Weekly PhD Newsletter | SIGN UP NOW Weekly PhD Newsletter | SIGN UP NOW

Human innate immune response modelling using self-supervised graph-based deep learning


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 Shagufta Henna, Dr L Creedon, Dr Kevin Meehan  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Project description: The immune response of severe acute respiratory syndrome coronavirus (SARS-CoV) infection is a complicated process and plays a critical role in the progression of the disease. The immune response is based on various pattern recognition receptors (PRRs) to react to viral pathogens using pathogen-associated molecular patterns (PAMPs), an essential component of immune system response. The recognition of PAMPs triggers a cascaded signalling process that activates microbicidal/pro-inflammatory responses for an adaptive immune response. Several investigations report critical implications of PRRs for immunomodulator design and cancer immunotherapy, etc. This project aims to use graph-based deep learning to model the cascaded activation process of PRRs in response to SARS-CoV strains to determine an understanding and reaction of the immune response. Further, the project seeks to harness self-supervised learning to handle large-scale unlabelled molecular graphs data with better generalization capabilities. 

Project objectives: 

  1. Model cascaded dependencies of PPRs using a graph model. 
  2. Propose graph-based deep learning approaches for immune response prediction against SARS-CoV strains. 
  3. Adopt cardinality preserved attention to graph-based deep learning to model the distinct structures of the immune system. 
  4. Apply self-supervised learning on a graph-based neural network to work with unlabelled samples for better generalization. 
  5. Validate the performance of the graph-based deep learning with and without self-supervision. 
  6. Evaluate the performance of self-supervised graph-based deep learning with cardinality preservation attention mechanism. 

Candidate Attributes:

Candidate should have Masters in Artificial Intelligence/Big Data Analytics/ Computer Science. Candidate should have at least a 2:1 Honour’s degree, or equivalent, in Computer Science/Mathematics or relevant discipline. Experience in Machine Learning tools (TensorFlow, PyTorch, Keras) and computational modelling is strongly desirable. Ability to pursue independent research and excellent writing and fluency in English are mandatory


Please send to Veronica Cawley – [Email Address Removed] Only using the application form.

Application Form / Terms of Conditions can be obtained on the website:


The closing date for receipt of applications is 5pm, (GMT) 21st February 2022

Funding Notes

Unit costs per PRTP scholar p/a:
Stipend: €19,000 gross, €16,000 nett (nett stipend of €16,000 p/a is after deduction of €3,000 p/a student contribution).
Tuition fees: Waived by each institute (fee waivers may be partial for non-EU candidates).
Consumables, Mobility, and Training: Up to €3,500 p/a for non-laboratory, desk-based research; Up to €4,500 p/a for studio, or fieldwork research; Up to €5,500 p/a for laboratory-based research


Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs