Navigating heterogeneous protein landscapes through geometry-aware smoothing

2026-02-11

AI Summary

This work addresses the challenge that conventional generative models, relying on fixed global noise, struggle to balance fidelity to functional clusters and effective exploration of sparse regions in the highly sparse and heterogeneous protein sequence space, often yielding non-functional sequences. To overcome this limitation, the authors propose a geometry-aware diffusion generative framework featuring a novel density-dependent smoothing (DDS) mechanism, which inversely couples diffusion noise intensity with local sequence density. This design enables fine-grained optimization in high-density regions while facilitating controlled exploration in sparse areas. The method significantly outperforms existing diffusion and autoregressive models across multiple tasks—including antibody repertoire modeling, therapeutic antibody design, antimicrobial peptide generation, and coronavirus antibody design—simultaneously enhancing both functionality and diversity of the generated sequences.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The evolutionary fitness landscape of biological molecules is extremely sparse and heterogeneous, with functional sequences forming isolated dense ``islands''within a vast combinatorial space of largely non-functional variants. Protein sequences, in particular, exemplify this structure, yet most generative artificial intelligence models implicitly assume a homogeneous data distribution. We show that this assumption fundamentally breaks down in heterogeneous biological sequence spaces: fixed global noise levels impose a destructive trade-off, either oversmoothing dense functional clusters or fragmenting sparse regions and producing non-functional hallucinations. To address this limitation, we introduce \emph{Density-Dependent Smoothing} (DDS), a geometry-aware generative framework that adapts stochastic smoothing to the local density of the underlying sequence landscape. By inversely coupling diffusion noise to estimated sequence density, DDS enables gentle refinement in high-density functional regions while promoting controlled exploration across sparse regions. Implemented as a plug-in mechanism for discrete molecular sampling, DDS consistently outperforms state-of-the-art diffusion and autoregressive models across antibody repertoires, therapeutic antibody design, antimicrobial peptide generation and coronavirus antibody design. Together, these results show that fixed global smoothing assumptions fundamentally limit generative modeling in sparse biological sequence spaces, and that geometry-aware smoothing removes this constraint, enabling reliable exploration and design previously unattainable with fixed-noise generative models.

Problem

• heterogeneous protein landscapes
• evolutionary fitness landscape
• generative modeling
• sequence space sparsity
• functional sequence islands

Innovation

• Density-Dependent Smoothing
• geometry-aware generative modeling
• protein sequence design
• heterogeneous fitness landscape
• adaptive diffusion noise