Applying a Robot Scientist to Modelling Cancer Cells

Challenge: The fundamental problem in treating cancer is that we don’t understand enough about healthy and cancerous human cells to intervene rationally to kill cancerous cells but not healthy ones.

Background: Human cells are incredibly complex, tens of thousands of genes, proteins, and small molecules interact in complex temporal-spatial ways. The only way to disentangle and model these interactions, and hence treat cancer, is through hypothesis formation, and reproducible experimentation. However, progress is slow because of the limited number of qualified human scientists. A Robot Scientist is a physically implemented laboratory automation system that exploits techniques from the field of artificial intelligence (AI) to automatically execute cycles of scientific experimentation. I currently have a grant to adopt the laboratory automation part of the Robot Scientist Eve to work with human cancer cells, the aim is to test statements taken from the scientific literature.

Goals: The goal of the PhD would be to use Eve to automatically: hypothesise improvements to models of cell signalling in healthy and cancerous cells, to form experiments to test theses hypotheses, to execute these experiments, and to decide whether the model should be changed. This ambitious goal is possible within a PhD because: computational models of cell signalling exist, the wet biology/automation work in adapting Eve has been done, and a similar cycle of model improvement has been achieved in modelling yeast metabolism.

Possible outcomes: New AI techniques for automating scientific reasoning. New biomedical
knowledge about healthy and cancerous human cells.

Skills: The students should have a background in AI with an interest in biology.