Back

Cell Morphology accurately predicts the nuclear shape of adherent cells

Lawton, S.; Danzman, R. A.; Spagnuolo, R.; Stephan, S.; Graul, S.; Wiggan, O.; Ghosh, S.; Prasad, A.

2024-12-28 cell biology
10.1101/2024.12.28.630588 bioRxiv
Show abstract

Cells are internally tensed, or prestressed, largely by actomyosin contractility. We hypothesized that nuclear shape is quantitatively predictable from cell shape since prestress couples them both. We trained machine learning models on a publicly available image database of the WTC-11 cell line and predicted shape modes of the nucleus with high accuracy. We develop a U-Net architecture-based model, Cell2Nuc, that predicted nuclear voxels from the cell membrane with accuracies between 74%-87%. To investigate prestress, we cultured and imaged HeLa cells after inhibiting actomyosin contractility. The Cell2Nuc model retrained on the HeLa cells predicted nuclear voxels with slightly lower accuracy. Statistical analysis revealed changes in nuclear size and chromatin organization upon prestress inhibition. Similar trends were seen in images taken from NIH3T3 cells. Thus, cell shape encodes features of nuclear shape, their coupling is partly due to actomyosin contractility, whose abrogation leads to changes in chromatin organization of mechanosensitive origin.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.