Computer vision reveals hidden variables underlying NF-κB activation in single cells

Individual cells are heterogeneous when responding to environmental cues. Under an external signal, certain cells activate gene regulatory pathways, while others completely ignore that signal. Mechanisms underlying cellular heterogeneity are often inaccessible because experiments needed to study molecular states destroy the very states that we need to examine. Here, we developed an image-based support vector machine learning model to uncover variables controlling activation of the immune pathway nuclear factor xB (NF-kappa B). Computer vision analysis predicts the identity of cells that will respond to cytokine stimulation and shows that activation is predetermined by minute amounts of leaky NF-kappa B (p65:p50) localization to the nucleus. Mechanistic modeling revealed that the ratio of NF-kappa B to inhibitor of NF-kappa B predetermines leakiness and activation probability of cells. While cells transition between molecular states, they maintain their overall probabilities for NF-kappa B activation. Our results demonstrate how computer vision can find mechanisms behind heterogeneous single-cell activation under proinflammatory stimuli.

Automated summary

The study investigates the heterogeneity of individual cells in response to environmental cues, revealing underlying mechanisms using computer vision technology. Results demonstrate that the ratio of NF-kappa B to inhibitor of NF-kappa B determines the activation probability of cells, highlighting the importance of minute leaky amounts of NF-kappa B in cell activation predictability.