Edward B. Irvine

CAPO automates and selects protein-model adaptations by measuring feasibility and cost before training, improving performance while reducing compute usage and failures.

The paper predicts viral host range using a combination of experimental screening and deep learning to identify potential animal reservoirs for reverse zoonotic transmission.

This study designs antibody Fc-variants with programmable functional profiles using deep learning and experimental validation.

The paper develops a high-throughput method to profile SARS-CoV-2 RBD variants' affinity against antibodies, generating binding energy landscapes for variant analysis.

This paper introduces a method for high-throughput mutational library assembly using oligo-based Golden Gate assembly and validates it by improving nanobody affinity.

This study identifies protective antibodies against Mycobacterium tuberculosis and shows that their Fc-effector function and Fab domains collaborate to restrict infection through immune cell reorganization.

This study uses deep learning to identify antibodies resistant to SARS-CoV-2 Omicron variants by predicting their binding and escape from mutations.

The paper uses Markov Fields to integrate multi-modal immune data from vaccinated macaques, identifying critical immune interactions and predicting perturbation effects.

The paper identifies a relationship between protein structure and glycan structure, introducing a glycoimpact matrix to predict glycosylation patterns and validate it through disease variants and engineered antibodies.