Prompt-to-Pill: Multi-Agent Drug Discovery and Clinical Simulation Pipeline

Abstract

This study presents a comprehensive, modular framework for AI-driven drug discovery (DD) and clinical trial simulation, spanning from target identification to virtual patient recruitment. Synthesized from a systematic analysis of 51 LLM-based systems, the proposed Prompt-to-Pill *architecture and corresponding implementation leverages a multi-agent system (MAS) divided into DD, preclinical and clinical phases, coordinated by a central Orchestrator. Each phase comprises specialized large language model (LLM) for molecular generation, toxicity screening, docking, trial design, and patient matching. To demonstrate the full pipeline in practice, the well-characterized target Dipeptidyl Peptidase 4 (DPP4) was selected as a representative use case. The process begins with generative molecule creation and proceeds through ADMET evaluation, structure-based docking, and lead optimization. Clinical-phase agents then simulate trial generation, patient eligibility screening using EHRs, and predict trial outcomes. By tightly integrating generative, predictive, and retrieval-based LLM components, this architecture bridges drug discovery and preclinical phase with virtual clinical development, offering a demonstration of how LLM-based agents can operationalize the drug development workflow in silico.