{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T18:02:25Z","timestamp":1785261745209,"version":"3.55.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014118","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000}}],"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Cell-penetrating peptides (CPPs) facilitate the delivery of a variety of therapeutic molecules across the plasma membrane, from small chemical substances to nucleic acid-based macromolecules, such as antisense oligonucleotides (ASOs). Among neutral ASOs, peptide nucleic acids (PNAs) and phosphorodiamidate morpholino oligomers (PMOs) have been extensively studied as potential medical treatments for Duchenne Muscular Dystrophy (DMD), a severe genetic disease that causes muscle degeneration progressively. Over the last few decades, many\n                      <jats:italic>in silico<\/jats:italic>\n                      methods have emerged to detect novel CPPs, counterbalancing the cost of wet-lab experiments.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In this study, we propose CPP2Vec, a Word2Vec-based CPP prediction method, where the Word2Vec technique is used to represent amino acid sequences of peptides. To address the limited sequence diversity, sparse biological grounding, and the still poorly understood mechanisms underlying CPPs uptake, we constructed CPP2Vec-GenSet, a hybrid dataset that integrates computationally generated peptides with experimentally curated CPPs. This combined resource provides a robust training foundation that supports reliable representation learning and enhances cross-task model performance. Using this framework, we developed three task-specific supervised machine learning models for CPP-Classification, Uptake-Efficiency and PMO-Delivery. The first two models were designed to determine if an unseen peptide is a CPP and to predict its uptake efficiency, respectively, while the PMO-Delivery model predicts whether a peptide could enhance the cellular delivery of a PMO-complex compared to its naked version. Furthermore, we explored an alternative approach using pre-trained protein-based Large Language Models (LLMs) \u2013 ProtT5, ProtBERT, and ESM-2 \u2013 to generate the embeddings, resulting in three task-specific models, namely CPP2LLM. Benchmarking against state-of-the-art CPP prediction tools demonstrates that CPP2Vec achieves robust predictive performance and generalization across tasks, while maintaining exceptional computational efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      In this research, we present a Machine Learning (ML)-based tool that introduces the use of the Word2Vec technique in the field of CPPs prediction. Notably, CPP2Vec automatically learns informative peptide representations directly from sequence data, generalizes reliably across multiple tasks, and achieves high predictive performance with minimal computational resources, providing a reproducible and practical\n                      <jats:italic>in silico<\/jats:italic>\n                      tool to support the early-stage identification and prioritization of CPPs with potential therapeutic relevance. CPP2Vec is available for use at:\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/SSvolou\/CPP2Vec\" xlink:type=\"simple\">https:\/\/github.com\/SSvolou\/CPP2Vec<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pcbi.1014118","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:42:42Z","timestamp":1783964562000},"page":"e1014118","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["CPP2Vec: A representation learning approach for cell-penetrating peptides prediction"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5047-8506","authenticated-orcid":true,"given":"Stavroula","family":"Svolou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0332-7506","authenticated-orcid":true,"given":"Vasileios","family":"Konstantakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasia","family":"Krithara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Paliouras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"pcbi.1014118.ref001","doi-asserted-by":"crossref","first-page":"697","DOI":"10.3389\/fphar.2020.00697","article-title":"Cell-Penetrating Peptides in Diagnosis and Treatment of Human Diseases: From Preclinical Research to Clinical Application","volume":"11","author":"J Xie","year":"2020","journal-title":"Front Pharmacol"},{"issue":"2","key":"pcbi.1014118.ref002","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1093\/bib\/bby124","article-title":"Empirical comparison and analysis of web-based cell-penetrating peptide prediction tools","volume":"21","author":"R Su","year":"2020","journal-title":"Brief Bioinform"},{"issue":"9","key":"pcbi.1014118.ref003","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.1021\/acs.jproteome.8b00322","article-title":"KELM-CPPpred: Kernel Extreme Learning Machine Based Prediction Model for Cell-Penetrating Peptides","volume":"17","author":"P Pandey","year":"2018","journal-title":"J Proteome Res"},{"key":"pcbi.1014118.ref004","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1186\/s12864-017-4128-1","article-title":"SkipCPP-Pred: an improved and promising sequence-based predictor for predicting cell-penetrating peptides","volume":"18","author":"L Wei","year":"2017","journal-title":"BMC Genomics"},{"issue":"5","key":"pcbi.1014118.ref005","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1021\/acs.jproteome.7b00019","article-title":"CPPred-RF: A Sequence-based Predictor for Identifying Cell-Penetrating Peptides and Their Uptake Efficiency","volume":"16","author":"L Wei","year":"2017","journal-title":"J Proteome Res"},{"issue":"1","key":"pcbi.1014118.ref006","first-page":"11","article-title":"CPPred-FL: a sequence-based predictor for large-scale identification of cell-penetrating peptides by feature representation learning","volume":"21","author":"X Qiang","year":"2020","journal-title":"Brief Bioinform"},{"key":"pcbi.1014118.ref007","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/1479-5876-11-74","article-title":"In silico approaches for designing highly effective cell penetrating peptides","volume":"11","author":"A Gautam","year":"2013","journal-title":"J Transl Med"},{"issue":"4","key":"pcbi.1014118.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004786","article-title":"Effective Design of Multifunctional Peptides by Combining Compatible Functions","volume":"12","author":"C Diener","year":"2016","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"pcbi.1014118.ref009","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.bbrc.2016.06.035","article-title":"Prediction of cell-penetrating peptides with feature selection techniques","volume":"477","author":"H Tang","year":"2016","journal-title":"Biochem Biophys Res Commun"},{"issue":"8","key":"pcbi.1014118.ref010","doi-asserted-by":"crossref","first-page":"2715","DOI":"10.1021\/acs.jproteome.8b00148","article-title":"Machine-Learning-Based Prediction of Cell-Penetrating Peptides and Their Uptake Efficiency with Improved Accuracy","volume":"17","author":"B Manavalan","year":"2018","journal-title":"J Proteome Res"},{"issue":"1","key":"pcbi.1014118.ref011","doi-asserted-by":"crossref","first-page":"7628","DOI":"10.1038\/s41598-021-87134-w","article-title":"Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space","volume":"11","author":"ECL de Oliveira","year":"2021","journal-title":"Sci Rep"},{"issue":"4","key":"pcbi.1014118.ref012","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1021\/acscentsci.8b00098","article-title":"Machine Learning To Predict Cell-Penetrating Peptides for Antisense Delivery","volume":"4","author":"JM Wolfe","year":"2018","journal-title":"ACS Cent Sci"},{"issue":"5","key":"pcbi.1014118.ref013","doi-asserted-by":"crossref","first-page":"2749","DOI":"10.1109\/TCBB.2021.3102133","article-title":"DeepCPPred: A Deep Learning Framework for the Discrimination of Cell-Penetrating Peptides and Their Uptake Efficiencies","volume":"19","author":"M Arif","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"11","key":"pcbi.1014118.ref014","doi-asserted-by":"crossref","first-page":"167604","DOI":"10.1016\/j.jmb.2022.167604","article-title":"MLCPP 2.0: An Updated Cell-penetrating Peptides and Their Uptake Efficiency Predictor","volume":"434","author":"B Manavalan","year":"2022","journal-title":"J Mol Biol"},{"issue":"3","key":"pcbi.1014118.ref015","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1021\/acs.jcim.4c01338","article-title":"pLM4CPPs: Protein Language Model-Based Predictor for Cell Penetrating Peptides","volume":"65","author":"N Kumar","year":"2025","journal-title":"J Chem Inf Model"},{"issue":"10","key":"pcbi.1014118.ref016","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning","volume":"44","author":"A Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pcbi.1014118.ref017","unstructured":"Devlin J. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint. 2018. doi: 10.48550\/arXiv.1810.04805"},{"issue":"6637","key":"pcbi.1014118.ref018","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Z Lin","year":"2023","journal-title":"Science"},{"key":"pcbi.1014118.ref019","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. In: 2013. https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"pcbi.1014118.ref020","volume-title":"Muscular Dystrophy: Hope Through Research","author":"National Institute of Neurological Diseases and Stroke","year":"1971"},{"issue":"6","key":"pcbi.1014118.ref021","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1016\/j.jacbts.2021.11.004","article-title":"Cardiovascular disease in Duchenne muscular dystrophy: overview and insight into novel therapeutic targets","volume":"7","author":"TI Schultz","year":"2022","journal-title":"Basic to Translational Science"},{"key":"pcbi.1014118.ref022","volume-title":"Computational methods for optimization of therapeutic approaches for Duchenne muscular dystrophy","author":"V Triantafyllidou","year":"2018"},{"key":"pcbi.1014118.ref023","unstructured":"Project SF. IUPAC amino acid ambiguity codes. https:\/\/samformat.pages.dev\/IUPAC-ambiguity-codes"},{"issue":"8","key":"pcbi.1014118.ref024","doi-asserted-by":"crossref","first-page":"104421","DOI":"10.1016\/j.drudis.2025.104421","article-title":"CPPsite3: An updated large repository of experimentally validated cell-penetrating peptides","volume":"30","author":"N Bajiya","year":"2025","journal-title":"Drug Discov Today"},{"issue":"1","key":"pcbi.1014118.ref025","doi-asserted-by":"crossref","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","article-title":"ProtGPT2 is a deep unsupervised language model for protein design","volume":"13","author":"N Ferruz","year":"2022","journal-title":"Nat Commun"},{"key":"pcbi.1014118.ref026","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-1-4939-3167-5_2","volume-title":"Plant bioinformatics: methods and protocols","author":"E Boutet","year":"2016"},{"issue":"13","key":"pcbi.1014118.ref027","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"W Li","year":"2006","journal-title":"Bioinformatics"},{"key":"pcbi.1014118.ref028","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkv1051","article-title":"CAMPR3: a database on sequences, structures and signatures of antimicrobial peptides","volume":"44","author":"FH Waghu","year":"2016","journal-title":"Nucleic Acids Res"},{"issue":"23","key":"pcbi.1014118.ref029","doi-asserted-by":"crossref","first-page":"5978","DOI":"10.3390\/ijms20235978","article-title":"BIOPEP-UWM Database of Bioactive Peptides: Current Opportunities","volume":"20","author":"P Minkiewicz","year":"2019","journal-title":"Int J Mol Sci"},{"issue":"7","key":"pcbi.1014118.ref030","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1002101","article-title":"Prediction of cell penetrating peptides by support vector machines","volume":"7","author":"WS Sanders","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1014118.ref031","doi-asserted-by":"crossref","DOI":"10.1093\/database\/bas015","article-title":"CPPsite: a curated database of cell penetrating peptides","volume":"2012","author":"A Gautam","year":"2012","journal-title":"Database (Oxford)"},{"issue":"1","key":"pcbi.1014118.ref032","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/nar\/27.1.49","article-title":"The SWISS-PROT protein sequence data bank and its supplement TrEMBL in 1999","volume":"27","author":"A Bairoch","year":"1999","journal-title":"Nucleic Acids Res"},{"issue":"11","key":"pcbi.1014118.ref033","doi-asserted-by":"crossref","first-page":"166703","DOI":"10.1016\/j.jmb.2020.11.002","article-title":"Cppsite 2.0: An Available Database of Experimentally Validated Cell-Penetrating Peptides Predicting their Secondary and Tertiary Structures","volume":"433","author":"K Kardani","year":"2021","journal-title":"J Mol Biol"},{"issue":"23","key":"pcbi.1014118.ref034","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/btt518","article-title":"CPPpred: prediction of cell penetrating peptides","volume":"29","author":"TA Holton","year":"2013","journal-title":"Bioinformatics"},{"issue":"4","key":"pcbi.1014118.ref035","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac265","article-title":"iACVP: markedly enhanced identification of anti-coronavirus peptides using a dataset-specific word2vec model","volume":"23","author":"H Kurata","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1014118.ref036","unstructured":"\u0158eh\u016f\u0159ek R, Sojka P. Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, Valletta, Malta, 2010. 45\u201350."},{"issue":"140","key":"pcbi.1014118.ref037","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"C Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"pcbi.1014118.ref038","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"UniProt Consortium","year":"2019","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014118.ref039","doi-asserted-by":"crossref","DOI":"10.1093\/bioadv\/vbac026","article-title":"Federated horizontally partitioned principal component analysis for biomedical applications","volume":"2","author":"A Hartebrodt","year":"2022","journal-title":"Bioinform Adv"},{"key":"pcbi.1014118.ref040","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, et al. Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv. 2019. doi: 10.48550\/arXiv.1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"issue":"1","key":"pcbi.1014118.ref041","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The Protein Data Bank","volume":"28","author":"HM Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"issue":"15","key":"pcbi.1014118.ref042","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"A Rives","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1014118.ref043","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"pcbi.1014118.ref044","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"A Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1014118.ref045","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J. Umap: Uniform manifold approximation and projection for dimension reduction. In: 2018. https:\/\/arxiv.org\/abs\/1802.03426","DOI":"10.21105\/joss.00861"},{"issue":"11","key":"pcbi.1014118.ref046","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"K Pearson","year":"1901","journal-title":"The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science"},{"issue":"4912","key":"pcbi.1014118.ref047","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.1126\/science.2662404","article-title":"The molecular basis of muscular dystrophy in the mdx mouse: a point mutation","volume":"244","author":"P Sicinski","year":"1989","journal-title":"Science"},{"key":"pcbi.1014118.ref048","unstructured":"Yin H, Lu Q, Wood M. Effective exon skipping and restoration of dystrophin expression by peptide nucleic acid antisense oligonucleotides in mdx mice. N\/A. 2023."},{"issue":"24","key":"pcbi.1014118.ref049","doi-asserted-by":"crossref","first-page":"3909","DOI":"10.1093\/hmg\/ddn293","article-title":"Cell-penetrating peptide-conjugated antisense oligonucleotides restore systemic muscle and cardiac dystrophin expression and function","volume":"17","author":"H Yin","year":"2008","journal-title":"Hum Mol Genet"},{"issue":"7","key":"pcbi.1014118.ref050","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1038\/mt.2011.79","article-title":"Pip5 transduction peptides direct high efficiency oligonucleotide-mediated dystrophin exon skipping in heart and phenotypic correction in mdx mice","volume":"19","author":"H Yin","year":"2011","journal-title":"Mol Ther"},{"issue":"9","key":"pcbi.1014118.ref051","doi-asserted-by":"crossref","first-page":"1624","DOI":"10.1038\/mt.2008.120","article-title":"Sustained dystrophin expression induced by peptide-conjugated morpholino oligomers in the muscles of mdx mice","volume":"16","author":"N Jearawiriyapaisarn","year":"2008","journal-title":"Mol Ther"},{"issue":"8","key":"pcbi.1014118.ref052","article-title":"Pip6-PMO, A New Generation of Peptide-oligonucleotide Conjugates With Improved Cardiac Exon Skipping Activity for DMD Treatment","volume":"1","author":"C Betts","year":"2012","journal-title":"Mol Ther Nucleic Acids"},{"issue":"1","key":"pcbi.1014118.ref053","doi-asserted-by":"crossref","first-page":"4477","DOI":"10.1038\/s41467-025-59494-8","article-title":"DG9 boosts PMO nuclear uptake and exon skipping to restore dystrophic muscle and cardiac function","volume":"16","author":"MNA Shah","year":"2025","journal-title":"Nat Commun"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014118","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T17:44:40Z","timestamp":1785260680000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014118"}},"subtitle":[],"editor":[{"given":"Nir","family":"Ben-Tal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":53,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014118","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]}}}