Oliver Nakano-Baker

The paper evaluates contrastive learning on VOC-OR binding datasets, showing improved generalization and reduced performance inflation from identity leakage.

The paper introduces iOBPdb, a database compiling functional data on odorant binding proteins from 91 insect species, enabling comparative analysis of structure-function relationships.

The paper develops a high-throughput peptide-selection protocol to generate a large dataset of solid-binding peptides, emphasizing data quality and enabling future machine learning applications.

The paper introduces VSEPRnet, a method to encode biomolecule structures for functionality prediction, demonstrating improved accuracy in predicting peptide-MHC binding affinities.