Detecting abnormal cell behaviors from dry mass time series
Abstract The prediction of pathological changes on single cell behaviour is a challenging task for deep learning models. Indeed, in self-supervised learning methods, no prior labels are used for the training and all of the information for event predictions are extracted from the data themselves. We...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-57684-w |
| _version_ | 1827130287607250944 |
|---|---|
| author | Romain Bailly Marielle Malfante Cédric Allier Chiara Paviolo Lamya Ghenim Kiran Padmanabhan Sabine Bardin Jérôme Mars |
| author_facet | Romain Bailly Marielle Malfante Cédric Allier Chiara Paviolo Lamya Ghenim Kiran Padmanabhan Sabine Bardin Jérôme Mars |
| author_sort | Romain Bailly |
| collection | DOAJ |
| description | Abstract The prediction of pathological changes on single cell behaviour is a challenging task for deep learning models. Indeed, in self-supervised learning methods, no prior labels are used for the training and all of the information for event predictions are extracted from the data themselves. We present here a novel self-supervised learning model for the detection of anomalies in a given cell population, StArDusTS. Cells are monitored over time, and analysed to extract time-series of dry mass values. We assessed its performances on different cell lines, showing a precision of 96% in the automatic detection of anomalies. Additionally, anomaly detection was also associated with cell measurement errors inherent to the acquisition or analysis pipelines, leading to an improvement of the upstream methods for feature extraction. Our results pave the way to novel architectures for the continuous monitoring of cell cultures in applied research or bioproduction applications, and for the prediction of pathological cellular changes. |
| first_indexed | 2024-04-24T16:19:47Z |
| format | Article |
| id | doaj.art-713270a8224f4a1f8b2948288b411b09 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2025-03-20T16:13:48Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-713270a8224f4a1f8b2948288b411b092024-09-01T11:15:29ZengNature PortfolioScientific Reports2045-23222024-03-0114111210.1038/s41598-024-57684-wDetecting abnormal cell behaviors from dry mass time seriesRomain Bailly0Marielle Malfante1Cédric Allier2Chiara Paviolo3Lamya Ghenim4Kiran Padmanabhan5Sabine Bardin6Jérôme Mars7Univ. Grenoble Alpes, CEA, ListUniv. Grenoble Alpes, CEA, ListUniv. Grenoble Alpes, CEA, LetiUniv. Grenoble Alpes, CEA, LetiUniv. Grenoble Alpes, INSERM, CEA-IRIG, BGE, BiomicsInstitut de Génomique Fonctionnelle de Lyon, Univ. Lyon, CNRS/ENS, UMR 5242Institut Curie, PSL Research University, CNRS, UMR 144, Molecular Mechanisms of Intracellular TransportUniv. Grenoble Alpes, CNRS, Grenoble-INP, GIPSA-LabAbstract The prediction of pathological changes on single cell behaviour is a challenging task for deep learning models. Indeed, in self-supervised learning methods, no prior labels are used for the training and all of the information for event predictions are extracted from the data themselves. We present here a novel self-supervised learning model for the detection of anomalies in a given cell population, StArDusTS. Cells are monitored over time, and analysed to extract time-series of dry mass values. We assessed its performances on different cell lines, showing a precision of 96% in the automatic detection of anomalies. Additionally, anomaly detection was also associated with cell measurement errors inherent to the acquisition or analysis pipelines, leading to an improvement of the upstream methods for feature extraction. Our results pave the way to novel architectures for the continuous monitoring of cell cultures in applied research or bioproduction applications, and for the prediction of pathological cellular changes.https://doi.org/10.1038/s41598-024-57684-w |
| spellingShingle | Romain Bailly Marielle Malfante Cédric Allier Chiara Paviolo Lamya Ghenim Kiran Padmanabhan Sabine Bardin Jérôme Mars Detecting abnormal cell behaviors from dry mass time series Scientific Reports |
| title | Detecting abnormal cell behaviors from dry mass time series |
| title_full | Detecting abnormal cell behaviors from dry mass time series |
| title_fullStr | Detecting abnormal cell behaviors from dry mass time series |
| title_full_unstemmed | Detecting abnormal cell behaviors from dry mass time series |
| title_short | Detecting abnormal cell behaviors from dry mass time series |
| title_sort | detecting abnormal cell behaviors from dry mass time series |
| url | https://doi.org/10.1038/s41598-024-57684-w |
| work_keys_str_mv | AT romainbailly detectingabnormalcellbehaviorsfromdrymasstimeseries AT mariellemalfante detectingabnormalcellbehaviorsfromdrymasstimeseries AT cedricallier detectingabnormalcellbehaviorsfromdrymasstimeseries AT chiarapaviolo detectingabnormalcellbehaviorsfromdrymasstimeseries AT lamyaghenim detectingabnormalcellbehaviorsfromdrymasstimeseries AT kiranpadmanabhan detectingabnormalcellbehaviorsfromdrymasstimeseries AT sabinebardin detectingabnormalcellbehaviorsfromdrymasstimeseries AT jeromemars detectingabnormalcellbehaviorsfromdrymasstimeseries |