Nabia Shahreen

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

This study uses machine learning to identify minimal gene signatures predicting antibiotic resistance in Pseudomonas aeruginosa with high accuracy.

This paper develops a genome-scale metabolic model for Treponema pallidum, identifies glycerol-3-phosphate dehydrogenase as an alternative electron sink, and validates its predictive accuracy with proteomics data.

This paper uses artificial neural networks to predict growth rates of Rhodopseudomonas palustris on lignin breakdown products by analyzing transcriptomics and proteomics data, identifying key transport proteins as critical predictors.

This study identifies a thermodynamic bottleneck in the TCA cycle of S. aureus that favors acetate overflow metabolism for bioenergetic efficiency.

The paper shows that optimal protein allocation in Neisseria gonorrhoeae enhances GltA and AcnB activity, delaying acetate overflow for ATP production.