Sujith Sritharan

This paper evaluates limitations of deep learning in biomolecular structure prediction, highlighting the benefits of explicit ion modeling for improving conformational accuracy.

The paper shows plasmodesmata function as ER-PM tubular membrane contact sites that regulate intercellular molecular exchange in plants through PI4P and MCTP proteins.

The paper predicts the structure of Arabidopsis MCTP4's transmembrane region using deep learning and explores its dynamics with molecular simulations, revealing conformational complexity not captured by deep learning alone.