Improved prediction and characterization of blood-brain barrier penetrating peptides using estimated propensity scores of dipeptides

Charoenkwan, Phasit; Chumnanpuen, Pramote; Schaduangrat, Nalini; Lió, Píetro; Moni, Mohammad Ali; Shoombuatong, Watshara

doi:10.1007/s10822-022-00476-z

Cited by 6 publications

(1 citation statement)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noteworthy to compare the performance of the BrainPepPass with previously developed techniques for predicting B3PPs. While some ML-based tools, such as BBPpred, 67 B3Pred, 68 BBPpredict, 36 and SCMB3PP, 69 have been developed to predict the BBB permeability of peptides using ML algorithms trained with properties extracted from the primary structure of natural peptides encoded in FASTA format, the proposed ML-based framework presented herein employs a distinct approach by incorporating the 3D structure of these molecules encoded in MOL format. Additionally, most peptides used for training and testing BrainPepPass contain chemical modifications, which further distinguish our tool from those that focus on natural peptides.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

BrainPepPass: A Framework Based on Supervised Dimensionality Reduction for Predicting Blood-Brain Barrier-Penetrating Peptides

de Oliveira,

Hirmz,

Wynendaele

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Peptides that pass through the blood-brain barrier (BBB) not only are implicated in brain-related pathologies but also are promising therapeutic tools for treating brain diseases, e.g., as shuttles carrying active medicines across the BBB. Computational prediction of BBB-penetrating peptides (B3PPs) has emerged as an interesting approach because of its ability to screen large peptide libraries in a cost-effective manner. In this study, we present BrainPepPass, a machine learning (ML) framework that utilizes supervised manifold dimensionality reduction and extreme gradient boosting (XGB) algorithms to predict natural and chemically modified B3PPs. The results indicate that the proposed tool outperforms other classifiers, with average accuracies exceeding 94% and 98% in 10-fold cross-validation and leave-one-out cross-validation (LOOCV), respectively. In addition, accuracy values ranging from 45% to 97.05% were achieved in the independent tests. The BrainPepPass tool is available in a public repository for academic use (https://github.com/ewerton-cristhian/BrainPepPass).

show abstract