Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication
This thesis investigates diverse computational methodologies for modeling cellular interactions using single-cell RNA sequencing (scRNA-seq) data. We evaluate the performance of Graph Neural Networks (GNNs) both with and without gene-gene edges, Contrastive Learning, and Variational Autoencoders (VA...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/156766 |
| _version_ | 1826216046630010880 |
|---|---|
| author | Yan, Binwei |
| author2 | Kellis, Manolis |
| author_facet | Kellis, Manolis Yan, Binwei |
| author_sort | Yan, Binwei |
| collection | MIT |
| description | This thesis investigates diverse computational methodologies for modeling cellular interactions using single-cell RNA sequencing (scRNA-seq) data. We evaluate the performance of Graph Neural Networks (GNNs) both with and without gene-gene edges, Contrastive Learning, and Variational Autoencoders (VAEs) across multiple datasets. Our study compares these methods and establishes benchmarks for assessing their effectiveness beyond traditional case studies. By integrating extensive signaling pathway data, we aim to unveil complex cell-cell communication patterns and regulatory mechanisms that conventional scRNA-seq analysis methods might overlook. Our approach emphasizes the use of spatial data as a crucial indicator, facilitated by the advanced capabilities of heterogeneous GNNs to model physical proximity. We found that our analysis of the functioning genes aligns with previous findings, proving our model’s effectiveness as a potential method for further analyze communication mechanisms. |
| first_indexed | 2024-09-23T16:41:28Z |
| format | Thesis |
| id | mit-1721.1/156766 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T16:41:28Z |
| publishDate | 2024 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1567662024-09-17T03:02:43Z Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication Yan, Binwei Kellis, Manolis Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science This thesis investigates diverse computational methodologies for modeling cellular interactions using single-cell RNA sequencing (scRNA-seq) data. We evaluate the performance of Graph Neural Networks (GNNs) both with and without gene-gene edges, Contrastive Learning, and Variational Autoencoders (VAEs) across multiple datasets. Our study compares these methods and establishes benchmarks for assessing their effectiveness beyond traditional case studies. By integrating extensive signaling pathway data, we aim to unveil complex cell-cell communication patterns and regulatory mechanisms that conventional scRNA-seq analysis methods might overlook. Our approach emphasizes the use of spatial data as a crucial indicator, facilitated by the advanced capabilities of heterogeneous GNNs to model physical proximity. We found that our analysis of the functioning genes aligns with previous findings, proving our model’s effectiveness as a potential method for further analyze communication mechanisms. M.Eng. 2024-09-16T13:47:50Z 2024-09-16T13:47:50Z 2024-05 2024-07-11T14:36:47.766Z Thesis https://hdl.handle.net/1721.1/156766 Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) Copyright retained by author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Yan, Binwei Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title | Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title_full | Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title_fullStr | Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title_full_unstemmed | Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title_short | Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication |
| title_sort | using heterogeneous graph neural networks hgnn to predict cell cell communication |
| url | https://hdl.handle.net/1721.1/156766 |
| work_keys_str_mv | AT yanbinwei usingheterogeneousgraphneuralnetworkshgnntopredictcellcellcommunication |