PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 27, 2025Journal of Chemical Information and Modeling6 citations

Robust Prediction of Protein–Ligand Binding Potency with Multi-modal Customized Gate Control

View Full Paper
BXBing XuWTWenting TangDMD. Muhammad

Key Points

  • The model significantly improved predictions of protein-ligand binding potency, outperforming traditional methods.
  • Achieving top performance in a blind competition, the model satisfied the challenge's strict criteria for accuracy in drug-potential evaluation.
  • Incorporating multimodal representations proved crucial, establishing their superior role in deep learning models for molecular interactions.
  • Pretraining with synthetic docking datasets showed notable enhancements in performance, reducing reliance on experimental data in limited scenarios.

Abstract

The main protease (Mpro) is a critical target in the design of antiviral drugs against coronaviruses, while accurately predicting the binding affinity between small molecules and this target remains a key challenge. In the recent Polaris challenge of blind drug-potency prediction targeting SARS-CoV-2 and MERS-CoV Mpro, we developed a multimodal multitask graph attention network based on the customized gate control framework (abbreviated as MultiMolCGC). Our team achieved top performance among all participating teams in the blind prediction challenge. In this paper, we detail the model development and further explorations in terms of pretraining, adjusting the model architecture, and many others. Our model consistently outperforms traditional machine learning baselines, demonstrating the effectiveness of end-to-end deep learning in capturing complex molecular interactions. Integrating multimodal representations proved essential, and the multitask specialized gating architecture outperformed both single-task and nonspecialized multitask variants, highlighting the value of tailored knowledge sharing. While auxiliary loss weighting and hyperparameter tuning offered modest improvements, incorporating predicted structural data unexpectedly reduced performance, likely due to structural uncertainty. Notably, pretraining on large-scale synthetic docking data sets significantly enhanced performance in low-data scenarios, reducing dependence on experimental pIC50 data. The numerical results highlight the potential of MultiMolCGC as a robust and accurate deep-learning framework for protein–ligand binding in future studies.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Xu et al. (2025) studied this question.

synapsesocial.com/papers/68d7be6ceebfec0fc5237f62https://doi.org/10.1021/acs.jcim.5c01668
Ask AI
Helpful
Bookmark
Share
View Full Paper