University of Edinburgh Featured PhD Programmes
University of Leeds Featured PhD Programmes
University of Glasgow Featured PhD Programmes

Big biological data integration via deep learning methods to understand mechanisms underlying cardiometabolic disorders (Advert Reference: RDF21/EE/CIS/KURTZeyneb)

Faculty of Engineering and Environment

About the Project

Cardiometabolic disorders such as coronary artery disease (CAD), obesity, and type 2 diabetes (T2D) represent the top leading causes of morbidity and mortality worldwide. These disorders are highly interconnected and the recent rise in their prevalence poses elevated health burden and calls for a better understanding of the mechanisms underlying them. In this manner, more effective prevention and treatment strategies can be developed. In the past decades, human genome-wide association studies (GWAS), which represent a particular type of big biological data resources, have emerged as a revolutionary tool to uncover genetic risk variants associated with complex human diseases such CAD and T2D. Despite the GWAS datasets have crucially improved our understanding in disease progression, several critical questions remain to be addressed. First, the GWASs can only capture a limited portion of genetic heritability, implicating many additional causal genetic risk factors remain to be uncovered. Second, how these genetic signals communicate and altogether contribute to disease pathogenesis through perturbing certain biological mechanisms or gene-gene interaction subnetworks remains to be explored. In addition to the GWAS, tissue-specific transcriptome datasets, which represent another type of big biological data resources and are highly associated to environmental factors such as nutrition/diet, have been collected from human samples to study complex diseases. Transcriptome datasets can be used for inferring tissue-specific gene regulatory networks(GRN), thereby can improve our understanding of common human diseases by complementing our findings from GWAS data. Hence, proposing an integrative genomics approach can address the knowledge gaps that is raised from using a single type of biological data.

In this project, we propose to leverage big biological datasets from human samples and implement an integrative genomics approach based on deep neural networks and autoencoder models, to identify molecular mechanisms contributing to the cardiometabolic disorders Most of the previous genomic studies have focused on individual types of data (such as either genetic or transcriptomics), one at a time, and employed traditional statistical approaches to identify a few top significant GWAS signals which only provide fragmented and incomplete views of disease pathogenesis, whereas an integrative approach can utilize the power of collaborative use of various biological data types. In particular, this integrative approach will merge the summary statistics from the disease-associated GWASs and tissue-specific gene network models through the tissue-specific expression quantitative trait loci (eQTLs) signals, which correspond to another type of big-biological data resource, to prioritize the disease-associated subnetworks in a GRN and their hub genes that are potentially driving the disease progress. Hence, we purpose, not only elucidating the disease-mechanisms, but also predicting the hub (potential regulator) genes in these mechanisms. Therefore, our study may provide valuable guidance for testing new drug candidates, which target diseases-associated genes found from our study, on experimental animal models such as mouse or rats in pharmacological studies for cardiometabolic research. This interdisciplinary design incorporating computer science with biology, genetics, and medicine can significantly raise the quality of human lives.

The principal supervisor for this project is Dr. Zeyneb Kurt.

Eligibility and How to Apply:

Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
• Applicants cannot apply for this funding if currently engaged in Doctoral study at Northumbria or elsewhere.

For further details of how to apply, entry requirements and the application form, see

Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. RDF21/EE/CIS/KURTZeyneb) will not be considered.
Deadline for applications: 29 January 2021
Start Date: 1 October 2021
Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community.

Funding Notes

The studentship is available to Home and International (including EU) students, and includes a full stipend, paid for three years at RCUK rates (for 2020/21, this is £15,285 pa) and full tuition fees.


Recent publications by supervisors relevant to this project (optional)

I earned two post-doctoral fellowships in computational biology and bioinformatics research fields. These projects have been relevant to the proposed project:
1. 2017, American Heart Association (AHA) Postdoctoral Fellowship for 2 years.
2. 2017, University of California, Los Angeles (UCLA) Women’s Health Center Iris-Cantor/CTSI Young Investigator Award, Postdoctoral Fellowship for 1 year.
My top five journal articles relevant to the proposed project:
1. Kurt Z, Barrere-Cain R, Laguardia J, Mehrabian M, Pan C, et al. "Tissue-specific pathways and networks underlying sexual dimorphism in non-alcoholic fatty liver disease", Biology of Sex Differences 2018, vol. 9:46. doi: 10.1186/s13293-018-0205-7.
2. Krishnan KC*, Kurt Z*, Barrere-Cain R, Sabir S, Das A, et al. “Integration of Multi-omics Data from Mouse Diversity Panel Highlights Mitochondrial Dysfunction in Non-Alcoholic Fatty Liver Disease”, Cell Systems 2017. doi: 10.1016/j.cels.2017.12.006. *Shared (co-first) authors.
3. Hui S, Kurt Z, Tuominen L, Norheim F, Davis RC, et al. “The Genetic Architecture of Diet-induced Hepatic Fibrosis in Mice”, Hepatology 2018, vol.1, pp.1-20. doi: 10.1002/hep.30113.
4. Erdogan C, Kurt Z, Diri B, "Estimation of the proteomic cancer co-expression subnetworks by using association estimators", PLOS ONE 2017, doi:10.1371/journal.pone.0188016.
5. Kurt Z, Aydın N, and Altay G, “A Comprehensive Comparison of Association Estimators for Gene Network Inference Algorithms”, Bioinformatics: Oxford Journals 2014, vol. 30 (15), pp. 2142-2149. doi: 10.1093/bioinformatics/btu182

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here

The information you submit to Northumbria University will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.

* required field

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2021
All rights reserved.