Automated solubility screening platform using computer vision

• DOI: 10.1016/j.isci.2021.102176
• Publication Date: 2021-02-16T06:28:20Z
• Authors: Parisa Shiri; Veronica Lai; Tara Zepel; Daniel Griffin; Jonathan Reifman; Sean Clark; Shad Grunert; Lars P.E. Yunker; Sebastian Steiner; Henry Situ; Fan Yang; Paloma L. Prieto; Jason E. Hein
• Keywords: green chemistry; engineering; Science; Q; 02 engineering and technology; organic synthesis; 0210 nano-technology; Article; organic chemistry; automation

Solubility screening is an essential, routine process that is often labour intensive. Robotic platforms have been developed to automate some aspects of the manual labour involved. However, many of the existing systems rely on traditional analytic techniques such as High Performance Liquid Chromatography or HPLC, which require pre-calibration for each compound and can be prohibitively expensive. In addition, automation is not typically end-to-end, requiring user intervention to move vials, establish analytical methods for each compound and interpret the raw data. We developed a closed-loop, flexible robotics system with integrated solid and liquid dosing capabilities that relies on computer vision and iterative feedback to successfully measure caffeine solubility in multiple solvents. After initial researcher input (<2 min), the system ran autonomously, screening five different solvent systems (20-80 min each). The resulting data matched values obtained using traditional manual techniques.