Chloe Hsu

The paper uses allelic inclusion data to train models that identify antibody sequence constraints, finding stronger correlations with antibody properties than existing methods.

GENTANGLE is a computational tool for designing overlapping gene pairs in microbial genomes, enabling safer genetic engineering through gene entanglements.

Adding 12 million AlphaFold2-predicted structures to training lifts native sequence recovery on held-out backbones to 51.6%, versus 42.2% for the best experimental-only model; likelihoods score mutation effects zero-shot.

The paper demonstrates that a hybrid HMM-DNN approach outperforms both pure HMM and DNN methods for 5mC calling with incomplete training data.

The paper evaluates methods for predicting protein fitness using both evolutionary and assay-labelled data, finding a simple baseline approach competitive with more complex methods.