Score-Based Generative Models for Designing Binding Peptide Backbones

TL;DR

This paper introduces LoopGen, a score-based generative model framework for designing peptide backbones that bind specific targets, emphasizing the importance of modeling residue orientations and variance schedules for improved structure quality and diversity.

Contribution

The paper presents LoopGen, a novel flexible SGM framework for peptide design, and systematically explores design choices impacting model performance and structure conditioning.

Findings

Modeling residue orientations enhances structure quality and diversity.

Optimized variance schedules significantly improve model performance.

Generated structures are effectively conditioned on epitopes, reflecting target dependence.

Abstract

Score-based generative models (SGMs) have proven to be powerful tools for designing new proteins. Designing proteins that bind a pre-specified target is highly relevant to a range of medical and industrial applications. Despite the flurry of new SGMs in the last year, there has been little systematic exploration of the impact of design choices in SGMs for protein design. Here we present LoopGen, a flexible SGM framework for the design of short binding peptide structures. We apply our framework to design antibody binding loop structures conditional on a target epitope and evaluate a variety of modelling choices in SGM-based protein design. We demonstrate that modelling residue orientations in addition to positions improves not only the quality of the output structures but also their diversity. Additionally, we identify variance schedules that result in significant performance improvements and observe patterns that may motivate the development of better schedules for protein design. Finally, we develop three novel tests to evaluate whether the model generates structures that are appropriately conditioned on an epitope, demonstrating that LoopGen's generated structures are dependent on the structure, sequence, and position of the epitope. Our findings will help guide future development and evaluation of generative models for binding proteins.