Artificial Intelligence and Machine Learning for Enhanced Phenotyping of Breath Metabolomics Data

   Department of Respiratory Sciences

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

Click here to search for PhD studentship opportunities
  Prof S Siddiqui, Prof Y Zhang, Prof P Monks  No more applications being accepted  Competition Funded PhD Project (European/UK Students Only)

About the Project

Exhaled breath contains a rich matrix of volatile chemicals (metabolites) that may be useful as disease biomarkers. However manual visual evaluation of metabolites from exhaled breath samples is subject to significant inter-expert and intra-expert variations. Furthermore conventional statistical techniques need to make prior assumptions on data models.

The PhD program will develop computer vision and deep learning (particularly convolutional neural network) techniques for the analysis and discovery of biomarkers from exhaled samples. Breath metabolomics data has already been acquired in approximately 600 patients with acute exacerbations of cardio respiratory disease in a large exhaled breath metabolomics program funded by the EPSRC/MRC. Breath samples have been acquired using GCxGC-MS and PTR-MS technologies in the acute state and during recovery from an exacerbation. The PhD will focus on biomarker discovery and replication within these existing rich datasets. The project will be hosted jointly in the Department of Computer Science, NIHR Biomedical Research Centre at Leicester University and East Midlands Breathomics Molecular Pathology Node. A range of training opportunities in artificial intelligence and data science will be made available to the successful candidate.

Entry requirements
Applicants are required to hold/or expect to obtain a UK Bachelor Degree 2:1 or better in a relevant subject. The University of Leicester English language requirements apply where applicable.

UK/EU applicants only
Applicants should have a strong background in computer science or mathematics & statistics (2:1 degree or above) and be skilled in relevant programming languages, e.g. Python, R and Matlab

How to apply
Please apply via:

Project / Funding Enquiries: Please direct initial enquiries to Professor Salman Siddiqui ([Email Address Removed]) or Professor Yudong Zhang ([Email Address Removed]).
Application enquiries to [Email Address Removed]

Funding Notes

3.5 year MRC IMPACT DTP studentship


[1] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition.
In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
(pp. 770-778).
[2] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017, July). Densely
Connected Convolutional Networks. In CVPR