GraphCliff: Short-Long Range Gating for Modeling Critical Activity Changes Caused by Subtle Molecular Differences

arXiv:2511.03170v3 Announce Type: replace-cross Abstract: The quantitative structure-activity relationship assumes a smooth mapping between molecular structure and biological activity. However, activity cliffs, defined as pairs of structurally similar compounds with large potency differences, break this continuity. Recent activity cliff benchmarks show that machine learning models with extended connectivity fingerprints outperform graph neural networks. Our analysis shows that the embedding distances of conventional graph neural networks fail to reflect the activity differences, collapsing structurally similar yet functionally divergent molecules into nearly indistinguishable representations. To recover sensitivity to such local changes while preserving global molecular context, we propose GraphCliff, which integrates short and long range information at the node level through a locally conditioned gating mechanism. Experimental results demonstrate that GraphCliff consistently improves performance on both non-cliff and cliff compounds, with layer-wise embedding analyses attributing these gains to sharper discrimination of structurally similar molecules relative to strong baseline graph models.

Abstract:The quantitative structure-activity relationship assumes a smooth mapping between molecular structure and biological activity. However, activity cliffs, defined as pairs of structurally similar compounds with large potency differences, break this continuity. Recent activity cliff benchmarks show that machine learning models with extended connectivity fingerprints outperform graph neural networks. Our analysis shows that the embedding distances of conventional graph neural networks fail to reflect the activity differences, collapsing structurally similar yet functionally divergent molecules into nearly indistinguishable representations. To recover sensitivity to such local changes while preserving global molecular context, we propose GraphCliff, which integrates short and long range information at the node level through a locally conditioned gating mechanism. Experimental results demonstrate that GraphCliff consistently improves performance on both non-cliff and cliff compounds, with layer-wise embedding analyses attributing these gains to sharper discrimination of structurally similar molecules relative to strong baseline graph models.

Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI)

arXiv:2511.03170 [cs.CE]

(or arXiv:2511.03170v3 [cs.CE] for this version)

https://doi.org/10.48550/arXiv.2511.03170 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1145/3770855.3818898 Focus to learn more DOI(s) linking to related resources

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.

aiqbench analysis

GraphCliff: Short-Long Range Gating for Modeling Critical Activity Changes Caused by Subtle Molecular Differences

Related coverage