Nature· Alireza Karbalayghareh·· 13 hours agoPickScore78
Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells
In brief
The authors present DynaVelo, a generative deep learning model that uses a neural ODE to jointly model RNA expression and TF motif accessibility. It infers cell dynamics from single-time-point paired scRNA and scATAC multiome data, predicts loss-of-function perturbation outcomes, and nominates rescue targets.
Why it matters
DynaVelo incorporates TF motif accessibility into a neural ODE and predicts loss-of-function and rescue perturbations, and the method transfers to other single-cell multiomic settings.
Source: Nature