{ "abstract": "Understanding non-genetic determinants of cell fate is critical for developing and improving cancer therapies, as genetically identical cells can exhibit divergent outcomes under the same treatment conditions. In this work, we present a deep learning approach for cell fate prediction from raw long-term live-cell recordings of cancer cell populations under chemotherapeutic treatment. Our Transformer model is trained to predict cell fate directly from raw image sequences, without relying on predefined morphological or molecular features. Beyond classification, we introduce a comprehensive explainability framework for interpreting the temporal and morphological cues guiding the model’s predictions. We demonstrate that prediction of cell outcomes is possible based on the video only, our model achieves balanced accuracy of 0.94 and an F1-score of 0.93. Attention and masking experiments further indicate that the signal predictive of the cell fate is not uniquely located in the final frames of a cell trajectory, as reliable predictions are possible up to 8 h before the event. Our analysis reveals distinct temporal distribution of predictive information in the mitotic and apoptotic sequences, as well as the role of cell morphology and p53 signaling in determining cell outcomes. Together, these findings demonstrate that attention-based temporal models enable accurate cell fate prediction while providing biologically interpretable insights into non-genetic determinants of cellular decision-making. Author summary: Cancer treatment often fails because not all cells respond in the same way. Even when exposed to the same drug, some cells die while others survive and continue to grow, which can lead to relapse. Understanding why genetically identical cells make different decisions is therefore an important challenge. In this study, we investigate whether it is possible to predict the fate of individual cells directly from time-lapse microscopy videos. We develop a computational approach that learns from raw image sequences without relying on manually defined features. This allows us to capture subtle changes in cell behavior over time. We find that cell fate can be predicted with high accuracy based on the video data alone, and that informative signals appear well before the final outcome is visible. By analyzing the model, we identify when during a cell’s lifetime predictive information emerges and which aspects of cell behavior are most relevant. Our results show that dynamic patterns in cell behavior contain early indicators of fate decisions, providing new opportunities to better understand variability in treatment response.", "abstract_shown": true, "affiliations": [ "Institute for Biomedical Informatics, Faculty of Medicine, University of Cologne and University Hospital Cologne, Cologne, Germany", "Faculty of Mathematics and Natural Sciences, University of Cologne, Cologne, Germany", "Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), University of Cologne, Cologne, Germany", "Center for Molecular Medicine Cologne (CMMC), University of Cologne and University Hospital Cologne, Cologne, Germany", "Granada Lab, Berlin, Germany" ], "article_type": "Research Article", "arxiv": null, "author_total": 5, "authors": [ { "affs": [ 0 ], "name": "Florian Bürger" }, { "affs": [ 1 ], "name": "Martim Dias Gomes" }, { "affs": [ 2 ], "name": "Adrián E. Granada" }, { "affs": [ 3 ], "name": "Noémie Moreau" }, { "affs": [ 4 ], "name": "Katarzyna Bozek" } ], "bibtex": "https://research.draconitic.com/paper/3z87cgbnpsqjf.bib", "cited_by": 0, "doi": "10.1371/journal.pcbi.1014813", "fulltext_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014813", "id": "3z87cgbnpsqjf", "issns": [ "1553-7358", "1553-734X" ], "landing_url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014813", "language": "eng", "licence": "CC-BY", "licence_label": "CC BY", "licence_source": "article", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "openalex", "1304|Cell Image Analysis Techniques" ], [ "plos", "/Biology and life sciences/Cell biology/Cell processes/Cell cycle and cell division" ], [ "plos", "/Biology and life sciences/Cell biology/Cell processes/Cell cycle and cell division/Mitosis" ], [ "plos", "/Biology and life sciences/Cell biology/Cell processes/Cell death/Apoptosis" ], [ "plos", "/Biology and life sciences/Cell biology/Chromosome biology/Mitosis" ], [ "plos", "/Biology and life sciences/Cell biology/Signal transduction/Cell signaling/Signaling cascades/Apoptotic signaling cascade" ], [ "plos", "/Biology and life sciences/Chronobiology" ], [ "plos", "/Medicine and health sciences/Oncology/Cancer treatment" ], [ "plos", "/Medicine and health sciences/Oncology/Cancer treatment/Epigenetic therapy" ], [ "plos", "/Medicine and health sciences/Pharmaceutics/Dose prediction methods" ] ], "openalex": "W7138876509", "pdf_url": "https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1014813&type=printable", "pmcid": "PMC13657290", "pmid": null, "published": "2026-10-01", "publisher": "Public Library of Science", "ris": "https://research.draconitic.com/paper/3z87cgbnpsqjf.ris", "sources": [ { "first_seen": "2026-10-30T12:17:30Z", "native_id": "10.1371/journal.pcbi.1014813", "source": "plos", "url": "https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014813" }, { "first_seen": "2026-10-30T12:17:35Z", "native_id": "PMC:PMC13657290", "source": "europepmc", "url": "https://europepmc.org/article/PMC/PMC13657290" } ], "subjects": [ { "field": "biology", "origin": "plos:cell biology", "subfield": "cell-biology" } ], "title": "Understanding cell fate decisions with temporal attention", "title_text": "Understanding cell fate decisions with temporal attention", "type": "peer-reviewed", "updated_at": "2026-10-30T12:17:35Z", "url": "https://research.draconitic.com/paper/3z87cgbnpsqjf", "venue": "PLOS Computational Biology", "versions": [] }