An explainable language model for antibody specificity prediction using curated influenza hemagglutinin antibodies.

Despite decades of antibody research, it remains challenging to predict the specificity of an antibody solely based on its sequence. Two major obstacles are the lack of appropriate models and the inaccessibility of datasets for model training. In this study, we curated >5,000 influenza hemagglutinin (HA) antibodies by mining research publications and patents, which revealed many distinct sequence features between antibodies to HA head and stem domains. We then leveraged this dataset to develop a lightweight memory B cell language model (mBLM) for sequence-based antibody specificity prediction. Model explainability analysis showed that mBLM could identify key sequence features of HA stem antibodies. Additionally, by applying mBLM to HA antibodies with unknown epitopes, we discovered and experimentally validated many HA stem antibodies. Overall, this study not only advances our molecular understanding of the antibody response to the influenza virus but also provides a valuable resource for applying deep learning to antibody research.

Sarm1 knockout prevents type 1 diabetic bone disease in females independent of neuropathy.

Patients with diabetes have a high risk of developing skeletal diseases accompanied by diabetic peripheral neuropathy (DPN). In this study, we isolated the role of DPN in skeletal disease with global and conditional knockout models of sterile-α and TIR-motif-containing protein-1 (Sarm1). SARM1, an NADase highly expressed in the nervous system, regulates axon degeneration upon a range of insults, including DPN. Global knockout of Sarm1 prevented DPN, but not skeletal disease, in male mice with type 1 diabetes (T1D). Female wild-type mice also developed diabetic bone disease but without DPN. Unexpectedly, global Sarm1 knockout completely protected female mice from T1D-associated bone suppression and skeletal fragility despite comparable muscle atrophy and hyperglycemia. Global Sarm1 knockout rescued bone health through sustained osteoblast function with abrogation of local oxidative stress responses. This was independent of the neural actions of SARM1, as beneficial effects on bone were lost with neural conditional Sarm1 knockout. This study demonstrates that the onset of skeletal disease occurs rapidly in both male and female mice with T1D completely independently of DPN. In addition, this reveals that clinical SARM1 inhibitors, currently being developed for treatment of neuropathy, may also have benefits for diabetic bone through actions outside of the nervous system.

Epistasis mediates the evolution of the receptor binding mode in recent human H3N2 hemagglutinin.

The receptor-binding site of influenza A virus hemagglutinin partially overlaps with major antigenic sites and constantly evolves. In this study, we observe that mutations G186D and D190N in the hemagglutinin receptor-binding site have coevolved in two recent human H3N2 clades. X-ray crystallography results show that these mutations coordinately drive the evolution of the hemagglutinin receptor binding mode. Epistasis between G186D and D190N is further demonstrated by glycan binding and thermostability analyses. Immunization and neutralization experiments using mouse and human samples indicate that the evolution of receptor binding mode is accompanied by a change in antigenicity. Besides, combinatorial mutagenesis reveals that G186D and D190N, along with other natural mutations in recent H3N2 strains, alter the compatibility with a common egg-adaptive mutation in seasonal influenza vaccines. Overall, our findings elucidate the role of epistasis in shaping the recent evolution of human H3N2 hemagglutinin and substantiate the high evolvability of its receptor-binding mode.