EUVIMEDEUVIMED entdecken
Crossref

DiConSite: A Unified Topology-Adaptive Architecture for Protein Binding Site Prediction Across Ligand Modalities

Shouzhi Chen, Zhenchao Tang, Linlin You, Yonghong Tian, Calvin Yu-Chian Chen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-13

DOI: 10.1109/tpami.2026.3720695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Shouzhi Chen und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate identification of protein binding sites is essential for understanding biological mechanisms and advancing drug design. However, many structure-based predictors rely on spatial graphs whose topology remains fixed throughout message passing, making them sensitive to structural noise and difficult to transfer across ligand modalities. To address this issue, we propose DiConSite, a topology-adaptive and reusable architecture for residue-level binding site prediction across ligand-specific tasks. DiConSite is centered on a Latent Topological Evolution (LTE) module that augments the initial Euclidean graph with a latent functional topology. A Hierarchical Topological Distillation (HTD) objective and a Dynamic Curriculum Distillation (DCD) schedule are further introduced as LTE-dependent optimization stabilizers: they align relational structure across network depths only after the underlying topology has been refined. Extensive experiments across nine benchmarks show that DiConSite achieves consistently strong and often best-performing results, while improving robustness to structural uncertainty and cross-modal variation. By combining protein language model embeddings with topology-adaptive geometric reasoning, DiConSite offers a reusable framework for residue-level protein interaction analysis.

Zitieren

APA

Chen, S., Tang, Z., You, L., Tian, Y., & Chen, C. Y. (2026). DiConSite: A Unified Topology-Adaptive Architecture for Protein Binding Site Prediction Across Ligand Modalities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-13. https://doi.org/10.1109/tpami.2026.3720695

Vancouver

Chen S, Tang Z, You L, Tian Y, Chen CY. DiConSite: A Unified Topology-Adaptive Architecture for Protein Binding Site Prediction Across Ligand Modalities. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-13. doi:10.1109/tpami.2026.3720695

BibTeX
@article{Chen2026,
  author = {Chen, Shouzhi and Tang, Zhenchao and You, Linlin and Tian, Yonghong and Chen, Calvin Yu-Chian},
  title = {DiConSite: A Unified Topology-Adaptive Architecture for Protein Binding Site Prediction Across Ligand Modalities},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  pages = {1--13},
  doi = {10.1109/tpami.2026.3720695}
}
Kostenlos starten →