Conditionally Site-Independent Neural Evolution of Antibody Sequences

TL;DR

This paper introduces CoSiNE, a neural network-based model that captures antibody evolution more accurately than traditional methods, enabling better prediction and optimization of antibody affinity through a novel sampling scheme.

Contribution

We develop CoSiNE, a deep neural network-based continuous-time Markov model that captures complex epistatic interactions in antibody evolution, bridging the gap between classical phylogenetics and deep learning.

Findings

CoSiNE outperforms existing language models in zero-shot variant effect prediction.

The model provides a quadratic error bound for capturing epistatic effects.

Guided Gillespie sampling enables efficient affinity optimization.

Abstract

Common deep learning approaches for antibody engineering focus on modeling the marginal distribution of sequences. By treating sequences as independent samples, however, these methods overlook affinity maturation as a rich and largely untapped source of information about the evolutionary process by which antibodies explore the underlying fitness landscape. In contrast, classical phylogenetic models explicitly represent evolutionary dynamics but lack the expressivity to capture complex epistatic interactions. We bridge this gap with CoSiNE, a continuous-time Markov chain parameterized by a deep neural network. Mathematically, we prove that CoSiNE provides a first-order approximation to the intractable sequential point mutation process, capturing epistatic effects with an error bound that is quadratic in branch length. Empirically, CoSiNE outperforms state-of-the-art language models in zero-shot variant effect prediction by explicitly disentangling selection from context-dependent somatic hypermutation. Finally, we introduce Guided Gillespie, a classifier-guided sampling scheme that steers CoSiNE at inference time, enabling efficient optimization of antibody binding affinity toward specific antigens.