English

Multi-segment preserving sampling for deep manifold sampler

Machine Learning 2022-05-10 v1 Biomolecules

Abstract

Deep generative modeling for biological sequences presents a unique challenge in reconciling the bias-variance trade-off between explicit biological insight and model flexibility. The deep manifold sampler was recently proposed as a means to iteratively sample variable-length protein sequences by exploiting the gradients from a function predictor. We introduce an alternative approach to this guided sampling procedure, multi-segment preserving sampling, that enables the direct inclusion of domain-specific knowledge by designating preserved and non-preserved segments along the input sequence, thereby restricting variation to only select regions. We present its effectiveness in the context of antibody design by training two models: a deep manifold sampler and a GPT-2 language model on nearly six million heavy chain sequences annotated with the IGHV1-18 gene. During sampling, we restrict variation to only the complementarity-determining region 3 (CDR3) of the input. We obtain log probability scores from a GPT-2 model for each sampled CDR3 and demonstrate that multi-segment preserving sampling generates reasonable designs while maintaining the desired, preserved regions.

Keywords

Cite

@article{arxiv.2205.04259,
  title  = {Multi-segment preserving sampling for deep manifold sampler},
  author = {Daniel Berenberg and Jae Hyeon Lee and Simon Kelow and Ji Won Park and Andrew Watkins and Vladimir Gligorijević and Richard Bonneau and Stephen Ra and Kyunghyun Cho},
  journal= {arXiv preprint arXiv:2205.04259},
  year   = {2022}
}
R2 v1 2026-06-24T11:11:28.383Z