Personalising cancer treatment with modelling tumour evolution based on genomics biomarkers and PK/PD

Tumour heterogeneity is a major problem limiting the efficacy of targeted oncological therapies. Most advanced tumours eventually become resistant to the treatments, ultimately making the patient succumb to metastatic disease.

This project invites you to develop advanced computational modelling to maximise survival of a patient by combining cancer genomics data with pharmacometrics information for the first time, which might inform personalised cancer treatments.

For successful model development, we need to articulate these 4 main questions with AI-driven and PK/PD modelling methods.

1. Can genomics predict survival?

You will classify patients based on whole-genome sequencing data and molecular interaction networks to establish robust relationship between cancer genotypes and patient survival for different treatments. You will also apply gene signatures to infer personal attributes and pre-treatments for each patient.

2. Can genotypes and other factors predict tumour dynamics?

Using information from step 1 as covariates, you will train and test a tumour dynamics model with longitudinal tumour size data. This model will help infer important hidden parameters such as the fraction of sensitive cells prior to treatment and the rates of growth and death for treated tumours. We aim to test the model for 5 important types of cancer, including breast, colorectal, lung, ovarian and prostate cancer.

3. Can pharmacometrics information refine tumour dynamics prediction? 

You will evaluate whether the parameters of the model from step 2 can be predicted by drug pharmacokinetics and tumour pharmacodynamics.

4. Can this tumour dynamics model predict tumour evolution?

You will gain an impressive set of skills in mathematical modelling for patient selection and efficacy evaluation in drug discovery and development, which is in short supply for the pharmaceutical industry.

To apply to this project, email your CV and cover letter to the primary supervisor: tao.you@liverpool.ac.uk