Spotlight
in
Workshop: Machine Learning for Drug Discovery (MLDD)

Multi-Segment Preserving Sampling for Deep Manifold Sampler

Dan Berenberg · Jae Hyeon Lee · Simon Kelow · Ji Park · Andrew Watkins · Richard Bonneau · Vladimir Gligorijevic · Stephen Ra · Kyunghyun Cho

[ Abstract ] [ Project Page ]
[ OpenReview
Fri 29 Apr 12:50 p.m. PDT — 12:55 p.m. PDT
 
presentation: Machine Learning for Drug Discovery (MLDD)
Fri 29 Apr 6 a.m. PDT — 2:30 p.m. PDT

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. Sampling was done by exploiting the gradients from a function predictor trained on top of the manifold sampler.In this work, we introduce an alternative approach to guided 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 call this method ``multi-segment preserving sampling" and present its effectiveness in the context of antibody design.We train two models: a deep manifold sampler and a GPT-2 language model on nearly six million heavy chain sequences annotated with the \textit{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.

Chat is not available.