Sakib Ferdous

RealKcat predicts enzyme kinetics from sequence using a curated dataset and embeddings, showing sensitivity to catalytic mutations and robustness across evaluations.

This paper introduces EscaPRRS, a Bayesian variational autoencoder that predicts antibody escape propensities of PRRSV GP5 mutants using structural and sequence data, showing strong correlation with binding affinities.

The paper develops a method to classify hydrolase functions using structural similarity of reaction cores, identifying enzyme backbones that can support multiple catalytic activities.