Martin K. M. Engqvist

The paper trains a deep learning model to predict enzyme thermal adaptation using a dataset of enzymes labeled with optimal growth temperatures.

A substrate graph neural network plus protein-sequence CNN predicts enzyme kcat (test Pearson r 0.71), tracks mutation effects, and parameterizes enzyme-constrained models for 343 yeast/fungi species.

This paper introduces ESP, a machine learning model predicting enzyme-substrate pairs with over 90% accuracy, outperforming existing models for specific enzyme families.

The paper develops a deep learning model to predict Michaelis constants for enzyme-substrate combinations using structural features.

This paper introduces ProteinGAN, a GAN that generates functional protein sequences, showing 24% of generated sequences are soluble and active in vitro.

This study shows that physiological levels of rNMPs in mtDNA do not compromise its stability across mouse lifespan.

The paper develops machine learning models to predict microorganism growth temperatures and enzyme catalytic optima using proteome-wide amino acid composition data.

The paper correlates enzyme annotations with microbial growth temperatures to identify metabolic adaptations to different temperatures, finding 319 temperature-associated enzyme activities and 33 DUFs linked to temperature adaptation.