Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space

Abstract

Cell-penetrating peptides (CPPs) are naturally able to cross the lipid bilayer membrane that protects cells. These peptides share common structural and physicochemical properties and show different pharmaceutical applications, among which drug delivery is the most important. Due to their ability to cross the membranes by pulling high-molecular-weight polar molecules, they are termed Trojan horses. In this study, we proposed a machine learning (ML)-based framework named BChemRF-CPPred (beyondchemicalrules-basedframework forCPP prediction) that uses an artificial neural network, a support vector machine, and a Gaussian process classifier to differentiate CPPs from non-CPPs, using structure- and sequence-based descriptors extracted from PDB and FASTA formats. The performance of our algorithm was evaluated by tenfold cross-validation and compared with those of previously reported prediction tools using an independent dataset. The BChemRF-CPPred satisfactorily identified CPP-like structures using natural and synthetic modified peptide libraries and also obtained better performance than those of previously reported ML-based algorithms, reaching the independent test accuracy of 90.66% (AUC = 0.9365) for PDB, and an accuracy of 86.5% (AUC = 0.9216) for FASTA input. Moreover, our analyses of the CPP chemical space demonstrated that these peptides break some molecular rules related to the prediction of permeability of therapeutic molecules in cell membranes. This is the first comprehensive analysis to predict synthetic and natural CPP structures and to evaluate their chemical space using an ML-based framework. Our algorithm is freely available for academic use at http://comptools.linc.ufpa.br/BChemRF-CPPred.

A Yeast-Derived Peptide Promotes Skin Wound Healing by Stimulating Effects on Fibroblast and Immunomodulatory Activities

“…The exact relationship between peptide size and its anti-inflammatory activity is not well-established, but some reports attributed the higher anti-inflammatory of small-sized peptides to the easier absorbance by immune cells [12]. Peptides that penetrate cells usually have a sequence length of 5 to 42 amino acids [27]. The size of VW-9 may also have influenced its anti-inflammatory activity.…”

Molecular Descriptors and QSAR Models for Sedative Activity of Sesquiterpenes Administered to Mice via Inhalation

“…However, using restrictive criteria with different filters could discard some interesting chemicals [60]. Nevertheless, although other interesting rules such as the beyond rule of five (bRo5) exist [61][62][63][64], sesquiterpenes in this study do not have a MW >500 Da. Therefore, the bRo5 was not considered in the analysis.…”

Design of Membrane Active Peptides Considering Multi-Objective Optimization for Biomedical Application

“…Some of the above-mentioned algorithms are freely available web-based applications that can be used in attempts to optimize AMPs based on QSAR criteria [103,104]. A combination of different algorithms allows the accurate identification of membrane active peptides in chemical space [105] requiring basic input of sequence data in FASTA format only. Beyond that, membrane active peptides selectively lysing the membranes of cancer cells are designed using ML techniques in the same way [106].…”