Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.14977 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917276796583936 |
|---|---|
| author | Maksymiuk, Alicja Duplessis, Alexandre Bronstein, Michael Tong, Alexander Duarte, Fernanda Ceylan, İsmail İlkan |
| author_facet | Maksymiuk, Alicja Duplessis, Alexandre Bronstein, Michael Tong, Alexander Duarte, Fernanda Ceylan, İsmail İlkan |
| contents | Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public datasets and the challenges of enforcing topological constraints in standard deep generative models. We introduce MacroGuide: Topological Guidance for Macrocycle Generation, a diffusion guidance mechanism that uses Persistent Homology to steer the sampling of pretrained molecular generative models toward the generation of macrocycles, in both unconditional and conditional (protein pocket) settings. At each denoising step, MacroGuide constructs a Vietoris-Rips complex from atomic positions and promotes ring formation by optimizing persistent homology features. Empirically, applying MacroGuide to pretrained diffusion models increases macrocycle generation rates from 1% to 99%, while matching or exceeding state-of-the-art performance on key quality metrics such as chemical validity, diversity, and PoseBusters checks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14977 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MacroGuide: Topological Guidance for Macrocycle Generation Maksymiuk, Alicja Duplessis, Alexandre Bronstein, Michael Tong, Alexander Duarte, Fernanda Ceylan, İsmail İlkan Machine Learning Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public datasets and the challenges of enforcing topological constraints in standard deep generative models. We introduce MacroGuide: Topological Guidance for Macrocycle Generation, a diffusion guidance mechanism that uses Persistent Homology to steer the sampling of pretrained molecular generative models toward the generation of macrocycles, in both unconditional and conditional (protein pocket) settings. At each denoising step, MacroGuide constructs a Vietoris-Rips complex from atomic positions and promotes ring formation by optimizing persistent homology features. Empirically, applying MacroGuide to pretrained diffusion models increases macrocycle generation rates from 1% to 99%, while matching or exceeding state-of-the-art performance on key quality metrics such as chemical validity, diversity, and PoseBusters checks. |
| title | MacroGuide: Topological Guidance for Macrocycle Generation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.14977 |