Covid-19 antibody discovery with topology-enhanced learning models
The recent global spread of Coronavirus disease 2019 (COVID-19) has been fueled by the appearance of various new variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), including Alpha, Beta, Gamma, Delta, Omicron, etc. The impact of variants on infectivity and monoclonal antib...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156992 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The recent global spread of Coronavirus disease 2019 (COVID-19) has been fueled by the appearance of various new variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), including Alpha, Beta, Gamma, Delta, Omicron, etc. The impact of variants on infectivity and monoclonal antibodies (mAbs) effectiveness is largely determined by how related receptor-binding domain (RBD) mutations affect ACE2 and antibody binding.
Topological Data Analysis (TDA) is a fast-growing field combining topology and computational geometry to retrieve features from high-dimensional datasets. In the face of noisy and incomplete datasets, TDA deals with qualitative geometric features independent of metric choice and minimizes the effect of noise.
This project reviews antibody structure, function, mutation impact and existing antibodies in clinical trials. We introduce the TopNetTree model which consists of topological feature generation and network models to predict the binding free energy change induced by RBD mutations. The previous related paper about mutation impact is also reviewed and some of the results are validated. |
|---|