Aim and Significance
This project seeks to develop a novel drug formulation by detecting and eliminating unfavorable interactions between active pharmaceutical ingredients (APIs) and excipients. Our approach goes beyond the current state of the art through miniaturization and process optimization in a lab‐on‐a‐chip environment, leveraging the “coffee‐ring effect.”
By combining this innovative methodology with machine learning, we aim to significantly enhance the efficiency and precision of drug formulation.

Aim and SignificanceThe project integrates interdisciplinary expertise from chemistry, chemical engineering, machine learning, pharmacy, and biomedicine. Our results will establish new principles for assessing the properties and performance of early‐stage drug candidates. We will validate and refine these principles on ten commercially available drugs (azithromycin, doxycycline, carbamazepine, pantoprazole, omeprazole, dasatinib, imatinib, celecoxib, deferasirox, and entacapone), providing faster, more accurate, and cost‐effective solutions compared to existing methods. Ultimately, the goal is to proactively eliminate compounds with unfavorable properties before they progress to expensive and demanding development phases, thereby streamlining and economizing the drug development process. The new protocols are expected to be highly attractive and valuable to both local and global pharmaceutical industries, which are already represented within our research consortium.

Going Beyond the State of the Art
Our project addresses a critical challenge in the pharmaceutical industry using a pioneering approach: miniaturizing processes so they occur “on the chip” rather than “in the flask.” This lab-on-a-chip approach is at the forefront of global scientific research, and we aim to push its boundaries by coupling prototype chips with machine learning for the first time.

Innovative Aspects

On-the-Chip Miniaturization
We use minute quantities of substances to derive vital information about their properties and interactions. This approach eliminates the need for large-scale synthesis, which can be costly, time-consuming, and sometimes constrained by limited availability of materials

Particle Self-Organization
We explore the self-organization of particles that crystallize in minuscule volumes of solution. These interactions-among APIs and excipients-greatly influence the resulting crystal structures, providing insight into compatibility and stability.

Particle Self-OrganizationInkjet Printer Technology
Employing inkjet printing for formulating new drugs is a novel concept. This technique may expedite R&D by enabling precise, rapid, and reproducible sample dispensing.

Integration of Machine Learning
Using AI tools in combination with chemical engineering principles allows us to automate data analysis, predict outcomes, and optimize processes more effectively.