Predicting cell morphological responses to perturbations using generative modeling
Abstract Advancements in high-throughput screenings enable the exploration of rich phenotypic readouts through high-content microscopy, expediting the development of phenotype-based drug discovery. However, analyzing large and complex high-content imaging screenings remains challenging due to incomp...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55707-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544527127511040 |
|---|---|
| author | Alessandro Palma Fabian J. Theis Mohammad Lotfollahi |
| author_facet | Alessandro Palma Fabian J. Theis Mohammad Lotfollahi |
| author_sort | Alessandro Palma |
| collection | DOAJ |
| description | Abstract Advancements in high-throughput screenings enable the exploration of rich phenotypic readouts through high-content microscopy, expediting the development of phenotype-based drug discovery. However, analyzing large and complex high-content imaging screenings remains challenging due to incomplete sampling of perturbations and the presence of technical variations between experiments. To tackle these shortcomings, we present IMage Perturbation Autoencoder (IMPA), a generative style-transfer model predicting morphological changes of perturbations across genetic and chemical interventions. We show that IMPA accurately captures morphological and population-level changes of both seen and unseen perturbations on breast cancer and osteosarcoma cells. Additionally, IMPA accounts for batch effects and can model perturbations across various sources of technical variation, further enhancing its robustness in diverse experimental conditions. With the increasing availability of large-scale high-content imaging screens generated by academic and industrial consortia, we envision that IMPA will facilitate the analysis of microscopy data and enable efficient experimental design via in-silico perturbation prediction. |
| format | Article |
| id | doaj-art-8a815f03be9c41d4aaa26a47a9a9bdbf |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-8a815f03be9c41d4aaa26a47a9a9bdbf2025-01-12T12:30:37ZengNature PortfolioNature Communications2041-17232025-01-0116111910.1038/s41467-024-55707-8Predicting cell morphological responses to perturbations using generative modelingAlessandro Palma0Fabian J. Theis1Mohammad Lotfollahi2Department of Computational Health, Institute of Computational BiologyDepartment of Computational Health, Institute of Computational BiologyDepartment of Computational Health, Institute of Computational BiologyAbstract Advancements in high-throughput screenings enable the exploration of rich phenotypic readouts through high-content microscopy, expediting the development of phenotype-based drug discovery. However, analyzing large and complex high-content imaging screenings remains challenging due to incomplete sampling of perturbations and the presence of technical variations between experiments. To tackle these shortcomings, we present IMage Perturbation Autoencoder (IMPA), a generative style-transfer model predicting morphological changes of perturbations across genetic and chemical interventions. We show that IMPA accurately captures morphological and population-level changes of both seen and unseen perturbations on breast cancer and osteosarcoma cells. Additionally, IMPA accounts for batch effects and can model perturbations across various sources of technical variation, further enhancing its robustness in diverse experimental conditions. With the increasing availability of large-scale high-content imaging screens generated by academic and industrial consortia, we envision that IMPA will facilitate the analysis of microscopy data and enable efficient experimental design via in-silico perturbation prediction.https://doi.org/10.1038/s41467-024-55707-8 |
| spellingShingle | Alessandro Palma Fabian J. Theis Mohammad Lotfollahi Predicting cell morphological responses to perturbations using generative modeling Nature Communications |
| title | Predicting cell morphological responses to perturbations using generative modeling |
| title_full | Predicting cell morphological responses to perturbations using generative modeling |
| title_fullStr | Predicting cell morphological responses to perturbations using generative modeling |
| title_full_unstemmed | Predicting cell morphological responses to perturbations using generative modeling |
| title_short | Predicting cell morphological responses to perturbations using generative modeling |
| title_sort | predicting cell morphological responses to perturbations using generative modeling |
| url | https://doi.org/10.1038/s41467-024-55707-8 |
| work_keys_str_mv | AT alessandropalma predictingcellmorphologicalresponsestoperturbationsusinggenerativemodeling AT fabianjtheis predictingcellmorphologicalresponsestoperturbationsusinggenerativemodeling AT mohammadlotfollahi predictingcellmorphologicalresponsestoperturbationsusinggenerativemodeling |