MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jin, Jirui, Zeng, Cheng, Prakash, Pawan, Tadmor, Ellad B., Roitberg, Adrian, Hennig, Richard G., Martiniani, Stefano, Liu, Mingjie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911316669628416
author Jin, Jirui
Zeng, Cheng
Prakash, Pawan
Tadmor, Ellad B.
Roitberg, Adrian
Hennig, Richard G.
Martiniani, Stefano
Liu, Mingjie
author_facet Jin, Jirui
Zeng, Cheng
Prakash, Pawan
Tadmor, Ellad B.
Roitberg, Adrian
Hennig, Richard G.
Martiniani, Stefano
Liu, Mingjie
contents Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods -- including classifier-free guidance, autoguidance, and model guidance -- in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities -- operating on velocity fields and predicted logits, respectively -- while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S datasets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching
Jin, Jirui
Zeng, Cheng
Prakash, Pawan
Tadmor, Ellad B.
Roitberg, Adrian
Hennig, Richard G.
Martiniani, Stefano
Liu, Mingjie
Machine Learning
Quantitative Methods
Key objectives in conditional molecular generation include ensuring chemical validity, aligning generated molecules with target properties, promoting structural diversity, and enabling efficient sampling for discovery. Recent advances in computer vision introduced a range of new guidance strategies for generative models, many of which can be adapted to support these goals. In this work, we integrate state-of-the-art guidance methods -- including classifier-free guidance, autoguidance, and model guidance -- in a leading molecule generation framework built on an SE(3)-equivariant flow matching process. We propose a hybrid guidance strategy that separately guides continuous and discrete molecular modalities -- operating on velocity fields and predicted logits, respectively -- while jointly optimizing their guidance scales via Bayesian optimization. Our implementation, benchmarked on the QM9 and QMe14S datasets, achieves new state-of-the-art performance in property alignment for de novo molecular generation. The generated molecules also exhibit high structural validity. Furthermore, we systematically compare the strengths and limitations of various guidance methods, offering insights into their broader applicability.
title MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2512.12198