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

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).

Peptidomics: LC-MS operational parameters do matter.

The sensitive and specific detection of peptides at low levels in biofluids is critical to increase the lab-to-human translation of peptidomic research. An interesting group of peptides with increasing evidence for involvement in human diseases are quorum sensing peptides. To obtain more reliable conclusions on peptide measurands in biofluids, a selection of often neglected parts of the analytical process using LC-MS were investigated, with novel approaches recommended for each part. Quorum sensing peptides were used as the main model-peptides. The peptidomic parts investigated and discussed here are: Our work addresses aQbD-approached solutions to these challenges, encompassing sample stabilization measures, a suitable peptide anti-adsorption tool, judicious choice of injection solvent versus gradient system and optimal duty cycle parameters. Our recommendations will improve the peptidomics bio-analytics of not only quorum sensing peptides, but can also be of value for other measurands at low concentrations.