BBB-PEP-prediction: improved computational model for identification of blood–brain barrier peptides using blending position relative composition specific features and ensemble modeling

• Published in: Journal of cheminformatics Vol. 15; no. 1; p. 110
• Main Authors: Naseem, Ansar, Alturise, Fahad, Alkhalifah, Tamim, Khan, Yaser Daanial
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 18-11-2023; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Accuracy; Analysis; Bagging; Benchmarks; Blending; Blood-brain barrier; Brain research; Central nervous system; Chemistry; Chemistry and Materials Science; Classifiers; Computational Biology/Bioinformatics; Computational neuroscience; Computer Applications in Chemistry; Computer simulation; Computer-generated environments; Correlation coefficient; Correlation coefficients; Data Mining; Documentation and Information in Chemistry; Drug delivery; Drug development; Drugs; Ensemble Modeling; Machine Learning; Nervous system; Nervous system diseases; Neurophysiology; Peptide Classification; Peptides; Predictions; Sensitivity analysis; Sequence Analysis; Stacking; Statistical analysis; Theoretical and Computational Chemistry; Transfer LearningArtificial intelligence; Taiwan; Supervised Learning; Pattern Recognition; Peptide Classification; Data Mining; Ensemble Modeling; Transfer LearningArtificial intelligence; Sequence Analysis; Machine Learning
• ISSN: 1758-2946; 1758-2946
• DOI: 10.1186/s13321-023-00773-1

BBPs have the potential to facilitate the delivery of drugs to the brain, opening up new avenues for the development of treatments targeting diseases of the central nervous system (CNS). The obstacle faced in central nervous system disorders stems from the formidable task of traversing the blood–brain barrier (BBB) for pharmaceutical agents. Nearly 98% of small molecule-based drugs and nearly 100% of large molecule-based drugs encounter difficulties in successfully penetrating the BBB. This importance leads to identification of these peptides, can help in healthcare systems. In this study, we proposed an improved intelligent computational model BBB-PEP-Prediction for identification of BBB peptides. Position and statistical moments based features have been computed for acquired benchmark dataset. Four types of ensembles such as bagging, boosting, stacking and blending have been utilized in the methodology section. Bagging employed Random Forest (RF) and Extra Trees (ET), Boosting utilizes XGBoost (XGB) and Light Gradient Boosting Machine (LGBM). Stacking uses ET and XGB as base learners, blending exploited LGBM and RF as base learners, while Logistic Regression (LR) has been applied as Meta learner for stacking and blending. Three classifiers such as LGBM, XGB and ET have been optimized by using Randomized search CV. Four types of testing such as self-consistency, independent set, cross-validation with 5 and 10 folds and jackknife test have been employed. Evaluation metrics such as Accuracy (ACC), Specificity (SPE), Sensitivity (SEN), Mathew’s correlation coefficient (MCC) have been utilized. The stacking of classifiers has shown best results in almost each testing. The stacking results for independent set testing exhibits accuracy, specificity, sensitivity and MCC score of 0.824, 0.911, 0.831 and 0.663 respectively. The proposed model BBB-PEP-Prediction shown superlative performance as compared to previous benchmark studies. The proposed system helps in future research and research community for in-silico identification of BBB peptides.