiles_mcp_server.py Name to SMILES · patient_matching_mcp_server.py Patient matching · admet_prediction_mcp_server.py ADMET profiling
Components 18
Workflow coordination
- AutoGen orchestrator
Prompt_to_pill.py - Planning agent
Prompt_to_pill.py
Drug discovery
- Molecule generation
druggen_mcp_server.py - Name to SMILES
name2smiles_mcp_server.py - Docking tool
docking_mcp_server.py - Docking engine
docking_module.py
Preclinical assessment
- Chemical properties
chemical_properties_mcp_sever.py - ADMET profiling
admet_prediction_mcp_server.py - Lead optimization
mol_opt_mcp_server.py
Clinical feasibility
- Trial protocol generation
trialgen_mcp_server.py - Patient matching
patient_matching_mcp_server.py - Trial outcome prediction
trialpred_mcp_server.py
Other components
- Task requester
- PubChem
- FDA drug data
- ChemFM service
- Panacea model
- Patient XML data
diabetes_patients_final.xml
Connections 20
- Task requester → AutoGen orchestrator: submits task
README.md - AutoGen orchestrator → Planning agent: plans workflow
README.md - AutoGen orchestrator → Molecule generation: selects tool
README.md - AutoGen orchestrator → Name to SMILES: selects tool
- AutoGen orchestrator → Docking tool: selects tool
Prompt_to_pill.py - Docking tool → Docking engine: calls
docking_mcp_server.py - AutoGen orchestrator → Chemical properties: selects tool
Prompt_to_pill.py - AutoGen orchestrator → ADMET profiling: selects tool
Prompt_to_pill.py - AutoGen orchestrator → Lead optimization: selects tool
Prompt_to_pill.py - AutoGen orchestrator → Trial protocol generation: selects tool
README.md - AutoGen orchestrator → Patient matching: selects tool
Prompt_to_pill.py - AutoGen orchestrator → Trial outcome prediction: selects tool
- Name to SMILES → PubChem: queries
name2smiles_mcp_server.py - Name to SMILES → FDA drug data: looks up brands
name2smiles_mcp_server.py - ADMET profiling → ChemFM service: predicts via
admet_prediction_mcp_server.py - Trial protocol generation → Panacea model: generates with
trialgen_mcp_server.py - Patient matching → Panacea model: assesses with
patient_matching_mcp_server.py - Patient matching → Patient XML data: reads XML
patient_matching_mcp_server.py - AutoGen orchestrator → Chemical properties: rechecks leads
Prompt_to_pill.py - AutoGen orchestrator → ADMET profiling: rechecks leads
Prompt_to_pill.py