Papers › Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on...

Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure

23 Sep 2024arXiv:2410.05278archive 2025-07-28

Shengjie Xu, Lingxi Xie

Antibody-drug conjugates (ADCs) have emerged as a promising class of targeted cancer therapeutics, but the design and optimization of their cytotoxic payloads remain challenging. This study introduces DumplingGNN, a novel hybrid Graph Neural Network architecture specifically designed for predicting ADC payload activity based on chemical structure. By integrating Message Passing Neural Networks (MPNN), Graph Attention Networks (GAT), and GraphSAGE layers, DumplingGNN effectively captures multi-scale molecular features and leverages both 2D topological and 3D structural information. We evaluate DumplingGNN on a comprehensive ADC payload dataset focusing on DNA Topoisomerase I inhibitors, as well as on multiple public benchmarks from MoleculeNet. DumplingGNN achieves state-of-the-art performance across several datasets, including BBBP (96.4% ROC-AUC), ToxCast (78.2% ROC-AUC), and PCBA (88.87% ROC-AUC). On our specialized ADC payload dataset, it demonstrates exceptional accuracy (91.48%), sensitivity (95.08%), and specificity (97.54%). Ablation studies confirm the synergistic effects of the hybrid architecture and the critical role of 3D structural information in enhancing predictive accuracy. The model's strong interpretability, enabled by attention mechanisms, provides valuable insights into structure-activity relationships. DumplingGNN represents a significant advancement in molecular property prediction, with particular promise for accelerating the design and optimization of ADC payloads in targeted cancer therapy development.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Activity Prediction Drug Discovery Graph Attention Graph Neural Network Molecular Property Prediction Property Prediction Specificity

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Molecular Property Prediction	BBBP	DumplingGNN	ROC-AUC	96.4	#1 of 29	Archive leaderboard	report
Molecular Property Prediction	PCBA	DumplingGNN	ROC-AUC	88.87	#1 of 2	Archive leaderboard	report
Molecular Property Prediction	ToxCast	DumplingGNN	ROC-AUC	78.2	#1 of 8	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Attention Graph Neural Network GraphSAGE Softmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections