Autonom fenotypisk läkemedelsprofilering

The experimental space of biomedical research is vast and in many cases infeasible to cover with conventional methods where experiments are selected and carried out by humans. The purpose of this project is to develop an intelligent system for phenotypic cell profiling, being able to autonomously suggest the next most informative experiment, perform it using an automated lab, learn from the results, and repeat.  We propose a 4-year project combining the strengths of three research groups: Spjuth lab (AI, Big Data, Cell Painting), Kallioniemi lab (precision cancer medicine), Carreras-Puigvert (drug screening) with three aims: i) Expansion of our robotized lab into a fully automated cell profiling lab that can be controlled by AI; ii) Development of autonomous AI methods to control the automated lab; iii) Applying the autonomous system to identify optimal drug treatments using cancer cell lines, also in combination with other commonly used drugs to predict positive or negative synergies. AI-driven autonomous profiling of cells has the potential to radically speed up biological discoveries and allows for exploring previously infeasible problems. Here we use this approach for optimization of cancer treatment strategies, but our system will be applicable to many other scientific fields. Moreover, this project will result in unique, high-quality reference datasets and corresponding AI models, building a foundation upon which new discoveries can be made.