Iain H. Moal

Addressing the antibody germline bias and its effect on language models for improved antibody design

This study addresses germline bias in antibody language models by developing AbLang-2, which predicts non-germline residues more effectively than existing models.

Paragraph - Antibody paratope prediction using Graph Neural Networks with minimal feature vectors

Paragraph predicts antibody paratopes using graph neural networks with minimal features, outperforming existing tools without antigen information.

KA-Search: Rapid and exhaustive sequence identity search of known antibodies

KA-Search rapidly and exhaustively searches for similar antibody sequences across defined regions in large antibody repertoires to predict properties like immunogenicity and antigen specificity.

AbLang: An antibody language model for completing antibody sequences

AbLang is an antibody-specific language model that restores missing residues in antibody sequences more effectively than existing methods.

SKEMPI 2.0: An updated benchmark of changes in protein-protein binding energy, kinetics and thermodynamics upon mutation

SKEMPI 2.0 updates a database of binding energy changes upon mutation with expanded data on kinetics, thermodynamics, and binding abolition.