Back

MORPHIS (MORPHological Interpretable Signature) captures heterogeneous treatment- and aging-related responses of single cells

Bohr, F.; Oikonomou, A.; Nielsen, E. E. M.; Konstantinidis, G.; Mortensen, J. S.; Tavernarakis, N.; Nielsen, H. M.; Hatzakis, N. S.

2026-03-25 biophysics
10.64898/2026.03.24.713910 bioRxiv
Show abstract

Cell morphology encodes changes in cytoskeletal and organelle organization during disease, treatment, and aging, yet is often assessed qualitatively or through poorly interpretable feature sets extracted from microscopy images. Here we introduce MORPHIS (MORPHological Interpretable Signature), a machine learning framework on explainable, analytically rich features paired with statistical methodologies for robust and interpretable quantification of single-cell morphological signature. MORPHIS extracts compact, interpretable feature signatures that capture both perturbation-specific response magnitude and heterogeneous cellular responses. It accurately distinguishes treatment-specific morphological signatures of eight mechanistically distinct membrane-active and intracellular-targeting compounds in Caco-2 and HeLa cells elucidating conserved and divergent phenotypic responses among compound-classes, as well as ultrastructural nuclear alterations upon aging of C. elegans and quantifies heterogeneous single-cell fractional responses. By remaining cell-type and perturbation agnostic, MORPHIS provides a generalizable framework for quantifying morphological signatures across diverse biological contexts including pharmacological treatment or aging.

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.