Prediction of unconventional protein secretion by exosomes

Abstract

Motivation In eukaryotes, proteins targeted for secretion contain a signal peptide, which allows them to proceed through the conventional ER/Golgi-dependent pathway. However, an important number of proteins lacking a signal peptide can be secreted through unconventional routes, including that mediated by exosomes. Currently, no method is available to predict protein secretion via exosomes. Results Here, we first assembled a dataset including the sequences of 2992 proteins secreted by exosomes and 2961 proteins that are not secreted by exosomes. Subsequently, we trained different random forests models on feature vectors derived from the sequences in this dataset. In tenfold cross-validation, the best model was trained on dipeptide composition, reaching an accuracy of 69.88% ± 2.08 and an area under the curve (AUC) of 0.76 ± 0.03. In an independent dataset, this model reached an accuracy of 75.73% and an AUC of 0.840. After these results, we developed ExoPred, a web-based tool that uses random forests to predict protein secretion by exosomes. Conclusion ExoPred is available for free public use at http://imath.med.ucm.es/exopred/. Datasets are available at http://imath.med.ucm.es/exopred/datasets/.

Proteomic Profiling and Functional Analysis of B Cell-Derived Exosomes upon Pneumocystis Infection

“…Conventional ER-Golgi pathway and unconventional pathway are two types of protein secretion pathways, while the latter form is further categorized into vesicular and nonvesicular pathways [ 39 ]. Exosomes, a smaller subtype of EVs, are therefore speculated to carry proteins mainly of the unconventional pathway [ 40 ]. In our data, 495 (29.10%) proteins encapsulated in B cell exosomes were predicted to be unconventionally secreted, whereas a lower proportion (18.16%) of proteins were involved in the classical pathway based on the detection of signal peptides.…”

Unconventional Protein Secretion Dependent on Two Extracellular Vesicles: Exosomes and Ectosomes

“…Stimulation of the MVB exocytosis discussed so far is followed by the diffusion of many ILV/exosome vesicles, from the lumen to the extracellular space ( Figure 1 ) ( Rabouille, 2017 ; Bebelman et al, 2020 ; Gruenberg, 2020 ; Zhang et al, 2020 ; Gurung et al, 2021 ; Ras-Carmona et al, 2021 ; Raudenska et al, 2021 ). In many cases such process is accompanied by the release of ectosomes, the other type of EVs, generated not within the cytoplasm but at the plasma membrane.…”

“…In addition to proteins, cargos contain molecules of different nature: various types of RNA (mostly microRNAs, miRs, together with messenger RNAs, mRNAs, long non-coding RNAs, lncRNAs, and ribosome RNAs, rRNAs), small sequences of DNA, lipids and metabolic molecules ( Figure 2A ) ( Yang and Gould, 2013 ; Ras-Carmona et al, 2021 ). Recent studies have shown ubiquitin and ubiquitin-like proteins to participate in protein post-translational modifications and in the control of protein complex composition ( Chen et al, 2021 ; Padovani et al, 2022 ), thus contributing to their accumulation within ILVs ( Yang and Gould, 2013 ; Chen et al, 2021 ; Ras-Carmona et al, 2021 ). Surface proteins of cargo are often anchored to the ILV membrane by myristoylation, palmitoylation or other sequences.…”

BCEPS: A Web Server to Predict Linear B Cell Epitopes with Enhanced Immunogenicity and Cross-Reactivity

“…Here, Support Vector Machine (SVM)-with both Gaussian radial basis function (RBF) Kernel and polynomial function-, Neural Network (NN), K-Nearest Neighbor (KNN,) and Random Forest (RF) were used. Input data for WEKA consisted of datasets in ARFF format with epitope sequences translated into amino acid composition, dipeptide composition, and the combination of both, as described elsewhere in Ras-Carmona et al's study [21]. Briefly, the amino acid composition translation produces a vector feature including the proportion of each of the 20 natural amino acids in any sequence.…”