In pharmaceutical research, scientists face a fundamental challenge accessing and connecting vast scientific knowledge scattered across disparate systems, which slows drug discovery and risks losing institutional knowledge. Traditional methods yield only a **5 percent** success rate, and initial screening takes **over six months** per attempt. Critical insights are scattered across **PubMed**, internal lab notes, and genomics databases, leading to missed connections and redundant work. When researchers leave, valuable tacit knowledge is lost, breaking research continuity. The solution uses graph-powered AI with **Amazon Neptune Analytics**, allowing researchers to ask complex questions in natural language and receive evidence-backed insights from a unified knowledge graph connecting compound interactions, gene expressions, and clinical studies. The system reveals complete reasoning by showing detailed citation paths and graph traversal steps, making scientific discovery more transparent and reproducible.