TriplEP-CPP: Algorithm for Predicting the Properties of Peptide Sequences

Abstract

Advancements in medicine and pharmacology have led to the development of systems that deliver biologically active molecules inside cells, increasing drug concentrations at target sites. This improves effectiveness and duration of action and reduces side effects on healthy tissues. Cell-penetrating peptides (CPPs) show promise in this area. While traditional medicinal chemistry methods have been used to develop CPPs, machine learning techniques can speed up and reduce costs in the search for new peptides. A predictive algorithm based on machine learning models was created to identify novel CPP sequences using molecular descriptors using a combination of algorithms like k-nearest neighbors, gradient boosting, and random forest. Some potential CPPs were found and tested for cytotoxicity and penetrating ability. A new low-toxicity CPP was discovered from the Rhopilema esculentum venom proteome through this study.

Keywords: cell penetrating peptides (CPP); functional activity prediction; intracellular delivery; machine learning; protein-lipid interaction; structural-dynamic properties.

Figure 1

The scheme of the predictive algorithm, reflecting the main steps of data collection and preprocessing, model selection and training, and results evaluation.

Figure 2

Confocal laser scanning microscopy of internalization of McCoy cells by the predicted cell-penetrating peptide. Mouse fibroblast cells (A) without incubation with peptide CpRE12; after incubation with (B) NBD-F tag without peptide; (C) NBD-F tagged penetratin; (D) NBD-F tagged control peptide CpHM15 from the organism Hirudo medicinalis, identified by the algorithm as non-penetrating; (E) NBD-F tagged predicted peptide CpRE12 from the jellyfish species Rhopilema esculentum. Hoechst 33342 intranuclear localization regions are blue; Alexa Fluor 594 cell wall localisation regions are red and peptide-NBD-F localization regions are green. (Scale bar: 106 μm).

Figure 2

Confocal laser scanning microscopy of internalization of McCoy cells by the predicted cell-penetrating peptide. Mouse fibroblast cells (A) without incubation with peptide CpRE12; after incubation with (B) NBD-F tag without peptide; (C) NBD-F tagged penetratin; (D) NBD-F tagged control peptide CpHM15 from the organism Hirudo medicinalis, identified by the algorithm as non-penetrating; (E) NBD-F tagged predicted peptide CpRE12 from the jellyfish species Rhopilema esculentum. Hoechst 33342 intranuclear localization regions are blue; Alexa Fluor 594 cell wall localisation regions are red and peptide-NBD-F localization regions are green. (Scale bar: 106 μm).

Figure 3

NMR monitoring of CpRE12 structure folding upon its interaction with DPC micelle. Overlaid 1H-NMR spectra acquired for CpRE12 initially dissolved in water buffer (in red) and after addition of micellar suspension at L/P of 60 (in blue) and 200 (in green).

Figure 4

Spatial structure of CpRE12 obtained by NMR analysis in DPC micellar environment. (A) Superposition of 12 NMR structures with the lowest target function aligned over the backbone atoms of the folded N-terminal helical part (residues 1–14). Backbone and side chain heavy atom bonds are shown in black and yellow, respectively. Superimposed ribbon diagrams of the NMR-derived structures of are presented on the right. (B) Representative NMR-derived structure of CpRE12. (C) Molecular hydrophobicity potential (MHP) distribution on the CpRE12 surface. Green is the most hydrophilic (MHP ≤ −3.6), yellow is the most hydrophobic (MHP ≥ 2.1). MHP values are given in logP units, where P is the octanol/water partition coefficient. (D) Molecular electrostatic potential (MEP) distribution on the CpRE12 surface. Red is the most negative (MEP ≤ −3 kt/e), blue is the most positive (MEP ≥ 3 kt/e) potential.

Figure 5

Results of MD simulation of the NMR-derived structure of CpRE12 in POPC bilayer. (A) Representative MD snapshot with CpRE12 embedded into hydrated explicit POPC bilayer. The peptide is given in ribbon presentation, glycine, alanine and serine residues are shown in green. Phosphorus atoms of the lipid headgroups are shown by orange spheres. The density distributions of the peptide (in black), phosphorous (in yellow) and choline (in blue) groups of lipids, averaged over MD trajectory, are presented on the left. (B) Alternative conformations of CpRE12 observed in MD simulation. (C,D) Color-coded representation of the MD time evolution of the secondary structure and protein-lipid contacts of CpRE12 embedded into POPC bilayer. The secondary structure elements are shown in blue—α-helix, in gray—3₁₀-helix, in yellow—turn, in green—bend, in white—coil. Protein-lipid contacts are color-coded according to the number of direct van der Waals contacts between atoms with 5 Å distance cut-off from white (0 contacts) to black (100 protein-lipid contacts). (E) Propensity of H-bond formation between all backbone and side chain atoms of CpRE12, estimated over the MD trajectory.