From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments
The cell nucleus is a dynamic structure that changes locales during cellular processes such as proliferation, differentiation, or migration, and its mispositioning is a hallmark of several disorders. As with most mechanobiological activities of adherent cells, the repositioning and anchoring of the...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171110 |
| _version_ | 1826115404820381696 |
|---|---|
| author | Vasudevan, Jyothsna Zheng, Chuanxia Wan, James G. Cham, Tat-Jen Teck, Lim Chwee Fernandez, Javier G. |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Vasudevan, Jyothsna Zheng, Chuanxia Wan, James G. Cham, Tat-Jen Teck, Lim Chwee Fernandez, Javier G. |
| author_sort | Vasudevan, Jyothsna |
| collection | NTU |
| description | The cell nucleus is a dynamic structure that changes locales during cellular processes such as proliferation, differentiation, or migration, and its mispositioning is a hallmark of several disorders. As with most mechanobiological activities of adherent cells, the repositioning and anchoring of the nucleus are presumed to be associated with the organization of the cytoskeleton, the network of protein filaments providing structural integrity to the cells. However, demonstrating this correlation between cytoskeleton organization and nuclear position requires the parameterization of the extraordinarily intricate cytoskeletal fiber arrangements. Here, we show that this parameterization and demonstration can be achieved outside the limits of human conceptualization, using generative network and raw microscope images, relying on machine-driven interpretation and selection of parameterizable features. The developed transformer-based architecture was able to generate high-quality, completed images of more than 8,000 cells, using only information on actin filaments, predicting the presence of a nucleus and its exact localization in more than 70 per cent of instances. Our results demonstrate one of the most basic principles of mechanobiology with a remarkable level of significance. They also highlight the role of deep learning as a powerful tool in biology beyond data augmentation and analysis, capable of interpreting-unconstrained by the principles of human reasoning-complex biological systems from qualitative data. |
| first_indexed | 2024-10-01T03:54:34Z |
| format | Journal Article |
| id | ntu-10356/171110 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:54:34Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1711102023-10-13T15:36:32Z From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments Vasudevan, Jyothsna Zheng, Chuanxia Wan, James G. Cham, Tat-Jen Teck, Lim Chwee Fernandez, Javier G. School of Computer Science and Engineering Engineering::Computer science and engineering Cell Shape The cell nucleus is a dynamic structure that changes locales during cellular processes such as proliferation, differentiation, or migration, and its mispositioning is a hallmark of several disorders. As with most mechanobiological activities of adherent cells, the repositioning and anchoring of the nucleus are presumed to be associated with the organization of the cytoskeleton, the network of protein filaments providing structural integrity to the cells. However, demonstrating this correlation between cytoskeleton organization and nuclear position requires the parameterization of the extraordinarily intricate cytoskeletal fiber arrangements. Here, we show that this parameterization and demonstration can be achieved outside the limits of human conceptualization, using generative network and raw microscope images, relying on machine-driven interpretation and selection of parameterizable features. The developed transformer-based architecture was able to generate high-quality, completed images of more than 8,000 cells, using only information on actin filaments, predicting the presence of a nucleus and its exact localization in more than 70 per cent of instances. Our results demonstrate one of the most basic principles of mechanobiology with a remarkable level of significance. They also highlight the role of deep learning as a powerful tool in biology beyond data augmentation and analysis, capable of interpreting-unconstrained by the principles of human reasoning-complex biological systems from qualitative data. Ministry of Education (MOE) Published version The Singaporean Ministry of Education has supported this research through the MOE2018-T2-2-176 grant to Javier G. Fernandez. 2023-10-13T06:56:17Z 2023-10-13T06:56:17Z 2022 Journal Article Vasudevan, J., Zheng, C., Wan, J. G., Cham, T., Teck, L. C. & Fernandez, J. G. (2022). From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments. PloS ONE, 17(7), e0271056-. https://dx.doi.org/10.1371/journal.pone.0271056 1932-6203 https://hdl.handle.net/10356/171110 10.1371/journal.pone.0271056 35905093 2-s2.0-85135420871 7 17 e0271056 en PloS ONE © 2022 Vasudevan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. application/pdf |
| spellingShingle | Engineering::Computer science and engineering Cell Shape Vasudevan, Jyothsna Zheng, Chuanxia Wan, James G. Cham, Tat-Jen Teck, Lim Chwee Fernandez, Javier G. From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title | From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title_full | From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title_fullStr | From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title_full_unstemmed | From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title_short | From qualitative data to correlation using deep generative networks: demonstrating the relation of nuclear position with the arrangement of actin filaments |
| title_sort | from qualitative data to correlation using deep generative networks demonstrating the relation of nuclear position with the arrangement of actin filaments |
| topic | Engineering::Computer science and engineering Cell Shape |
| url | https://hdl.handle.net/10356/171110 |
| work_keys_str_mv | AT vasudevanjyothsna fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments AT zhengchuanxia fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments AT wanjamesg fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments AT chamtatjen fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments AT tecklimchwee fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments AT fernandezjavierg fromqualitativedatatocorrelationusingdeepgenerativenetworksdemonstratingtherelationofnuclearpositionwiththearrangementofactinfilaments |