Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion

• URL: http://arxiv.org/abs/2605.07048v1
• Date: Thu, 07 May 2026 23:56:02 GMT
• Title: Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion
• Abstract summary: We propose DualLGD, which reformulates molecular graph denoising as the alternating solution of two coupled subproblems.<n>On the NPLIB1 and MassSpecGym benchmarks, DualLGD achieves top-1 accuracy of 34.37% and 23.89%, approximately $3times$ the previous state of the art.
• Score: 3.2243643829769586
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: De novo molecular generation from tandem mass spectra is a challenging inverse problem whose core difficulty lies in the circular dependency between atom-level and bond-level reasoning: determining a bond's type requires knowing its endpoint atoms' chemical environment, yet an atom's environment is in turn defined by its incident bonds. Existing graph diffusion methods process atoms and bonds within a single computation stream, where atom-bond information synchronization can only occur implicitly across layers. We argue that this single-stream paradigm, rather than the choice of any particular aggregation kernel, is a key architectural bottleneck. We propose DualLGD (Dual-stream Line Graph Diffusion), which reformulates molecular graph denoising as the alternating solution of two coupled subproblems: atom-level reasoning and bond-level reasoning, each operating in its own dedicated representation space. The line graph provides a natural mathematical construction for the bond space, in which bond angles, dihedrals, conjugation chains, and rings correspond to local topological motifs between bonds. Incidence-constrained bidirectional cross-attention synchronizes the two streams at every layer, ensuring that each atom attends only to its incident bonds and vice versa, respecting the fundamental chemical principle that an atom's environment is determined by its bonding context. On the NPLIB1 and MassSpecGym benchmarks, DualLGD achieves top-1 accuracy of 34.37\% and 23.89\%, approximately $3\times$ the previous state of the art. Ablation studies confirm the architecture as the primary source of improvement: DualLGD without any pre-training already surpasses the previous best fully pretrained model.

Related papers

• Topological Edge States from Molecular Chirality: A General Framework for Dimerized Dipolar Arrays [0.9685837672183748]
  We show that molecular handedness provides a natural and tunable route to SSH-like topology in an interacting one-dimensional setting.<n>We also show that the chirality-induced Dzyaloshinskii--Moriya interaction amplifies the effective hopping amplitudes.<n>These findings establish dimerized chiral molecular arrays as a controllable and chirality-addressable platform.
  arXiv  Detail & Related papers  (2026-05-30T20:22:08Z)
• Comparison of the standard and dressed-picture master equations for the quantum Rabi model in the ultrastrong coupling regime [78.55450146498553]
  This chapter investigates the effects of relaxation and dephasing on the quantum Rabi model in the ultrastrong coupling regime.<n>It provides explicit formulas to implement and numerically solve the resulting nonunitary dynamics.
  arXiv  Detail & Related papers  (2026-04-10T01:22:07Z)
• Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions [18.371474900925865]
  We introduce textbfDeMol, a dual-graph framework for atom-centric representation learning.<n>DeMol explicitly models molecules through parallel atom-centric and bond-centric channels.<n>It establishes a new state-of-the-art, outperforming existing methods.
  arXiv  Detail & Related papers  (2026-02-28T09:36:19Z)
• Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation [32.464905769094536]
  Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. We introduce a Dual-Track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations. As for the second challenge, we design Geometric-Facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space.
  arXiv  Detail & Related papers  (2024-01-05T07:29:21Z)
• Atom-Motif Contrastive Transformer for Molecular Property Prediction [68.85399466928976]
  Graph Transformer (GT) models have been widely used in the task of Molecular Property Prediction (MPP) We propose a novel Atom-Motif Contrastive Transformer (AMCT) which explores atom-level interactions and considers motif-level interactions. Our proposed AMCT is extensively evaluated on seven popular benchmark datasets, and both quantitative and qualitative results firmly demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2023-10-11T10:03:10Z)
• Modeling Non-Covalent Interatomic Interactions on a Photonic Quantum Computer [50.24983453990065]
  We show that the cQDO model lends itself naturally to simulation on a photonic quantum computer. We calculate the binding energy curve of diatomic systems by leveraging Xanadu's Strawberry Fields photonics library. Remarkably, we find that two coupled bosonic QDOs exhibit a stable bond.
  arXiv  Detail & Related papers  (2023-06-14T14:44:12Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• Higher-order topological Peierls insulator in a two-dimensional atom-cavity system [58.720142291102135]
  We show how photon-mediated interactions give rise to a plaquette-ordered bond pattern in the atomic ground state. The pattern opens a non-trivial topological gap in 2D, resulting in a higher-order topological phase hosting corner states. Our work shows how atomic quantum simulators can be harnessed to investigate novel strongly-correlated topological phenomena.
  arXiv  Detail & Related papers  (2023-05-05T10:25:14Z)
• Collective Radiance of Giant Atoms in Non-Markovian Regime [11.798151369038557]
  We investigate the non-Markovian dynamics of two giant artificial atoms interacting with a continuum of bosonic modes in a 1D waveguide. For certain collective states, the decay rates are found to be far beyond that predicted in the the Dicke model and standard Markovian framework. The trapped photons/phonons in the BICs can also be re-released conveniently by changing the energy level splitting of giant atoms.
  arXiv  Detail & Related papers  (2022-05-23T01:14:56Z)
• MolNet: A Chemically Intuitive Graph Neural Network for Prediction of Molecular Properties [1.231476564107544]
  graph neural network (GNN) has been a powerful deep-learning tool in chemistry domain. MolNet model is chemically intuitive, accommodating the 3D non-bond information in a molecule. MolNet gives a state-of-the-art performance in the classification task of BACE dataset and regression task of ESOL dataset.
  arXiv  Detail & Related papers  (2022-02-01T20:47:28Z)
• Mechanism for particle fractionalization and universal edge physics in quantum Hall fluids [58.720142291102135]
  We advance a second-quantization framework that helps reveal an exact fusion mechanism for particle fractionalization in FQH fluids. We also uncover the fundamental structure behind the condensation of non-local operators characterizing topological order in the lowest-Landau-level (LLL)
  arXiv  Detail & Related papers  (2021-10-12T18:00:00Z)
• Multipoint correlation functions: spectral representation and numerical evaluation [0.0]
  We derivation generalized spectral representations for multipoint correlation functions that apply to many-body frameworks. Our approach separates spectral from time-ordering properties and thereby elucidates the relation between the three formalisms. Using a numerical renormalization group (NRG) method, we present numerical results for selected quantum impurity models.
  arXiv  Detail & Related papers  (2021-01-03T21:35:56Z)

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.