Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bergues, Noémie, Carré, Arthur, Join-Lambert, Paul, Hoffmann, Brice, Blondel, Arnaud, Tajmouati, Hamza
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915529998991360
author Bergues, Noémie
Carré, Arthur
Join-Lambert, Paul
Hoffmann, Brice
Blondel, Arnaud
Tajmouati, Hamza
author_facet Bergues, Noémie
Carré, Arthur
Join-Lambert, Paul
Hoffmann, Brice
Blondel, Arnaud
Tajmouati, Hamza
contents Predicting the 3D conformation of small molecules within protein binding sites is a key challenge in drug design. When a crystallized reference ligand (template) is available, it provides geometric priors that can guide 3D pose prediction. We present a two-stage method for ligand conformation generation guided by such templates. In the first stage, we introduce a molecular alignment approach based on flow-matching to generate 3D coordinates for the ligand, using the template structure as a reference. In the second stage, a differentiable pose optimization procedure refines this conformation based on shape and pharmacophore similarities, internal energy, and, optionally, the protein binding pocket. We introduce a new benchmark of ligand pairs co-crystallized with the same target to evaluate our approach and show that it outperforms standard docking tools and open-access alignment methods, especially in cases involving low similarity to the template or high ligand flexibility.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06305
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
Bergues, Noémie
Carré, Arthur
Join-Lambert, Paul
Hoffmann, Brice
Blondel, Arnaud
Tajmouati, Hamza
Biomolecules
Machine Learning
Predicting the 3D conformation of small molecules within protein binding sites is a key challenge in drug design. When a crystallized reference ligand (template) is available, it provides geometric priors that can guide 3D pose prediction. We present a two-stage method for ligand conformation generation guided by such templates. In the first stage, we introduce a molecular alignment approach based on flow-matching to generate 3D coordinates for the ligand, using the template structure as a reference. In the second stage, a differentiable pose optimization procedure refines this conformation based on shape and pharmacophore similarities, internal energy, and, optionally, the protein binding pocket. We introduce a new benchmark of ligand pairs co-crystallized with the same target to evaluate our approach and show that it outperforms standard docking tools and open-access alignment methods, especially in cases involving low similarity to the template or high ligand flexibility.
title Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2506.06305