A. Slabodkin

Weakly supervised identification and generation of adaptive immune receptor sequences associated with immune disease status

The paper develops AIRRTM, a generative model that identifies and generates disease-associated adaptive immune receptor sequences using only repertoire-level immune status data.

Atypical memory B cells form a pre-plasmacellular reservoir for steady-state IgD responses to common nasopharyngeal antigens

The paper identifies a new subset of tonsillar memory B cells that serve as precursors for IgD-secreting plasma cells, contributing to steady-state IgD responses to common antigens.

In silico proof of principle of machine learning-based antibody design at unconstrained scale

This paper demonstrates that deep generative models can design high-affinity, developable antibodies at scale using synthetic data and transfer learning.

Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for real-world antibody specificity prediction

The paper introduces Absolut!, a software suite generating synthetic antibody-antigen structures to benchmark machine learning methods for antibody specificity prediction.

Individualized VDJ recombination predisposes the available Ig sequence space

The paper shows that VDJ recombination rules vary between individuals, leading to individual-specific Ig sequence spaces.

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

The paper identifies a compact vocabulary of paratope-epitope interaction motifs that enables machine learning prediction of antibody-antigen binding.