analiza aiqbench
This research introduces MolPAIR, a framework that enhances tabular foundation models for molecular property prediction by leveraging explicit comparisons between query and reference molecules. By refining initial predictions through error difference analysis without updating model weights, the approach significantly improves structural generalization across diverse drug discovery tasks. The findings demonstrate that simple architectural adjustments to in-context learning can yield substantial performance gains using existing pretrained backbones.
Molecular Property Prediction under Structural Shift with Tabular Foundation Models
arXiv:2609.38744v1 Announce Type: new Abstract: Predicting molecular properties for compounds that differ structurally from labeled training molecules is important for drug discovery and materials design. Tabular foundation models (TFMs) offer a promising approach through in-context learning, but their performance under structural shifts and the value of molecular comparisons in this setting remain underexplored. We study structural generalization in molecular property prediction and introduce MolPAIR (Molecular Pair-Augmented In-context Refinement), a framework that combines molecule-level and molecular-pair contexts without task-specific parameter updates. A global tabular foundation model (TFM) first predicts a query's property from labeled molecular examples. A second frozen TFM predicts differences in prediction errors between the query and labeled reference molecules, using these comparisons to refine the initial prediction. Across 58 MoleculeACE and Polaris tasks, CheMeleon representations combined with TabPFN-3 already outperform each evaluated baseline on a majority of tasks. MOLPAIR further improves this predictor on 46 of 58 tasks, with gains across four molecular representations and three TFM backbones. These results show that explicit molecular comparisons can strengthen tabular in-context learning for structural generalization while keeping the molecular encoder and pretrained model weights fixed. The code and datasets are available at https://github.com/nums-ai/MolPAIR.
Abstract:Predicting molecular properties for compounds that differ structurally from labeled training molecules is important for drug discovery and materials design. Tabular foundation models (TFMs) offer a promising approach through in-context learning, but their performance under structural shifts and the value of molecular comparisons in this setting remain underexplored. We study structural generalization in molecular property prediction and introduce MolPAIR (Molecular Pair-Augmented In-context Refinement), a framework that combines molecule-level and molecular-pair contexts without task-specific parameter updates. A global tabular foundation model (TFM) first predicts a query's property from labeled molecular examples. A second frozen TFM predicts differences in prediction errors between the query and labeled reference molecules, using these comparisons to refine the initial prediction. Across 58 MoleculeACE and Polaris tasks, CheMeleon representations combined with TabPFN-3 already outperform each evaluated baseline on a majority of tasks. MOLPAIR further improves this predictor on 46 of 58 tasks, with gains across four molecular representations and three TFM backbones. These results show that explicit molecular comparisons can strengthen tabular in-context learning for structural generalization while keeping the molecular encoder and pretrained model weights fixed. The code and datasets are available at this https URL.
Machine Learning (cs.LG)
arXiv:2609.38744 [cs.LG]
(or arXiv:2609.38744v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.38744 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 284 cuvinte
Subiecte conexe
Learning to Select Source Domains: Proxy-Rewarded Policy Optimization for Molecular OOD Generalization
arXiv · 30 sept. 2026
Molecular Dynamics Reveal Nanosecond Tubulin Conformational Shifts
Quantum Zeitgeist · 14 iul. 2026
7 Steps to Mastering Time Series Analysis with Python
KDnuggets · 4 iun. 2026
Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction
arXiv · 15 oct. 2026