Background:
Imagine being able to tell a patient with liver cancer that their tumour is growing approximately 40% faster than the surrounding normal tissue and that is why they need chemotherapy. Similarly, what if we could arm caregivers with the knowledge that a breast tumour is growing faster than 90% of all other breast tumours? This project will provide a framework for classifying any tumour in terms of its doubling speed and cell cycle activity. As such, it will not only extend our knowledge and understanding of tumour growth but will also redefinine how we interpret cell cycle activity by placing it in terms of absolute growth.

Methods:
We will examine cell cycle activity using RNA-expression data from the NCI-60 cell line database where highly accurate doubling times have been derived on the basis of multiple independent methods. From this we will initially be able to understand if a linear relationship exists between the CCS and cell doubling time within cell lines. Next, using the cell line database as a training dataset, we will apply Artificial Intelligence and machine learning techniques from within the R-statistical environment to classify both pan-cancer atlas tumours (n=11,286) and normal tissues from the same organs (GTEx cohot, n=11,688) on the basis of doubling time speed.

The Candidate:
This project is most suited to someone with programming experience in R or Python. Don't worry about a lack of biological knowledge, I can teach you that. If you want to use your programming skills to help us better understand and treat cancer patients then this is the project for you!