From Research to Impact: A Comprehensive Platform for AI Model Deployment in Drug Discovery

The increasing application of machine learning (ML) and artificial intelligence (AI) in drug discovery necessitates scalable solutions for operationalizing these technologies. This paper presents the development and implementation of a cloud-native Machine Learning Operations (MLOps) platform designed to facilitate the deployment of production-ready, scalable, and reliable AI models within the pharmaceutical drug discovery environment. The platform addresses challenges associated with operationalizing AI in complex research and development settings, emphasizing the critical interplay between well-defined business requirements and technical capabilities. Foundational business needs, such as ensuring model reliability, data traceability, and rapid experimental iteration, directly influenced the technical architecture, including choices around orchestration (Kubeflow Pipelines), real-time serving (KServe), data integration, and monitoring. Our comprehensive MLOps approach demonstrates how strategic alignment of business objectives with scalable technical solutions can address common deployment challenges, showcasing practical applications across diverse ML workflow types. The platform is designed to support operational efficiency by providing the foundational infrastructure to track model usage as a proxy for business impact and by bridging the gap between scientific research and AI deployment across the life sciences and pharmaceutical sectors.