Ensemble-Conditioned Molecular Design

• URL: http://arxiv.org/abs/2609.15077v1
• Date: Mon, 14 Sep 2026 05:49:37 GMT
• Title: Ensemble-Conditioned Molecular Design
• Abstract summary: We reframe molecular design as an optimisation of both the modes and properties of molecules' conformational ensembles.<n>We introduce ensemble-conditioned guidance, a framework which conditions 3D molecular generative models on both axes simultaneously.<n>We evaluate on new benchmarks for multi-mode conditioning and ensemble property optimisation.
• Score: 41.968590587501616
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Molecular design is typically approached as a problem of finding molecules which can adopt a single bioactive conformation. In reality, molecules occupy a distribution over conformations, and many of the properties which determine whether a candidate is viable depend on that distribution rather than on any single conformer. We reframe molecular design as an optimisation of both the modes and properties of molecules' conformational ensembles, where modes can be represented as shapes, pharmacophore profiles or protein pockets, and properties are aggregate scalars computed over the whole distribution. To realise this we introduce ensemble-conditioned guidance, a framework which conditions 3D molecular generative models on both axes simultaneously. Mode conditions are composed adaptively at inference by combining the vector fields produced under each condition. Conditions may be targeted or avoided, mixed across modalities and combined in arbitrary numbers, allowing a wide range of design tasks to be expressed with a single trained model. We introduce adaptive symmetry learning to allow conditions from different reference frames to be composed, and extend our generative framework to enable flexible-size generation. We evaluate on new benchmarks for multi-mode conditioning and ensemble property optimisation, and apply the framework to two practical drug discovery tasks, dual-target binder design and active-state-selective agonist design, where in both cases conditioning on the additional state improves the desired outcome over single-state conditioning.

Related papers

• Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport [27.245262040077716]
  We introduce Morph, a flexible-size generative model for conditional and unconditional 3D molecular design based on geometric graphs.<n>By dynamically adapting size, Morph can seamlessly integrate existing structural priors, like scaffolds, and significantly enhances property steering.<n>We show that Morph matches current fixed-size state-of-the-art models while offering the benefit of unparalleled sampling flexibility.
  arXiv  Detail & Related papers  (2026-06-05T13:07:56Z)
• FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble [43.16267651837197]
  FlexiFlow is a novel architecture that extends flow-matching models.<n>We demonstrate the effectiveness of our approach on the QM9 and GEOM Drugs datasets.
  arXiv  Detail & Related papers  (2025-11-21T13:50:54Z)
• Composition and Alignment of Diffusion Models using Constrained Learning [79.36736636241564]
  Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions.<n>Two commonly used methods are: (i) alignment, which involves fine-tuning a diffusion model to align it with a reward; and (ii) composition, which combines several pre-trained diffusion models, each emphasizing a desirable attribute in the generated outputs.<n>We propose a constrained optimization framework that unifies alignment and composition of diffusion models by enforcing that the aligned model satisfies reward constraints and/or remains close to (potentially multiple) pre-trained models.
  arXiv  Detail & Related papers  (2025-08-26T15:06:30Z)
• MolMiner: Towards Controllable, 3D-Aware, Fragment-Based Molecular Design [7.366789601705544]
  MolMiner is a fragment-based, geometry-aware, and order-agnostic autoregressive model for molecular design.<n>MolMiner supports conditional generation of molecules over twelve properties, enabling flexible control across physicochemical and structural targets.
  arXiv  Detail & Related papers  (2024-11-10T22:00:55Z)
• DPLM-2: A Multimodal Diffusion Protein Language Model [75.98083311705182]
  We introduce DPLM-2, a multimodal protein foundation model that extends discrete diffusion protein language model (DPLM) to accommodate both sequences and structures. DPLM-2 learns the joint distribution of sequence and structure, as well as their marginals and conditionals. Empirical evaluation shows that DPLM-2 can simultaneously generate highly compatible amino acid sequences and their corresponding 3D structures.
  arXiv  Detail & Related papers  (2024-10-17T17:20:24Z)
• UniIF: Unified Molecule Inverse Folding [67.60267592514381]
  We propose a unified model UniIF for inverse folding of all molecules. Our proposed method surpasses state-of-the-art methods on all tasks.
  arXiv  Detail & Related papers  (2024-05-29T10:26:16Z)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding [34.27649279751879]
  We develop a novel generative model that considers both the targeted pocket's circumstances and a variety of chemical properties. Experiments show that our model exhibits good controllability in both single and multi-conditional molecular generation.
  arXiv  Detail & Related papers  (2023-02-14T15:27:47Z)
• Learning Neural Generative Dynamics for Molecular Conformation Generation [89.03173504444415]
  We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph. We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
  arXiv  Detail & Related papers  (2021-02-20T03:17:58Z)
• Auto-Encoding Molecular Conformations [0.0]
  We show that our proposed model converts the discrete spatial arrangements of atoms in a given molecular graph into a continuous fixed-sized latent representation. We also demonstrate how our model can be used to generate diverse sets of energetically favorable conformations for a given molecule.
  arXiv  Detail & Related papers  (2021-01-05T16:09:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.