.png){kind=icon}
.png){kind=icon}
Return
Resolving data bias improves generalization in binding affinity prediction
.png){kind=icon}
OA
AI
DOI：10.1038/s42256-025-01124-5.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The field of computational drug design requires accurate scoring functions to predict binding affinities for protein–ligand interactions. However, train–test data leakage between the PDBbind database and the Comparative Assessment of Scoring Function benchmark datasets has severely inflated the performance metrics of currently available deep-learning-based binding affinity prediction models, leading to overestimation of their generalization capabilities. Here we address this issue by proposing PDBbind CleanSplit, a training dataset curated by a new structure-based filtering algorithm that eliminates train–test data leakage as well as redundancies within the training set. Retraining current top-performing models on CleanSplit caused their benchmark performance to drop substantially, indicating that the performance of existing models is largely driven by data leakage. By contrast, our graph neural network model maintains high benchmark performance when trained on CleanSplit. Leveraging a sparse graph modelling of protein–ligand interactions and transfer learning from language models, our model is able to generalize to strictly independent test datasets. Graber et al. characterize biases and data leakage in protein–ligand datasets and show that a cleanly filtered training–test split leads to improved generalization in binding affinity prediction tasks.
Keywords:
binding affinity prediction
data leakage
graph neural network
protein–ligand interactions
transfer learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
23.9
Papers:
1.3K
Citations:
1.5W
View more organizations