QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible molecules

• URL: http://arxiv.org/abs/2609.16527v1
• Date: Tue, 15 Sep 2026 02:19:20 GMT
• Title: QALPA: Property-guided diffusion modeling for efficient exploration of chemical spaces of flexible molecules
• Abstract summary: We introduce QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework.<n>By coupling generation with physics-based evaluation, QALPA improves molecular sampling and model reliability in sparsely populated regions of chemical space.<n>As a proof of concept, QALPA coupled with the machine learning-augmented tight-binding method EquiDTB efficiently augments alloQM dataset.
• Score: 2.783769708615212
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Exploring the chemical space of flexible molecules remains challenging because the vast number of possible compounds and conformations, together with the increasing cost and limited generalization of 3D generative models for larger and more complex molecules, restrict access to unexplored chemistry. Here, we introduce QALPA ("Quantum-Aware Learning for Property-space Augmentation"), a property-guided generative framework that combines an E(3)-equivariant diffusion model with active learning and efficient quantum-mechanical (QM) methods to iteratively explore targeted QM property manifolds. By coupling generation with physics-based evaluation, QALPA improves molecular sampling and model reliability in sparsely populated regions of chemical space. Our results show that training on complementary QM datasets spanning both small (QM7-X) and large (Aquamarine) drug-like compounds enables accurate molecular generation across a broad size range, improving transferability beyond the training distribution for complex property manifolds involving both extensive and intensive properties. As a proof of concept, QALPA coupled with the machine learning-augmented tight-binding method EquiDTB efficiently augments alloQM, a QM dataset introduced in this work, comprising 6,253 conformers of allosteric drug molecules, by populating sparse regions of the property landscape defined by the many-body dispersion energy and HOMO-LUMO energy gap. These results demonstrate that the integration of generative AI with efficient ML/QM methods offers a practical pathway toward augmenting sparse QM datasets and sustainably expanding the exploration of chemical space for molecular discovery.

Related papers

• Interpretable Machine Learning for Quantum-Informed Property Predictions in Artificial Sensing Materials [40.34973869620865]
  Digital sensing faces challenges in developing sustainable methods to extend the applicability of customized e-noses to body odor volatilome (BOV)<n>We developed MORE-ML, a computational framework that integrates quantum-mechanical (QM) property data of e-nose molecular building blocks with machine learning (ML) methods to predict sensing-relevant properties.
  arXiv  Detail & Related papers  (2026-01-01T22:56:07Z)
• QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning [2.2463678997251604]
  This work presents a novel quantum circuit Born machine (QCBM)-enabled Generative Adrialversa Network (GAN), called QCA-MolGAN, for generating drug-like molecules.<n>QCBM serves as a learnable prior distribution, which is associatively trained to define a latent space aligning with high-level features captured by the GANs discriminator.<n>We integrate a novel multi-agent reinforcement learning network to guide molecular generation with desired targeted properties.
  arXiv  Detail & Related papers  (2025-09-05T12:31:58Z)
• A Scalable and Quantum-Accurate Foundation Model for Biomolecular Force Field via Linearly Tensorized Quadrangle Attention [6.749581549330875]
  We present LiTEN, a novel AI-based force field framework for atomistic biomolecular simulations.<n>Building on LiTEN, LiTEN-FF is a robust AIFF foundation model, pre-trained on the nablaDFT dataset for broad chemical generalization.<n>LiTEN achieves state-of-the-art (SOTA) performance across most evaluation subsets of rMD17, MD22, and Chignolin, outperforming leading models such as MACE, NequIP, and EquiFormer.
  arXiv  Detail & Related papers  (2025-07-01T15:52:39Z)
• Data-Driven Parametrization of Molecular Mechanics Force Fields for Expansive Chemical Space Coverage [16.745564099126575]
  We develop ByteFF, an Amber-compatible force field for drug-like molecules. Our model predicts all bonded and non-bonded MM force field parameters for drug-like molecules simultaneously across a broad chemical space.
  arXiv  Detail & Related papers  (2024-08-23T03:37:06Z)
• Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting [53.44684898432997]
  Generation of molecules with desired chemical and biological properties is critical for drug discovery. We propose a probabilistic generative model to capture the joint distribution of molecules and their properties. Our method achieves very strong performances on various molecule design tasks.
  arXiv  Detail & Related papers  (2023-06-09T03:04:21Z)
• Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction [53.06671763877109]
  We develop molecular embeddings that encode complex molecular characteristics to improve the performance of few-shot molecular property prediction. Our approach leverages large amounts of synthetic data, namely the results of molecular docking calculations. On multiple molecular property prediction benchmarks, training from the embedding space substantially improves Multi-Task, MAML, and Prototypical Network few-shot learning performance.
  arXiv  Detail & Related papers  (2023-02-04T01:32:40Z)
• Exploring Chemical Space with Score-based Out-of-distribution Generation [57.15855198512551]
  We propose a score-based diffusion scheme that incorporates out-of-distribution control in the generative differential equation (SDE) Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool.
  arXiv  Detail & Related papers  (2022-06-06T06:17:11Z)
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations [51.68332623405432]
  Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations. This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
  arXiv  Detail & Related papers  (2022-05-17T13:08:28Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Optimizing Molecules using Efficient Queries from Property Evaluations [66.66290256377376]
  We propose QMO, a generic query-based molecule optimization framework. QMO improves the desired properties of an input molecule based on efficient queries. We show that QMO outperforms existing methods in the benchmark tasks of optimizing small organic molecules.
  arXiv  Detail & Related papers  (2020-11-03T18:51:18Z)

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.