By Dr. Daniela Blanco, Ph.D.,
CEO and Co-Founder, Sunthetics

Pharmaceutical crystallizations, as well as process and product development present significant challenges in terms of cost, efficiency, and sustainability. Harnessing the power of data-driven machine learning (ML) to predict behavioral trends, variable effects, and optimal conditions offers a promising solution to fast-track innovation. However, conventional ML algorithms often require extensive datasets, posing a resource-intensive challenge in experimental data collection.
To address this bottleneck, we introduce an enhanced Bayesian optimization (BO) approach, enabling a reaction-agnostic pathway to design and implement intelligent experimental campaigns for accelerated process optimization. SuntheticsML is an accessible online ML platform tailored for researchers without coding or ML expertise, demonstrating compelling returns on material and experimental efficiency, as well as performance gains against a competitive baseline.
We will share case studies showcasing SuntheticsML in crystallization processes, chemocatalytic reactions, biocatalytic cascades, in vitro transcription processes, and more. We will cover numeric, discrete, and mixed-integer optimization problems with up to 20 input parameters and multi-objective. The results will demonstrate enhancements in cost and material efficiency with up to a 75% reduction in the use of expensive or complex reagents, a 2-6X reduction in optimization experiments, and a 9-12% increase in previously-optimized yields. The individual or entity to whom it is addressed.
[Any unauthorized use or disclosure of this information is strictly prohibited]