A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks

• URL: http://arxiv.org/abs/2608.25893v1
• Date: Wed, 26 Aug 2026 15:11:15 GMT
• Title: A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks
• Abstract summary: We investigate whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems.<n>We fine-tune Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluate the resulting model without additional deep-learning training.<n>The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations.
• Score: 21.327527107800016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems. We investigate this question by fine-tuning Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluating the resulting model, without additional deep-learning training, on four complementary downstream settings: cross-dataset odor descriptor prediction, odorous-versus-odorless classification, enantiomer evaluation, and odor mixture discriminability. The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations. The enantiomer analysis further shows that three-dimensional molecular representations distinguish mirror-image molecules in a way that two-dimensional graph models fundamentally cannot, although accurately predicting the perceptual consequences of stereochemistry remains an open challenge. Together, these results support a train-once, transfer-across-tasks paradigm for machine olfaction and suggest that chemically pretrained molecular representations provide a strong foundation for transferable olfactory prediction.

Related papers

• Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference [1.3774496879239961]
  Bioassay activity prediction is often data-limited because drug-discovery datasets on time-consuming and expensive wetlab experiments for data generation and evaluation.<n>This paper presents Monroe, a new molecular foundation model with several innovations over the existing state of the art.
  arXiv  Detail & Related papers  (2026-08-19T14:48:19Z)
• SCENT: Aligning Mass Spectra with Molecular Structure for Olfactory Perception [48.96518000981492]
  We explore direct electron ionization mass spectrometry (EI-MS) as an alternative input modality for olfactory prediction.<n>We contribute Spectrum-to-Chemical Embedding alignmeNT (SCENT), a multi-modal contrastive learning framework that aligns EI-MS representations with pretrained chemical structure embeddings.<n>On the multi-label odor descriptor prediction task, SCENT significantly outperforms MS-only baselines and achieves olfactory performance comparable to structure-based models.
  arXiv  Detail & Related papers  (2026-05-26T13:28:57Z)
• Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra [31.563216077422084]
  Tandem Mass Spectrometry enables the identification of unknown compounds in crucial fields such as metabolomics, natural product discovery and environmental analysis.<n>We introduce a framework that, by leveraging test-time tuning, enhances the learning of a pre-trained transformer model to address this gap.<n>We surpass the de-facto state-of-the-art approach DiffMS on two popular benchmarks NPLIB1 and MassSpecGym by 100% and 20%, respectively.
  arXiv  Detail & Related papers  (2025-10-27T18:25:36Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Enhancing Chemical Explainability Through Counterfactual Masking [1.1024591739346294]
  We propose counterfactual masking, a framework that replaces masked substructures with chemically reasonable fragments.<n>Our approach bridges the gap between explainability and molecular design, offering a principled and generative path toward explainable machine learning in chemistry.
  arXiv  Detail & Related papers  (2025-08-25T23:41:36Z)
• Pre-trained Molecular Language Models with Random Functional Group Masking [54.900360309677794]
  We propose a SMILES-based underlineem Molecular underlineem Language underlineem Model, which randomly masking SMILES subsequences corresponding to specific molecular atoms. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities.
  arXiv  Detail & Related papers  (2024-11-03T01:56:15Z)
• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• Olfactory Label Prediction on Aroma-Chemical Pairs [0.2749898166276853]
  We present graph neural network models capable of accurately predicting the odor qualities arising from blends of aroma-chemicals. In this paper, we apply both existing and novel approaches to a dataset we gathered consisting of labeled pairs of molecules.
  arXiv  Detail & Related papers  (2023-12-26T17:18:09Z)
• Generative structured normalizing flow Gaussian processes applied to spectroscopic data [4.0773490083614075]
  In the physical sciences, limited training data may not adequately characterize future observed data. It is critical that models adequately indicate uncertainty, particularly when they may be asked to extrapolate. We demonstrate the methodology on laser-induced breakdown spectroscopy data from the ChemCam instrument onboard the Mars rover Curiosity.
  arXiv  Detail & Related papers  (2022-12-14T23:57:46Z)
• Unraveling Key Elements Underlying Molecular Property Prediction: A Systematic Study [27.56700461408765]
  Key elements underlying molecular property prediction remain largely unexplored. We conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4,200 models on SMILES sequences and 8,400 models on molecular graphs.
  arXiv  Detail & Related papers  (2022-09-26T14:07:59Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• Learning Graph Models for Retrosynthesis Prediction [90.15523831087269]
  Retrosynthesis prediction is a fundamental problem in organic synthesis. This paper introduces a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during a chemical reaction. Our model achieves a top-1 accuracy of $53.7%$, outperforming previous template-free and semi-template-based methods.
  arXiv  Detail & Related papers  (2020-06-12T09:40:42Z)

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.