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

This study presents a comprehensive, modular framework for AI-driven drug discovery 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 divided into preclinical and clinical phases, coordinated by a central Orchestrator . Each phase comprises specialized large language model (LLM) agents responsible for tasks such as molecular generation, toxicity screening, docking simulation, 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 preclinical discovery with virtual clinical development, offering an end-to-end demonstration of how LLM-based agents can operationalize the entire drug development workflow in silico.