Debsindhu Bhowmik

This paper uses deep learning language models to predict SARS-CoV-2 inhibitors by generating and scoring drug candidates based on protein binding affinity.

This paper trains and evaluates language models on protein sequences to predict structural and localization features, achieving state-of-the-art results without evolutionary information.

The paper develops an interactive visual analytics system to evaluate and analyze deep embeddings of large-scale molecular dynamics simulations.