PhD Studentship: Unlocking the Code within the Code: Using AI to Decipher the Role of Codon Usage in Protein Synthesis and Gene Regulation

Overview

Dr Susanne Bornelöv wishes to recruit a student to work on the project entitled: "Unlocking the code within the code: Using AI to decipher the role of codon usage in protein synthesis and gene regulation"

For further information about the research group, including their most recent publications, please visit their website at http://www.sblab.uk.

This is a unique opportunity for PhD study in the world-leading Cancer Research UK Cambridge Institute (CRUK CI), to start a research career in an environment committed to training outstanding cancer research scientists of the future.

The Institute's particular strengths are in genomics, computational biology and imaging; and significant research effort is currently devoted to cancers arising in the breast, pancreas, brain, and colon. Our Core Facilities provide researchers with access to state-of-the-art equipment, in-house expertise and training. Scientists at CRUK CI aim to understand the fundamental biology of cancer and translate these findings into the clinic to benefit patients.

If you are interested in finding out more about our groundbreaking scientific research, please visit our website at https://www.cruk.cam.ac.uk/

Project details

The genetic code contains 61 codons encoding 20 amino acids and most amino acids are therefore encoded by two or more 'synonymous' codons. Despite producing the same protein, the choice of one synonymous codon over another plays an important role in gene regulation [1,2]. Some codons slow down translation, which in turn triggers mRNA degradation and halt protein synthesis. Protein synthesis is often dysregulated in cancer, making mRNA translation an attractive therapeutic target.

This project uses artificial intelligence (AI) to unravel the underlying mechanism by which codon-level information regulates translation.

Our group uses computational methods to study the inner workings and control of biological systems. For instance, by systematically changing the input mRNA sequence to a model capable of predicting mRNA stability or localisation, and analysing resultant patterns, we can gain understanding of what sequence elements regulate these processes. Additionally, we can use disease-associated alterations as inputs to unravel the underlying mechanism.

These models enable us to conduct experiments on a scale far surpassing what is achievable through traditional methods. The primary challenge lies in making models that accurately capture the complexities of biological systems [3]. In this project, you will use cutting-edge deep learning techniques, such as foundation models, to address this challenge. Foundation models, such as those underlying ChatGPT, are trained on a vast array of data and are capable of generalising across a multitude of problems. Your work will use similar models, but trained on 'omics' data, to study the regulation of translation.

Preferred skills/knowledge

We are looking for someone with an keen interest in AI and deep learning, with good computer and coding skills, and a willingness to uncover fundamental workings of the cell. The ideal candidate will have a degree in computational or systems biology, bioinformatics, computer science or related discipline. Applicants with a background in e.g., molecular biology or biochemistry and with clear evidence of computational skills are also encouraged to apply. The role will offer extensive training in machine learning and computational biology.

How to apply

Please apply via the University Applicant Portal. For further information about the course and to access the Applicant Portal, visit: https://www.postgraduate.study.cam.ac.uk/courses/directory/cvcrpdmsc

You should select to commence study in Michaelmas Term 2025 (October 2025)

Advert information