Data and Code for B3P2Augur

The blood-brain barrier serves as a critical interface between the bloodstream and brain tissue. It plays a pivotal role in safeguarding brain from harmful substances, thus protecting the integrity of the nervous system and preserving overall brain homeostasis. However, the prediction models for B3PPs have been hampered by issue of limited positive data. In response to this challenge, this study aimed to use data augmentation to process the data, in order to develop better prediction models.In this study, we analyzed the amino acid composition and sequence features of blood-brain barrier penetrating peptides, and finally presented B³P²Augur, a novel prediction model using borderline-SMOTE-based data augmentation and machine learning. Further analysis demonstrated that the model performs best on the independent set (AUROC=0.931) with a 25% data augmentation ratio. Additionally, B³P²Augur has been developed into a tool that can be executed on a computer, with the source code freely available.B³P²Augur improves the prediction performance compared with existing models and demonstrates the effectiveness of data augmentation algorithms in predicting blood-brain barrier penetrating peptides, which may be valuable for developing new peptides.