Document Type
Dissertation
Degree
Doctor of Philosophy (PhD)
Major/Program
Computer Science
First Advisor's Name
Giri Narasimhan
First Advisor's Committee Title
Committee Chair
Second Advisor's Name
Prem Chapagain
Second Advisor's Committee Title
Committee Member
Third Advisor's Name
Kalai Mathee
Third Advisor's Committee Title
Committee Member
Fourth Advisor's Name
Trevor Cickovski
Fourth Advisor's Committee Title
Committee Member
Fifth Advisor's Name
Ananda Mondal
Fifth Advisor's Committee Title
Committee Member
Sixth Advisor's Name
Cuong Nguyen
Sixth Advisor's Committee Title
Committee Member
Keywords
Deep learning, structural bioinformatics, transformer networks, image analysis, vision AI, molecular mimicry, pandemic preparedness, protein interface features, contrastive learning, affinity prediction, protein flexibility, protein complex conformations
Date of Defense
3-30-2023
Abstract
The binding of proteins plays an essential role in the majority of critical processes in a cell. The protein binding investigation methods have significant practical importance in understanding biological processes and the development of modern vaccines, drugs, and therapeutics. Existing tools have been unable to accurately assess the protein binding in a cost-effective manner. Experimental techniques, such as X-ray crystallography, are time-consuming, labor-intensive, and expensive.
The binding of proteins plays an essential role in most critical biological processes. Investigating methods to study protein binding is of great practical importance in the development of modern vaccines, drugs, and therapeutics. Existing tools have been unable to study protein binding in a cost-effective manner. Laboratory experiments are time-consuming, labor-intensive, and expensive. This dissertation presents state-of-the-art, scalable, and interpretable deep learning solutions to investigate protein binding for the study of molecular mimicry, protein docking, and binding affinity estimation. In the first part, we developed a computational pipeline called EMoMiS that predicts cross-reactivity events induced by molecular mimicry with particular emphasis on antibody-antigen binding. The EMoMiS pipeline used sequence similarity search and structural alignment to identify similar proteins, followed by the application of a deep learning model to evaluate the cross-reactive binding between an antibody (or antigen) and a mimicking protein. The resulting molecular mimicry search pipeline, EMoMiS, can be used as a tool for pandemic preparedness. When applied to the SARS-CoV-2 Spike protein and its antibodies, the pipeline identified many examples of molecular mimicry that can explain COVID-19-related side effects. In the second part, a deep learning approach called PIsToN was developed to classify and rank protein interfaces. The PIsToN can identify viable protein complexes from a large set of candidate complexes. It introduces a novel way to extract features to represent protein interfaces as 2D multi-channel images. The PIsToN was designed as a hybrid multi-attention transformer network endowed with explainability and significantly outperformed current state-of-the-art methods to classify and rank protein docking models. In the last part, we present a deep learning model called PI-KD that incorporates protein molecular dynamics to predict the binding strength of protein complexes. PI-KD achieved state-of-the-art performance in predicting the binding affinity of two macromolecules. Overall, this dissertation is a significant step toward the use of deep learning to investigate the complex world of protein binding in an efficient and accurate manner.
Identifier
FIDC011058
ORCID
https://orcid.org/0000-0001-9377-0263
Previously Published In
Stebliankin, V., Baral, P., Balbin, C., Nunez-Castilla, J., Sobhan, M., Cickovski, T., Mondal, A.M., Siltberg-Liberles, J., Chapagain, P., Mathee, K. and Narasimhan, G., 2022. EMoMiS: A pipeline for epitope-based molecular mimicry search in protein structures with applications to SARS-CoV-2. BioRxiv, pp.2022-02.
Stebliankin, V., Shirali, A., Baral, P., Chapagain, P. and Narasimhan, G., 2023. PIsToN: Evaluating Protein Binding Interfaces with Transformer Networks. bioRxiv, pp.2023-01.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Stebliankin, Vitalii, "Deep Learning Strategies to Investigate Protein Binding" (2023). FIU Electronic Theses and Dissertations. 5276.
https://digitalcommons.fiu.edu/etd/5276
Rights Statement
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).