Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Awasthi, Urvi, Lobo, Alexander Arjun, Zhukov, Leonid
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911549955768320
author Awasthi, Urvi
Lobo, Alexander Arjun
Zhukov, Leonid
author_facet Awasthi, Urvi
Lobo, Alexander Arjun
Zhukov, Leonid
contents Generating chemically valid 3D molecules is hindered by discrete bond topology: small local bond errors can cause global failures (valence violations, disconnections, implausible rings), especially for drug-like molecules with long-range constraints. Many unconditional 3D generators emphasize coordinates and then infer bonds or rely on post-processing, leaving topology feasibility weakly controlled. We propose Hierarchy-Guided Latent Topology Flow (HLTF), a planner-executor model that generates bond graphs with 3D coordinates, using a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures. On QM9, HLTF achieves 98.8% atom stability and 92.9% valid-and-unique, improving PoseBusters validity to 94.0% (+0.9 over the strongest reported baseline). On GEOM-DRUGS, HLTF attains 85.5%/85.0% validity/valid-unique-novel without post-processing and 92.2%/91.2% after standardized relaxation, within 0.9 points of the best post-processed baseline. Explicit topology generation also reduces "false-valid" samples that pass RDKit sanitization but fail stricter checks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27113
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation
Awasthi, Urvi
Lobo, Alexander Arjun
Zhukov, Leonid
Machine Learning
Materials Science
Generating chemically valid 3D molecules is hindered by discrete bond topology: small local bond errors can cause global failures (valence violations, disconnections, implausible rings), especially for drug-like molecules with long-range constraints. Many unconditional 3D generators emphasize coordinates and then infer bonds or rely on post-processing, leaving topology feasibility weakly controlled. We propose Hierarchy-Guided Latent Topology Flow (HLTF), a planner-executor model that generates bond graphs with 3D coordinates, using a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures. On QM9, HLTF achieves 98.8% atom stability and 92.9% valid-and-unique, improving PoseBusters validity to 94.0% (+0.9 over the strongest reported baseline). On GEOM-DRUGS, HLTF attains 85.5%/85.0% validity/valid-unique-novel without post-processing and 92.2%/91.2% after standardized relaxation, within 0.9 points of the best post-processed baseline. Explicit topology generation also reduces "false-valid" samples that pass RDKit sanitization but fail stricter checks.
title Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation
topic Machine Learning
Materials Science
url https://arxiv.org/abs/2603.27113