Suriyanarayanan Vaikuntanathan

This study shows how motor activity enables cytoskeletal structures to adapt mechanically, transforming from contractile to extensile states under tension.

The paper trains a diffusion model on actomyosin system data to predict nonlinear trends in cortical flow at unseen filament turnover rates.

This paper investigates ultrafast contraction in Spirostomum using myonemes, showing centrin-Sfi1 structures drive calcium-triggered contraction without actomyosin or ATP.

The paper identifies a molecular mechanism for non-genetic learning in single cells using reversible interaction networks and autoregulatory training rules.

Keeping SCORE transforms diffusion models into probabilistic classifiers for genomics, providing accurate predictions with uncertainty and interpretability across multiple tasks.

The paper identifies target-specific fitness landscapes in protein-protein interactions and develops a supervised contrastive learning approach to predict binders.

CIPHER uses gene co-fluctuations in unperturbed cells to predict transcriptome-wide responses to perturbations, outperforming existing methods and revealing key regulatory structures.

The paper introduces TopicVelo, a method to improve RNA velocity estimation by integrating bursty transcriptional dynamics, enabling accurate process-specific velocity inference and transition analysis.

The paper develops a thermodynamic framework to model branched actin network self-assembly, showing how energy dissipation influences growth, force, and morphology tradeoffs.