Structural Hierarchy and Geometry in Molecular Representation Learning

• URL: http://arxiv.org/abs/2608.29886v1
• Date: Sun, 30 Aug 2026 16:34:17 GMT
• Title: Structural Hierarchy and Geometry in Molecular Representation Learning
• Abstract summary: We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular embedding changes what the model learns.<n>Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Molecular self-supervised learning uses chemical structures to guide which molecular embeddings should be similar. We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular embedding changes what the model learns. We further test whether this effect depends on the embedding geometry by comparing Euclidean and Lorentz contrastive objectives. Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds. The resulting embeddings also improve molecular property prediction on several tasks, while the exact gains depend on the predicted property. The effect of scaffold supervision on molecular organization is stronger under Lorentz objectives, but neither geometry provides a consistent overall advantage. These results show that explicitly teaching the relation between a molecule and its structural core can reliably shape the organization of molecular embedding space, while the extent of usefulness of this organization remains task dependent.

Related papers

• Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis [35.63799709687231]
  We introduce a Molecular Perturbation framework that generates structural variants of training molecules under controlled Graph Edit Distance (GED)<n>Our analysis shows that even a single edit can cause substantial performance drops on common molecular tasks, revealing a narrow local trust region and fragile sensitivity to structural changes.<n>Our experiments also examine whether ICT confers robustness under controlled structural perturbations.
  arXiv  Detail & Related papers  (2026-07-02T07:16:28Z)
• Molecular Representations in Implicit Functional Space via Hyper-Networks [53.70982267248536]
  We argue that molecular learning can instead be formulated as learning in function space.<n>We instantiate this formulation with MolField, a hyper-network-based framework that learns distributions over molecular fields.<n>Our results show that treating molecules as continuous functions fundamentally changes how molecular representations generalize across tasks.
  arXiv  Detail & Related papers  (2026-01-29T21:13:37Z)
• Mamba-driven multi-perspective structural understanding for molecular ground-state conformation prediction [69.32436472760712]
  We propose an approach of Mamba-driven multi-perspective structural understanding (MPSU-Mamba) to localize molecular ground-state conformation.<n>For complex and diverse molecules, three different kinds of dedicated scanning strategies are explored to construct a comprehensive perception of corresponding molecular structures.<n> Experimental results on QM9 and Molecule3D datasets indicate that MPSU-Mamba significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-10T11:18:32Z)
• $\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models [59.125833618091846]
  We propose a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view.<n>Experiments demonstrate that $textM2$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-12T05:46:47Z)
• Knowledge-aware contrastive heterogeneous molecular graph learning [77.94721384862699]
  We propose a paradigm shift by encoding molecular graphs into Heterogeneous Molecular Graph Learning (KCHML)<n>KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism.<n>This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction (DDI) prediction.
  arXiv  Detail & Related papers  (2025-02-17T11:53:58Z)
• Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation [10.025809630976065]
  This paper introduces a novel pre-training framework that learns robust and generalizable chemical knowledge.<n>Our approach demonstrates competitive performance across various molecular property benchmarks.
  arXiv  Detail & Related papers  (2023-11-05T23:47:52Z)
• Shift-Robust Molecular Relational Learning with Causal Substructure [5.319553007291377]
  We propose CMRL that is robust to the distributional shift in molecular relational learning. We first assume a causal relationship based on the domain knowledge of molecular sciences and construct a structural causal model (SCM) that reveals the relationship between variables. Our model successfully learns from the causal substructure and alleviates the confounding effect of shortcut substructures that are spuriously correlated to chemical reactions.
  arXiv  Detail & Related papers  (2023-05-29T04:02:10Z)
• An Equivariant Generative Framework for Molecular Graph-Structure Co-Design [54.92529253182004]
  We present MolCode, a machine learning-based generative framework for underlineMolecular graph-structure underlineCo-design. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Our investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design.
  arXiv  Detail & Related papers  (2023-04-12T13:34:22Z)
• 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)
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation [16.08677447593939]
  We propose a dual-branched neural network for molecular property prediction based on message-passing framework. Our model learns heterogeneous molecular features with different scales, which are trained flexibly according to each prediction target.
  arXiv  Detail & Related papers  (2021-06-14T10:00:39Z)
• Scaffold Embeddings: Learning the Structure Spanned by Chemical Fragments, Scaffolds and Compounds [0.41988513388760185]
  We show how molecules form classes of scaffolds, how scaffolds relate to each in a hypergraph, and how this structure of scaffolds is natural for drug discovery. We compare the assumptions and utility of various embeddings of molecules, such as their respective distance induced metrics.
  arXiv  Detail & Related papers  (2021-03-11T18:54:12Z)

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.