Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes
Polygenic risk scores (PRS) estimate an individual’s risk of developing a certain disease, suggesting that differences between cells of individuals with high versus low PRS could give us insight into the cellular disease mechanisms. To study metabolic diseases, we analyze the distribution of cell st...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/156626 https://orcid.org/0009-0002-2864-4935 |
| _version_ | 1811093521976786944 |
|---|---|
| author | Tan, Zipei |
| author2 | Uhler, Caroline |
| author_facet | Uhler, Caroline Tan, Zipei |
| author_sort | Tan, Zipei |
| collection | MIT |
| description | Polygenic risk scores (PRS) estimate an individual’s risk of developing a certain disease, suggesting that differences between cells of individuals with high versus low PRS could give us insight into the cellular disease mechanisms. To study metabolic diseases, we analyze the distribution of cell states of lipocytes of individuals with different PRS for metabolic diseases, thereby associating individual-level genotypes with cell-level features. To accomplish this, we make use of a recent large-scale lipocyte microscopy imaging dataset. By learning a representation of multi-channel lipocyte microscopy images using a convolutional autoencoder, we perform unsupervised clustering on the learnt representations to identify different cell states. We analyze the distribution of these cell states in different individuals and associate their PRS to the observed cell state distributions. Finally, we show that it is possible to generate counterfactual lipocyte images and understand the effect of increased or reduced PRS on cell states through transforming the learnt representations. |
| first_indexed | 2024-09-23T15:46:26Z |
| format | Thesis |
| id | mit-1721.1/156626 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:46:26Z |
| publishDate | 2024 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1566262024-09-04T03:07:23Z Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes Tan, Zipei Uhler, Caroline Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Polygenic risk scores (PRS) estimate an individual’s risk of developing a certain disease, suggesting that differences between cells of individuals with high versus low PRS could give us insight into the cellular disease mechanisms. To study metabolic diseases, we analyze the distribution of cell states of lipocytes of individuals with different PRS for metabolic diseases, thereby associating individual-level genotypes with cell-level features. To accomplish this, we make use of a recent large-scale lipocyte microscopy imaging dataset. By learning a representation of multi-channel lipocyte microscopy images using a convolutional autoencoder, we perform unsupervised clustering on the learnt representations to identify different cell states. We analyze the distribution of these cell states in different individuals and associate their PRS to the observed cell state distributions. Finally, we show that it is possible to generate counterfactual lipocyte images and understand the effect of increased or reduced PRS on cell states through transforming the learnt representations. M.Eng. 2024-09-03T21:12:50Z 2024-09-03T21:12:50Z 2024-05 2024-07-11T14:36:09.597Z Thesis https://hdl.handle.net/1721.1/156626 https://orcid.org/0009-0002-2864-4935 Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) Copyright retained by author(s) https://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Tan, Zipei Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title | Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title_full | Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title_fullStr | Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title_full_unstemmed | Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title_short | Representation Learning Associates Patients’ Risks for Metabolic Diseases with Features of Their Lipocytes |
| title_sort | representation learning associates patients risks for metabolic diseases with features of their lipocytes |
| url | https://hdl.handle.net/1721.1/156626 https://orcid.org/0009-0002-2864-4935 |
| work_keys_str_mv | AT tanzipei representationlearningassociatespatientsrisksformetabolicdiseaseswithfeaturesoftheirlipocytes |