{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:34:20Z","timestamp":1793918060459,"version":"4.8.0"},"reference-count":34,"publisher":"American Chemical Society (ACS)","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP25nk0101112"],"award-info":[{"award-number":["JP25nk0101112"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Chemically modified and macrocyclic peptides are increasingly important therapeutics, yet current molecular representation models do not natively represent chemical modification and covalent topology in a unified way. Atom-level strings obscure macrocyclic connectivity, whereas protein sequence models cannot encode noncanonical residues and explicit cross-links. Here we pretrain an encoder-only transformer directly on Hierarchical Editing Language for Macromolecules (HELM) notation, which specifies monomer identity and connectivity. In this work, we show that the resulting representations achieve best mean performance in cyclic peptide membrane permeability prediction (random split R2 = 0.668; retaining best mean performance under a Murcko scaffold split), exceeding external pretrained SMILES-based encoders. An architecture-matched SMILES control narrowed the HELM\u2013SMILES gap under full finetuning, whereas HELM-BERT retained clearer advantages in frozen-representation settings. HELM-BERT also preserves HELM-specified macrocyclic topology in a linearly accessible form and supports competitive peptide\u2013protein interaction prediction across complementary Propedia and ChEMBL benchmarks. More broadly, these findings suggest that pretraining directly on notation that makes structural constraints explicit offers a transferable strategy for biomolecular modalities that fall between small-molecule chemistry and protein sequence.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00451","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T23:34:21Z","timestamp":1784158461000},"page":"7900-7916","source":"Crossref","is-referenced-by-count":3,"title":["HELM-BERT: Topology-Aware\nRepresentations for Chemically\nModified Peptides"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3232-1386","authenticated-orcid":true,"given":"Seungeon","family":"Lee","sequence":"first","affiliation":[{"name":"Kyoto University , , 53 Kawahara-cho, Shogoin , , ,","place":["Sakyo-ku, Kyoto, Japan, 606-8507"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9569-8370","authenticated-orcid":true,"given":"Takuto","family":"Koyama","sequence":"additional","affiliation":[{"name":"Kyoto University , , 53 Kawahara-cho, Shogoin , , ,","place":["Sakyo-ku, Kyoto, Japan, 606-8507"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8097-6166","authenticated-orcid":true,"given":"Itsuki","family":"Maeda","sequence":"additional","affiliation":[{"name":"Kyoto University , , 53 Kawahara-cho, Shogoin , , ,","place":["Sakyo-ku, Kyoto, Japan, 606-8507"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigeyuki","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"Kyoto University , , 53 Kawahara-cho, Shogoin , , ,","place":["Sakyo-ku, Kyoto, Japan, 606-8507"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasushi","family":"Okuno","sequence":"additional","affiliation":[{"name":"Kyoto University , , 53 Kawahara-cho, Shogoin , , ,","place":["Sakyo-ku, Kyoto, Japan, 606-8507"]},{"name":"RIKEN Center for Computational Science , 7-1-26 minatojima-minamimachi , Chuo-ku , , ,","place":["Kobe, Hyogo, Japan, 650-0047"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"2026072709081966400_cit1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26115131","article-title":"Therapeutic Peptides:\nRecent Advances in Discovery, Synthesis, and Clinical Translation","volume":"26","author":"Zheng","year":"2025","journal-title":"Int. J. Mol. Sci."},{"key":"2026072709081966400_cit2","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-022-00904-4","article-title":"Therapeutic\npeptides: current applications and future directions","volume":"7","author":"Wang","year":"2022","journal-title":"Signal Transduction Targeted Ther."},{"key":"2026072709081966400_cit3","doi-asserted-by":"publisher","first-page":"4167","DOI":"10.1021\/jacs.8b13178","article-title":"Macrocyclic Peptides\nas Drug Candidates: Recent Progress\nand Remaining Challenges","volume":"141","author":"Vinogradov","year":"2019","journal-title":"J. Am. Chem. Soc."},{"key":"2026072709081966400_cit4","doi-asserted-by":"publisher","first-page":"7264","DOI":"10.1158\/1078-0432.CCR-07-2184","article-title":"The Challenge of\nDrugging Undruggable Targets in Cancer:\nLessons Learned from Targeting BCL-2 Family Members","volume":"13","author":"Verdine","year":"2007","journal-title":"Clin. Cancer Res."},{"key":"2026072709081966400_cit5","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale chemical\nlanguage representations capture molecular structure\nand properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026072709081966400_cit6","unstructured":"Chithrananda, S.; Grand, G.; Ramsundar, B.\n          ChemBERTa: Large-Scale\nSelf-Supervised Pretraining for Molecular Property Prediction. 2020, arXiv:2010.09885. arXiv.org e-Printarchive. https:\/\/arxiv.org\/abs\/2010.09885."},{"key":"2026072709081966400_cit7","doi-asserted-by":"crossref","unstructured":"Wang, S.; Guo, Y.; Wang, Y.; Sun, H.; Huang, J.\n          SMILES-BERT: Large Scale Unsupervised\nPre-Training\nfor Molecular Property Prediction. In  Proceedings\nof the 10th ACM International Conference on Bioinformatics, Computational\nBiology and Health Informatics, Niagara Falls, NY USA, September\n7, 2019; ACM: New York, NY, USA;  pp 429\u2013436.","DOI":"10.1145\/3307339.3342186"},{"key":"2026072709081966400_cit8","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale\nprediction of atomic-level protein structure with\na language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026072709081966400_cit9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nchemical language and information system. 1. Introduction to methodology\nand encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026072709081966400_cit10","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.4155\/fmc.15.78","article-title":"Beyond\nCyclosporine A: Conformation-Dependent\nPassive Membrane Permeabilities of Cyclic Peptide Natural Products","volume":"7","author":"Ahlbach","year":"2015","journal-title":"Future Med. Chem."},{"key":"2026072709081966400_cit11","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1021\/jacs.0c06115","article-title":"Geometrically Diverse Lariat Peptide\nScaffolds Reveal an Untapped Chemical Space of High Membrane Permeability","volume":"143","author":"Kelly","year":"2021","journal-title":"J. Am. Chem. Soc."},{"key":"2026072709081966400_cit12","doi-asserted-by":"publisher","first-page":"2796","DOI":"10.1021\/ci3001925","article-title":"HELM: A Hierarchical\nNotation Language for Complex Biomolecule Structure Representation","volume":"52","author":"Zhang","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709081966400_cit13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae364","article-title":"HELM-GPT:\nde novo macrocyclic peptide design using generative pre-trained transformer","volume":"40","author":"Xu","year":"2024","journal-title":"Bioinformatics"},{"key":"2026072709081966400_cit14","unstructured":"He, P.; Liu, X.; Gao, J.; Chen, W.\n          DeBERTa: Decoding-Enhanced\nBERT with Disentangled\nAttention.  International Conference on Learning\nRepresentations (ICLR), 2021."},{"key":"2026072709081966400_cit15","unstructured":"He, P.; Gao, J.; Chen, W.\n          DeBERTaV3: Improving DeBERTa using\nELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.  International Conference on Learning Representations (ICLR), 2023."},{"key":"2026072709081966400_cit16","doi-asserted-by":"publisher","first-page":"D930","DOI":"10.1093\/nar\/gky1075","article-title":"ChEMBL: towards direct\ndeposition of bioassay data","volume":"47","author":"Mendez","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2026072709081966400_cit17","doi-asserted-by":"publisher","first-page":"2240","DOI":"10.1021\/acs.jcim.2c01573","article-title":"CycPeptMPDB:\nA Comprehensive Database of Membrane Permeability\nof Cyclic Peptides","volume":"63","author":"Li","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709081966400_cit18","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2023.1103103","article-title":"Propedia v2.3: A novel\nrepresentation approach for the peptide-protein interaction database\nusing graph-based structural signatures","volume":"3","author":"Martins","year":"2023","journal-title":"Front.\nBioinform."},{"key":"2026072709081966400_cit19","unstructured":"Landrum, G.; Paolo, T.; Brian, K.; et al.\n          rdkit\/rdkit: 2025_09_3\n(Q3 2025) Release.  Zenodo, 202510.5281\/zenodo.17746401."},{"key":"2026072709081966400_cit20","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","volume":"8","author":"Joshi","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2026072709081966400_cit21","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes:\nA graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"key":"2026072709081966400_cit22","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"A Cluster Separation Measure","volume":"PAMI-1","author":"Davies","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2026072709081966400_cit23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for\ncluster analysis","volume":"3","author":"Calin\u0301ski","year":"1974","journal-title":"Commun. Stat."},{"key":"2026072709081966400_cit24","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The Properties of Known Drugs. 1.\nMolecular Frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med. Chem."},{"key":"2026072709081966400_cit25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s13321-026-01155-z","article-title":"Chemical genomics language\nmodel toward reliable and explainable compound-protein interaction\nexploration","volume":"18","author":"Koyama","year":"2026","journal-title":"J. Cheminf."},{"key":"2026072709081966400_cit26","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1093\/bioinformatics\/btt058","article-title":"aCSM: noise-free graph-based\nsignatures to large-scale receptor-based ligand prediction","volume":"29","author":"Pires","year":"2013","journal-title":"Bioinformatics"},{"key":"2026072709081966400_cit27","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1021\/acs.jcim.4c01441","article-title":"Peptide-Aware Chemical Language Model\nSuccessfully\nPredicts Membrane Diffusion of Cyclic Peptides","volume":"65","author":"Feller","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026072709081966400_cit28","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","article-title":"Molecular Transformer:\nA Model for\nUncertainty-Calibrated Chemical Reaction Prediction","volume":"5","author":"Schwaller","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"2026072709081966400_cit29","doi-asserted-by":"publisher","first-page":"4","DOI":"10.32614\/RJ-2015-001","article-title":"Peptides:\nA Package\nfor Data Mining of Antimicrobial Peptides","volume":"7","author":"Osorio","year":"2015","journal-title":"R\nJ,"},{"key":"2026072709081966400_cit30","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1023\/A:1024068626366","article-title":"Inference for the Generalization\nError","volume":"52","author":"Nadeau","year":"2003","journal-title":"Mach. Learn."},{"key":"2026072709081966400_cit31","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False\nDiscovery Rate: A Practical and\nPowerful Approach to Multiple Testing.","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R.\nStat. Soc. Ser. B: Stat. Methodol."},{"key":"2026072709081966400_cit32","doi-asserted-by":"crossref","DOI":"10.4324\/9780203771587","volume-title":"Statistical Power Analysis\nfor the Behavioral Sciences","author":"Cohen","year":"2013","edition":"2"},{"key":"2026072709081966400_cit33","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","article-title":"Comparison\nof the predicted and observed secondary structure of T4 phage lysozyme","volume":"405","author":"Matthews","year":"1975","journal-title":"Biochim. Biophys. Acta, Protein Struct."},{"key":"2026072709081966400_cit34","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the\nMatthews correlation coefficient\n(MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00451","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/7900\/65967524\/acs.jcim.6c00451.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/14\/7900\/65967524\/acs.jcim.6c00451.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T13:31:36Z","timestamp":1785159096000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/14\/7900\/5211366\/HELM-BERT-Topology-Aware-Representations-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":34,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7,15]]},"published-print":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00451","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}