University of Hong Kong Featured PhD Programmes
University of West London Featured PhD Programmes
University College London Featured PhD Programmes

Machine learning methods to identify regulatory networks controlling proliferation and senescence


School of Biological Sciences

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
Dr G Stracquadanio , Dr T Ly No more applications being accepted Competition Funded PhD Project (Students Worldwide)

About the Project

Cells are controlled by an intricate network of interactions between genes and proteins, which mediate fundamental processes, such as metabolism, growth and proliferation. A key challenge is understanding how cells regulate state changes between proliferation, quiescence and senescence. Whereas cells that become quiescent can reversibly re-enter the cell cycle to proliferate, senescent cells are characterised by irreversible cell cycle exit, increased size and increased secretion of inflammatory signalling molecules. Regulation of quiescence and senescence have been shown to be important in the context of human disease. Loss of quiescence is a hallmark of proliferative diseases, including cancer. Senescent cells marked by high levels of p16Ink4a protein expression have been shown to be important in ageing phenotypes in mice. High-throughput experimental technologies, such as next-generation sequencing and mass spectrometry, provide useful information about gene expression, protein levels and phosphorylation changes in quiescent and senescent cells; however, using this information to infer biological pathways controlling these processes has been challenging (1,2).

Here we plan to harness recent advances in deep learning and network theory to identify the regulatory networks controlling these processes. We will then analyse publicly available datasets, including those generated by the Ly lab, to identify regulatory networks that can be validated in functional cells.

The student will develop new methods for network discovery based on deep learning, using graph neural networks and dimensionality reduction techniques, such as graph embedding and autoencoders. He/she will also receive training in writing reproducible bioinformatics analysis workflows, mass spectrometry-based analysis of cellular proteins and high-quality research software.

The ideal candidate has a background in mathematics, computer science, computer engineering, statistics, physics or related fields. He/she is strongly motivated to develop a competitive profile in machine learning, data science and computational biology and likes to work in a fast-pace environment.

• www.stracquadaniolab.org
• http://dynamic-proteomes.squarespace.com

Funding Notes

The “Visit Website” button on this page will take you to our Online Application checklist. Please complete each step and download the checklist which will provide a list of funding options and guide you through the application process.

If you would like us to consider you for one of our scholarships you must apply by 5 January 2020 at the latest.

References

1. Stracquadanio, G., Wang, X., Wallace, M. D., Grawenda, A. M., Zhang, P., Hewitt, J., … Bond, G. L. (2016). The importance of p53 pathway genetics in inherited and somatic cancer genomes. Nature Reviews Cancer, 16(4), 251–265. doi:10.1038/nrc.2016.15
2. Fanfani, V., & Stracquadanio, G. (2019). A unified framework for geneset network analysis. doi:10.1101/699926


FindAPhD. Copyright 2005-2021
All rights reserved.