Navigating heterogeneous protein landscapes through geometry-aware smoothing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908827502247936 |
|---|---|
| author | Anumasa, Srinivas Chandran, Barath Chen, Tingting Rahman, Nuwaisir Mohammad Zhu, Yingtao Shah, Rushi He, Hongyu Zhang, Peisong Liao, Yizhen Tang, Yiming Shen, Yong Fu, Tianfan Qing, Rui Li, Xiao Maurer-Stroh, Sebastian Su, Xinyi Zhang, Zhizhuo Liu, Dianbo |
| author_facet | Anumasa, Srinivas Chandran, Barath Chen, Tingting Rahman, Nuwaisir Mohammad Zhu, Yingtao Shah, Rushi He, Hongyu Zhang, Peisong Liao, Yizhen Tang, Yiming Shen, Yong Fu, Tianfan Qing, Rui Li, Xiao Maurer-Stroh, Sebastian Su, Xinyi Zhang, Zhizhuo Liu, Dianbo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10422 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Navigating heterogeneous protein landscapes through geometry-aware smoothing Anumasa, Srinivas Chandran, Barath Chen, Tingting Rahman, Nuwaisir Mohammad Zhu, Yingtao Shah, Rushi He, Hongyu Zhang, Peisong Liao, Yizhen Tang, Yiming Shen, Yong Fu, Tianfan Qing, Rui Li, Xiao Maurer-Stroh, Sebastian Su, Xinyi Zhang, Zhizhuo Liu, Dianbo Computational Engineering, Finance, and Science 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. |
| title | Navigating heterogeneous protein landscapes through geometry-aware smoothing |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2602.10422 |