GraphCliff: Short-Long Range Gating for Subtle Differences but Critical Changes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908637576822784 |
|---|---|
| author | Kim, Hajung Park, Jueon Choe, Junseok Baek, Sheunheun Hwang, Hyeon Kang, Jaewoo |
| author_facet | Kim, Hajung Park, Jueon Choe, Junseok Baek, Sheunheun Hwang, Hyeon Kang, Jaewoo |
| contents | Quantitative structure-activity relationship assumes a smooth relationship between molecular structure and biological activity. However, activity cliffs defined as pairs of structurally similar compounds with large potency differences break this continuity. Recent benchmarks targeting activity cliffs have revealed that classical machine learning models with extended connectivity fingerprints outperform graph neural networks. Our analysis shows that graph embeddings fail to adequately separate structurally similar molecules in the embedding space, making it difficult to distinguish between structurally similar but functionally different molecules. Despite this limitation, molecular graph structures are inherently expressive and attractive, as they preserve molecular topology. To preserve the structural representation of molecules as graphs, we propose a new model, GraphCliff, which integrates short- and long-range information through a gating mechanism. Experimental results demonstrate that GraphCliff consistently improves performance on both non-cliff and cliff compounds. Furthermore, layer-wise node embedding analyses reveal reduced over-smoothing and enhanced discriminative power relative to strong baseline graph models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GraphCliff: Short-Long Range Gating for Subtle Differences but Critical Changes Kim, Hajung Park, Jueon Choe, Junseok Baek, Sheunheun Hwang, Hyeon Kang, Jaewoo Computational Engineering, Finance, and Science Artificial Intelligence Quantitative structure-activity relationship assumes a smooth relationship between molecular structure and biological activity. However, activity cliffs defined as pairs of structurally similar compounds with large potency differences break this continuity. Recent benchmarks targeting activity cliffs have revealed that classical machine learning models with extended connectivity fingerprints outperform graph neural networks. Our analysis shows that graph embeddings fail to adequately separate structurally similar molecules in the embedding space, making it difficult to distinguish between structurally similar but functionally different molecules. Despite this limitation, molecular graph structures are inherently expressive and attractive, as they preserve molecular topology. To preserve the structural representation of molecules as graphs, we propose a new model, GraphCliff, which integrates short- and long-range information through a gating mechanism. Experimental results demonstrate that GraphCliff consistently improves performance on both non-cliff and cliff compounds. Furthermore, layer-wise node embedding analyses reveal reduced over-smoothing and enhanced discriminative power relative to strong baseline graph models. |
| title | GraphCliff: Short-Long Range Gating for Subtle Differences but Critical Changes |
| topic | Computational Engineering, Finance, and Science Artificial Intelligence |
| url | https://arxiv.org/abs/2511.03170 |