Sergio Bacallado

The paper introduces a hybrid framework to isolate stability-independent activity effects in enzymes using dual-graph deconvolution, validated with experimental data.

CAZyLingua uses protein language models to annotate carbohydrate-active enzymes in metagenomic data, outperforming traditional methods and revealing new annotations in disease-related datasets.

This paper uses transfer learning to identify potent antibacterials from large chemical libraries, finding 54% of tested compounds active against E. coli with sub-micromolar potency.

This paper uses conditional neural processes to predict adverse drug reactions from sparse data and finds they are well-calibrated and effective across organ systems.