Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
44354.pdf (7.52 MB)
ETD Abstract Container
Abstract Header
Modeling Complex Networks via Graph Neural Networks
Author Info
Yella, Jaswanth
ORCID® Identifier
http://orcid.org/0000-0002-0750-6157
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1684773048837483
Abstract Details
Year and Degree
2023, PhD, University of Cincinnati, Engineering and Applied Science: Computer Science and Engineering.
Abstract
Traditional drug discovery is costly and time-consuming. With the availability of large-scale molecular interaction networks, novel predictive modeling strategies have become vital to study the effect of drugs. Graphs are a powerful and flexible data structure in this regard. Biomedical graphs encompass the complex relationships between drugs, diseases, genes, and other micro/macroscopic effects of drugs. Hence, analyzing and modeling graphs can be valuable in identifying novel insights for drug discovery and its effects. Recently, deep learning research has made significant advances in image, speech, and natural language domains. The research in these fields has fostered progress in applying neural networks to graphs, referred to as graph neural networks (GNNs), for learning and identifying valuable hidden insights in graphs. While these GNNs are effective in learning representations, early research has focused primarily on optimizing GNNs for simple graph structures. Real-world graphs, however, tend to have complex characteristics such as heterogeneity, multi-modality, and combinatoriality. These complexities are particularly apparent in biomedical graphs, particularly in the areas of drug repurposing, virtual screening, and drug-drug interaction studies. This hinders the ability of GNNs to learn accurate representations and fully understand a drug’s behavior within the human body. Furthermore, for most current methods, the interpretation of the inferred predictions has not been investigated in detail, leading to skepticism in their adoption, especially in biomedical and healthcare domains. The work in this thesis aims to enhance the capabilities of GNNs for complex networks by studying and generating hypotheses for drug discovery and drug-drug interaction studies in biological networks. To achieve this, GNNs have been investigated and improved with three specific aims. Aim 1 is to develop GNNs that take heterogeneous networks as input and use multi-view attention to learn representations of the nodes. This improves link prediction accuracy for heterogeneous networks and, in biomedical networks, helps identify novel repurposable drug candidates. Aim 2 is to develop GNNs for multimodal graph inputs and further propose multimodal attention to fuse various representations across modalities. This allows the training of multiple modalities simultaneously and performs virtual screening to identify novel associations, e.g., drug-target associations. The third aim is to develop GNNs for combinatorial graphs, combining multiple modalities, and performing a multimodal fusion of different node representations. A decoder is then trained to predict the effects of combinations of nodes, and the entire process is trained end-to-end. This can be used to study the adverse effects of drug combinations by training GNNs using multimodal and combinatorial data. In each of these aims, case studies are performed that interpret the predictions through literature evidence and tools. The thesis concludes by discussing the benefits, limitations, and potential future extensions of the proposed frameworks for applying GNNs to complex networks.
Committee
Anil Jegga, DVM MRes (Committee Chair)
Raj Bhatnagar, Ph.D. (Committee Member)
Mayur Sarangdhar, PhD (Committee Member)
Ali Minai, Ph.D. (Committee Member)
Yizong Cheng, Ph.D. (Committee Member)
Pages
155 p.
Subject Headings
Computer Science
Keywords
graph neural networks
;
complex networks
;
deep learning
;
multimodal learning
;
drug discovery
;
drug interactions
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Yella, J. (2023).
Modeling Complex Networks via Graph Neural Networks
[Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1684773048837483
APA Style (7th edition)
Yella, Jaswanth.
Modeling Complex Networks via Graph Neural Networks.
2023. University of Cincinnati, Doctoral dissertation.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1684773048837483.
MLA Style (8th edition)
Yella, Jaswanth. "Modeling Complex Networks via Graph Neural Networks." Doctoral dissertation, University of Cincinnati, 2023. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1684773048837483
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
ucin1684773048837483
Download Count:
0
Copyright Info
© 2023, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.