{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T10:53:51Z","timestamp":1791370431381,"version":"4.3.1"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioinform."],"abstract":"<jats:p>Why does the proteasome cleave proteins at some peptide bonds but not others? Prior work has emphasized sequence motifs, amino acid properties, and proteasome isoform, but the role of local secondary-structure context remains unclear. Here, we evaluate whether helix, strand, and coil context help explain proteasomal cleavage and whether such information can improve cleavage-site prediction. By mining a human and viral PDB structure corpus, we found that high-confidence predicted cleavage sites are enriched in beta-strand extended conformations and depleted in coil-like regions. We then trained a machine learning model using only secondary-structure labels, and benchmarked its performance against a sequence-aware baseline, other well-known predictors, and ensemble approaches using hybrid position-specific scoring matrices (PSSMs). Our proof-of-concept SSO-8 model was trained on secondary structure features predicted by NetSurfP-3.0 for 8-mer sequences derived from a diverse experimental digestion dataset of 20 substrate proteins. SSO-8 reached AUC = 0.649 on a held-out benchmark constitutive dataset and AUC = 0.737 on a held-out immunoproteasome dataset. A same-protocol sequence-only model reached AUC of 0.674 and 0.736, respectively, and paired peptide\/protein-level tests found no evidence of a significant SSO-8-vs-sequence difference. Our model was also competitive with other sequence-based proteasomal prediction methods, using different training sets and architectures. Therefore, secondary-structure-only information captured substantial cleavage signal despite using much less input information than full substrate sequence, with the clearest support in the immunoproteasome dataset and hybrid PSSM analyses. These results extend the known preference for extended active-site geometry by showing an association between local substrate backbone conformation and proteasomal cleavage propensities, particularly in the context of the immunoproteasome, and suggest the use of sequence-encoded secondary-structure propensities as a measurable feature of proteasomal cleavage preferences.<\/jats:p>","DOI":"10.3389\/fbinf.2026.1730535","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T10:25:45Z","timestamp":1791368745000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Substrate secondary structure is associated with proteasomal cleavage propensity"],"prefix":"10.3389","volume":"6","author":[{"given":"Matheus De Bastos Balb\u00e9","family":"Gutierres","sequence":"first","affiliation":[{"name":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Gen\u00e9tica e Biologia Molecular (PPGBM-UFRGS)","place":["Porto Alegre, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Finn","family":"Beruldsen","sequence":"additional","affiliation":[{"name":"Department of Biology and Biochemistry, University of Houston","place":["Houston, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinler Amaral","family":"Antunes","sequence":"additional","affiliation":[{"name":"Department of Biology and Biochemistry, University of Houston","place":["Houston, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo Fioravanti","family":"Vieira","sequence":"additional","affiliation":[{"name":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Gen\u00e9tica e Biologia Molecular (PPGBM-UFRGS)","place":["Porto Alegre, Brazil"]},{"name":"Programa de P\u00f3s-Gradua\u00e7\u00e3o em Sa\u00fade e Desenvolvimento Humano \u2013 PPGSAUDEH, Universidade La Salle","place":["Canoas, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1093\/oxfordjournals.jbchem.a124327","article-title":"Interferon-gamma induces different subunit organizations and functional diversity of proteasomes","volume":"115","author":"Aki","year":"1994","journal-title":"J. Biochem."},{"key":"B2","doi-asserted-by":"publisher","first-page":"13126","DOI":"10.1038\/s41598-021-92632-y","article-title":"NetCleave: an open-source algorithm for predicting C-Terminal antigen processing for MHC-I and MHC-II","volume":"11","author":"Amengual-Rigo","year":"2021","journal-title":"Sci. Rep."},{"key":"B4","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1146\/annurev-biochem-062917-011931","article-title":"Structure and function of the 26S proteasome","volume":"87","author":"Bard","year":"2018","journal-title":"Annu. Rev. Biochem."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.4049\/jimmunol.164.4.1898","article-title":"Abrogation of CTL epitope processing by single amino acid substitution flanking the C-Terminal proteasome cleavage Site1","volume":"164","author":"Beekman","year":"2000","journal-title":"J. Immunol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.molcel.2012.08.029","article-title":"The direction of protein entry into the proteasome determines the variety of peptide products and depends on the force needed to unfold its two termini","volume":"48","author":"Berko","year":"2012","journal-title":"Mol. Cell"},{"key":"B7","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s00251-014-0815-0","article-title":"Role of peptide processing predictions in T cell epitope identification: contribution of different prediction programs","volume":"67","author":"Calis","year":"2015","journal-title":"Immunogenetics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3390\/biom11010060","article-title":"The ubiquitin\u2013proteasome system in immune cells","volume":"11","author":"\u00c7etin","year":"2021","journal-title":"Biomolecules"},{"key":"B10","doi-asserted-by":"publisher","first-page":"bbad242","DOI":"10.1093\/bib\/bbad242","article-title":"EnGens: a computational framework for generation and analysis of representative protein conformational ensembles","volume":"24","author":"Conev","year":"2023","journal-title":"Brief. Bioinform."},{"key":"B11","doi-asserted-by":"publisher","first-page":"7573","DOI":"10.1038\/ncomms8573","article-title":"Cryo-EM reveals the conformation of a substrate analogue in the human 20S proteasome core","volume":"6","author":"da Fonseca","year":"2015","journal-title":"Nat. Commun."},{"key":"B12","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/0014-5793(89)81441-3","article-title":"The multicatalytic proteinase (prosome) is ubiquitous from eukaryotes to archaebacteria","volume":"251","author":"Dahlmann","year":"1989","journal-title":"FEBS Lett."},{"key":"B13","doi-asserted-by":"publisher","first-page":"eaav0725","DOI":"10.1126\/science.aav0725","article-title":"Substrate-engaged 26S proteasome structures reveal mechanisms for ATP-Hydrolysis\u2013Driven translocation","volume":"362","author":"de la Pe\u00f1a","year":"2018","journal-title":"Science"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1084\/jem.182.6.1865","article-title":"The cleavage preference of the proteasome governs the yield of antigenic peptides","volume":"182","author":"Eggers","year":"1995","journal-title":"J. Exp. Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.humimm.2019.01.003","article-title":"Peptide trimming by endoplasmic reticulum aminopeptidases: role of MHC class I binding and ERAP dimerization","volume":"80","author":"Evnouchidou","year":"2019","journal-title":"Hum. Immunol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1146\/annurev.biochem.78.081507.101607","article-title":"Recognition and processing of ubiquitin-protein conjugates by the proteasome","volume":"78","author":"Finley","year":"2009","journal-title":"Annu. Rev. Biochem."},{"key":"B17","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.tcb.2003.09.001","article-title":"Proteasome degradation: enter the substrate","volume":"13","author":"F\u00f6rster","year":"2003","journal-title":"Trends Cell Biol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"11597","DOI":"10.1021\/acs.jmedchem.4c00840","article-title":"ERAP inhibitors in autoimmunity and immuno-oncology: medicinal chemistry insights","volume":"67","author":"Fougiaxis","year":"2024","journal-title":"J. Med. Chem."},{"key":"B19","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/biom11010054","article-title":"Nuclear ubiquitin-proteasome pathways in proteostasis maintenance","volume":"11","author":"Frani\u0107","year":"2021","journal-title":"Biomolecules"},{"key":"B20","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1126\/science.aav5095","article-title":"Structural topology defines protective CD8+ T cell epitopes in the HIV proteome","volume":"364","author":"Gaiha","year":"2019","journal-title":"Science"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e1006541","DOI":"10.1371\/journal.ppat.1006541","article-title":"HIV-1 epitopes presented by MHC class I types associated with superior immune containment of viremia have highly constrained fitness landscapes","volume":"13","author":"Gorin","year":"2017","journal-title":"PLoS Pathog."},{"key":"B22","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.str.2014.11.017","article-title":"Crystal structure of the human 20S proteasome in complex with carfilzomib","volume":"23","author":"Harshbarger","year":"2015","journal-title":"Structure"},{"key":"B23","doi-asserted-by":"publisher","first-page":"W500","DOI":"10.1093\/nar\/gkh429","article-title":"STRIDE: a web server for secondary structure assignment from known atomic coordinates of proteins","volume":"32","author":"Heinig","year":"2004","journal-title":"Nucleic Acids Res."},{"key":"B24","doi-asserted-by":"publisher","first-page":"W510","DOI":"10.1093\/nar\/gkac439","article-title":"NetSurfP-3.0: accurate and fast prediction of protein structural features by protein language models and deep learning","volume":"50","author":"H\u00f8ie","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"B25","doi-asserted-by":"publisher","first-page":"10900","DOI":"10.1038\/ncomms10900","article-title":"A unified mechanism for proteolysis and autocatalytic activation in the 20S proteasome","volume":"7","author":"Huber","year":"2016","journal-title":"Nat. Commun."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1002884","article-title":"Positional bias of MHC class I restricted T-Cell epitopes in viral antigens is likely due to a bias in conservation","volume":"9","author":"Kim","year":"2013","journal-title":"PLoS Comput. Biol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/0022-2836(80)90373-3","article-title":"How different amino acid sequences determine similar protein structures: the structure and evolutionary dynamics of the globins","volume":"136","author":"Lesk","year":"1980","journal-title":"J. Mol. Biol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13029-018-0068-7","article-title":"SOV_refine: a further refined definition of segment overlap score and its significance for protein structure similarity","volume":"13","author":"Liu","year":"2018","journal-title":"Source Code Biol. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1126\/science.7725097","article-title":"Crystal structure of the 20S proteasome from the archaeon T. acidophilum at 3.4 A resolution","volume":"268","author":"L\u00f6we","year":"1995","journal-title":"Science"},{"key":"B30","doi-asserted-by":"publisher","first-page":"PR1","DOI":"10.1021\/cr900368a","article-title":"Update 1 of: proteases universally recognize beta strands in their active sites","volume":"110","author":"Madala","year":"2010","journal-title":"Chem. Rev."},{"key":"B31","doi-asserted-by":"publisher","first-page":"e4792","DOI":"10.1002\/pro.4792","article-title":"UCSF ChimeraX: tools for structure building and analysis","volume":"32","author":"Meng","year":"2023","journal-title":"Protein Sci. Publ. Protein Soc."},{"key":"B32","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00251-005-0781-7","article-title":"The role of the proteasome in generating cytotoxic T-Cell epitopes: insights obtained from improved predictions of proteasomal cleavage","volume":"57","author":"Nielsen","year":"2005","journal-title":"Immunogenetics"},{"key":"B33","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn Res."},{"key":"B34","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1038\/nsmb814","article-title":"An unstructured initiation site is required for efficient proteasome-mediated degradation","volume":"11","author":"Prakash","year":"2004","journal-title":"Nat. Struct. Mol. Biol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1038\/s41580-018-0040-z","article-title":"Regulation of proteasome assembly and activity in health and disease","volume":"19","author":"Rousseau","year":"2018","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1038\/nature09444","article-title":"The proteasome antechamber maintains substrates in an unfolded state","volume":"467","author":"Ruschak","year":"2010","journal-title":"Nature"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1564649","DOI":"10.3389\/fcell.2025.1564649","article-title":"Unveiling the impact of ERAP1 and ERAP2 on migration, angiogenesis and ER stress response","volume":"13","author":"Saulle","year":"2025","journal-title":"Front. Cell Dev. Biol."},{"key":"B38","first-page":"743","article-title":"Pybrain","volume":"11","author":"Schaul","year":"2010","journal-title":"J. Mach. Learn Res."},{"key":"B39","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/s0006-291x(67)80055-x","article-title":"On the size of the active site in proteases. I. Papain","volume":"27","author":"Schechter","year":"1967","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"B40","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1472-6807-7-3","article-title":"Occurrence of protein structure elements in conserved sequence regions","volume":"7","author":"Sitbon","year":"2007","journal-title":"BMC Struct. Biol."},{"key":"B41","doi-asserted-by":"publisher","first-page":"13042","DOI":"10.3390\/ijms222313042","article-title":"Residue folding degree\u2014relationship to secondary structure categories and use as collective variable","volume":"22","author":"Sladek","year":"2021","journal-title":"Int. J. Mol. Sci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1038\/s41467-024-45339-3","article-title":"Protein degradation by human 20S proteasomes elucidates the interplay between peptide hydrolysis and splicing","volume":"15","author":"Soh","year":"2024","journal-title":"Nat. Commun."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1126\/science.3287615","article-title":"Measuring the accuracy of diagnostic systems","volume":"240","author":"Swets","year":"1988","journal-title":"Science"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/s00018-005-4528-2","article-title":"Modeling the MHC class I pathway by combining predictions of proteasomal cleavage, TAP transport and MHC class I binding","volume":"62","author":"Tenzer","year":"2005","journal-title":"Cell Mol. Life Sci."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1084\/jem.194.1.1","article-title":"Discrete cleavage motifs of constitutive and immunoproteasomes revealed by quantitative analysis of cleavage products","volume":"194","author":"Toes","year":"2001","journal-title":"J. Exp. Med."},{"key":"B46","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1021\/cr040669e","article-title":"Proteases universally recognize beta strands in their active sites","volume":"105","author":"Tyndall","year":"2005","journal-title":"Chem. Rev."},{"key":"B47","doi-asserted-by":"publisher","first-page":"102340","DOI":"10.1016\/j.coi.2023.102340","article-title":"Visualising Tapasin- and TAPBPR-assisted editing of major histocompatibility complex Class-I immunopeptidomes","volume":"83","author":"van Hateren","year":"2023","journal-title":"Curr. Opin. Immunol."},{"key":"B48","volume-title":"The Python Language Reference Manual","author":"Van Rossum","year":"2011"},{"key":"B49","doi-asserted-by":"publisher","first-page":"D436","DOI":"10.1093\/nar\/gkae1092","article-title":"The immune epitope database (IEDB): 2024 update","volume":"53","author":"Vita","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"B50","doi-asserted-by":"publisher","first-page":"3723","DOI":"10.1093\/bioinformatics\/btab628","article-title":"Pepsickle rapidly and accurately predicts proteasomal cleavage sites for improved neoantigen identification","volume":"37","author":"Weeder","year":"2021","journal-title":"Bioinformatics"},{"key":"B51","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/978-1-4939-6406-2_6","article-title":"SPIDER2: a package to predict secondary structure, accessible surface area, and main-chain torsional angles by deep neural networks","volume-title":"Prediction of Protein Secondary Structure","author":"Yang","year":"2017"},{"key":"B52","doi-asserted-by":"publisher","first-page":"4771","DOI":"10.1074\/jbc.M109.060095","article-title":"Degradation of some polyubiquitinated proteins requires an intrinsic proteasomal binding element in the substrates","volume":"285","author":"Zhao","year":"2010","journal-title":"J. Biol. Chem."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1730535\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T10:25:47Z","timestamp":1791368747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1730535\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":51,"alternative-id":["10.3389\/fbinf.2026.1730535"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1730535","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1730535"}}