The work aims to understand why some patients respond to drugs and others do not, seeking ways to improve response and match it to individual patients in advance. Current projects include understanding how dynamics of response change over time, and incorporating AI and machine learning into automation to make processes faster and more interpretable. On the pre-clinical side, the goal is to understand which drugs approved for a specific indication actually work in individual patients and if that can be predicted, though such tools do not yet exist due to a lack of the right models to predict drug response. The translational gap has historically been a very big problem, so bringing more humanized models into pre-clinical and clinical development is important for more predictivity. Building more representative models with more different cell types, or using AI to enhance responses for better understanding, are key. The most exciting next steps involve integrating AI to better interpret data and to take big data to understand drug response over time, which is only possible with AI tools to curate and understand data that humans cannot with current analysis methods.