(515e) ML-Ops Platforms and Cloud Computing in Pharmaceutical Development

The advantage of model driven decisions in research organizations has long been recognized and applied in the pharmaceutical research and development. From the conceptualization of the Quality by Design framework as a series of mathematical constructs to the application of digital twins, Machine Learning and mechanistic methodologies are widely applicable and efficient tools to construct mathematical models of relevant pharmaceutical processes enabling process optimization, robustness characterization, and failure rate estimation. However, the widespread adoption of these approaches requires a combination of streamlined availability, and institutional know-how to generate, interpret, and incorporate the results in the decision-making process.

This talk addresses different approaches to leverage emerging and stablished tools in Machine Learning and mechanistic software to pharmaceutical development applications from the perspective of options of specific algorithms and computational platforms. Specifically, the integration of cloud-based machine learning operation (ML-Ops) platforms (DOMINO data labs) with elastic cloud High Performance Computing (HPC) providers (Rescale) enables the democratization of domain specific computational tools which would normally require subject matter expertise. In this presentation we demonstrate the deployment of computational fluid mechanics and quantum mechanics workflows that are presented in a simple graphical user interface enabling rapid adoption and integration into the pharmaceutical development process.