{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T18:04:49Z","timestamp":1749146689701,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031716706"},{"type":"electronic","value":"9783031716713"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-71671-3_15","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T22:45:48Z","timestamp":1726785948000},"page":"209-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["How Much Do DNA and\u00a0Protein Deep Embeddings Preserve Biological Information?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1025-7363","authenticated-orcid":false,"given":"Matteo","family":"Tolloso","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-0344","authenticated-orcid":false,"given":"Silvia Giulia","family":"Galfr\u00e8","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8840-6157","authenticated-orcid":false,"given":"Arianna","family":"Pavone","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1497-9515","authenticated-orcid":false,"given":"Marco","family":"Podda","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-7143","authenticated-orcid":false,"given":"Alina","family":"S\u00eerbu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3261-6235","authenticated-orcid":false,"given":"Corrado","family":"Priami","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,19]]},"reference":[{"key":"15_CR1","unstructured":"Abdi, H., et\u00a0al.: DISTATIS: the analysis of multiple distance matrices. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)-Workshops. IEEE (2005)"},{"issue":"1","key":"15_CR2","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","volume":"25","author":"M Ashburner","year":"2000","unstructured":"Ashburner, M., et al.: Gene ontology: tool for the unification of biology. Nat. Genet. 25(1), 25\u201329 (2000)","journal-title":"Nat. Genet."},{"issue":"44","key":"15_CR3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2311219120","volume":"120","author":"G Benegas","year":"2023","unstructured":"Benegas, G., Batra, S.S., Song, Y.S.: DNA language models are powerful predictors of genome-wide variant effects. Proc. Natl. Acad. Sci. 120(44), e2311219120 (2023)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"15_CR4","unstructured":"Bepler, T., Berger, B.: Learning protein sequence embeddings using information from structure (2019). arXiv preprint arXiv:1902.08661"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Bepler, T., Berger, B.: Learning the protein language: evolution, structure, and function. Cell Syst. 12(6), 654\u2013669 (2021)","DOI":"10.1016\/j.cels.2021.05.017"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Brandes, N., et\u00a0al.: ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics 38(8), 2102\u20132110 (2022)","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Detlefsen, N.S., Hauberg, S., Boomsma, W.: Learning meaningful representations of protein sequences. Nat. Commun. 13(1), 1914 (2022)","DOI":"10.1038\/s41467-022-29443-w"},{"key":"15_CR8","unstructured":"Devlin, J. et al.: BERT: Pre-training of deep bidirectional transformers for language understanding (2018). arXiv preprint arXiv:1810.04805"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Durbin, R., Eddy, S.R., Krogh, A., Mitchison, G.: Biological sequence analysis: probabilistic models of proteins and nucleic acids. Cambridge university press, Cambridge (1998)","DOI":"10.1017\/CBO9780511790492"},{"issue":"10","key":"15_CR10","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","volume":"44","author":"A Elnaggar","year":"2021","unstructured":"Elnaggar, A., et al.: ProtTrans: toward understanding the language of life through self-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 7112\u20137127 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Evans, R., et al.: Protein complex prediction with alphafold-multimer. bioRxiv (2022). https:\/\/doi.org\/10.1101\/2021.10.04.463034","DOI":"10.1101\/2021.10.04.463034"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Fenoy, E., Edera, A.A., Stegmayer, G.: Transfer learning in proteins: evaluating novel protein learned representations for bioinformatics tasks. Briefings Bioinform. 23(4), bbac232 (2022)","DOI":"10.1093\/bib\/bbac232"},{"issue":"1","key":"15_CR13","doi-asserted-by":"publisher","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","volume":"13","author":"N Ferruz","year":"2022","unstructured":"Ferruz, N., Schmidt, S., H\u00f6cker, B.: ProtGPT2 is a deep unsupervised language model for protein design. Nat. Commun. 13(1), 4348 (2022)","journal-title":"Nat. Commun."},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Gao, M., et\u00a0al.: AF2Complex predicts direct physical interactions in multimeric proteins with deep learning. Nat. Commun. 13(1), 1744 (2022)","DOI":"10.1038\/s41467-022-29394-2"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Heinzinger, M., et\u00a0al.: Modeling aspects of the language of life through transfer-learning protein sequences. BMC Bioinform. 20(1), 723 (2019)","DOI":"10.1186\/s12859-019-3220-8"},{"issue":"2","key":"15_CR16","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1038\/s41587-023-01763-2","volume":"42","author":"BL Hie","year":"2024","unstructured":"Hie, B.L., et al.: Efficient evolution of human antibodies from general protein language models. Nat. Biotechnol. 42(2), 275\u2013283 (2024)","journal-title":"Nat. Biotechnol."},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF01908075","volume":"2","author":"L Hubert","year":"1985","unstructured":"Hubert, L., Arabie, P.: Comparing partitions. J. Classif. 2, 193\u2013218 (1985)","journal-title":"J. Classif."},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome. Bioinformatics 37(15), 2112\u20132120 (2021)","DOI":"10.1093\/bioinformatics\/btab083"},{"issue":"13","key":"15_CR19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2308788121","volume":"121","author":"X Jing","year":"2024","unstructured":"Jing, X., Wu, F., Luo, X., Xu, J.: Single-sequence protein structure prediction by integrating protein language models. Proc. Natl. Acad. Sci. 121(13), e2308788121 (2024)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Jumper, J., et\u00a0al.: Highly accurate protein structure prediction with AlphaFold. Nature 596(7873), 583\u2013589 (2021)","DOI":"10.1038\/s41586-021-03819-2"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Khurana, D., et\u00a0al.: Natural language processing: state of the art, current trends and challenges. Multimedia Tools Appl. 82(3), 3713\u20133744 (2023)","DOI":"10.1007\/s11042-022-13428-4"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Kosloff, M., Kolodny, R.: Sequence-similar, structure-dissimilar protein pairs in the PDB. Proteins: Structure Funct. Bioinform. 71(2), 891\u2013902 (2008)","DOI":"10.1002\/prot.21770"},{"key":"15_CR23","unstructured":"Kusner, M., et\u00a0al.: From word embeddings to document distances. In: International Conference on Machine Learning. PMLR (2015)"},{"key":"15_CR24","unstructured":"Lin, Z., et\u00a0al.: Language models of protein sequences at the scale of evolution enable accurate structure prediction. bioRxiv (2022)"},{"issue":"6637","key":"15_CR25","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z., et al.: Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379(6637), 1123\u20131130 (2023)","journal-title":"Science"},{"issue":"8","key":"15_CR26","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1038\/s41587-022-01618-2","volume":"41","author":"A Madani","year":"2023","unstructured":"Madani, A., et al.: Large language models generate functional protein sequences across diverse families. Nat. Biotechnol. 41(8), 1099\u20131106 (2023)","journal-title":"Nat. Biotechnol."},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Mardikoraem, M., et\u00a0al.: Generative models for protein sequence modeling: recent advances and future directions. Briefings Bioinform. 24(6), bbad358 (2023)","DOI":"10.1093\/bib\/bbad358"},{"key":"15_CR28","unstructured":"Mikolov, T., et\u00a0al.: Efficient estimation of word representations in vector space (2013). arXiv preprint arXiv:1301.3781"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Milligan, G.W., Cooper, M.C.: A study of the comparability of external criteria for hierarchical cluster analysis. Multivar. Behav. Res. 21(4), 441\u2013458 (1986)","DOI":"10.1207\/s15327906mbr2104_5"},{"issue":"11","key":"15_CR30","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1016\/j.cels.2023.10.002","volume":"14","author":"E Nijkamp","year":"2023","unstructured":"Nijkamp, E., Ruffolo, J.A., Weinstein, E.N., Naik, N., Madani, A.: ProGen2: exploring the boundaries of protein language models. Cell Syst. 14(11), 968\u2013978 (2023)","journal-title":"Cell Syst."},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Peters, M.E., et\u00a0al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1. Association for Computational Linguistics, New Orleans, Louisiana (2018)","DOI":"10.18653\/v1\/N18-1202"},{"issue":"15","key":"15_CR32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives, A., et al.: Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. 118(15), e2016239118 (2021)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"15_CR33","unstructured":"Salant, S., Berant, J.: Contextualized word representations for reading comprehension (2017). arXiv preprint arXiv:1712.03609"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Sievers, F., et\u00a0al.: Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal omega. Mol. Syst. Biol. 7(1), 539 (2011)","DOI":"10.1038\/msb.2011.75"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Sofi, M.Y., Shafi, A., Masoodi, K.Z.: Chapter 6 - multiple sequence alignment. In: Bioinformatics for Everyone, pp. 47\u201353. Academic Press (2022)","DOI":"10.1016\/B978-0-323-91128-3.00011-2"},{"key":"15_CR36","unstructured":"Su, J. et al.: RoFormer: Enhanced transformer with rotary position embedding (2021). arXiv preprint arXiv:2104.09864"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Suzek, B.E., et\u00a0al.: UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches. Bioinformatics 31(6), 926\u2013932 (2015)","DOI":"10.1093\/bioinformatics\/btu739"},{"key":"15_CR38","doi-asserted-by":"publisher","unstructured":"Tan, X., Yuan, C., Wu, H., Zhao, X.: Comprehensive evaluation of BERT model for DNA-language for prediction of DNA sequence binding specificities in fine-tuning phase. In: Huang, D.S., Jo, K.H., Jing, J., Premaratne, P., Bevilacqua, V., Hussain, A. (eds.) Intelligent Computing Theories and Application. ICIC 2022. LNCS, vol. 13394. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-13829-4_8","DOI":"10.1007\/978-3-031-13829-4_8"},{"key":"15_CR39","unstructured":"The Gene Ontology Consortium, et\u00a0al.: The gene ontology knowledgebase in 2023. Genetics 224(1), iyad031 (2023)"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Tsaban, T., et\u00a0al.: Harnessing protein folding neural networks for peptide\u2013protein docking. Nat. Commun. 13(1), 176 (2022)","DOI":"10.1038\/s41467-021-27838-9"},{"issue":"3","key":"15_CR41","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s42256-022-00457-9","volume":"4","author":"S Unsal","year":"2022","unstructured":"Unsal, S., Atas, H., Albayrak, M., Turhan, K., Acar, A.C., Do\u011fan, T.: Learning functional properties of proteins with language models. Nat. Mach. Intell. 4(3), 227\u2013245 (2022)","journal-title":"Nat. Mach. Intell."},{"issue":"2","key":"15_CR42","first-page":"19","volume":"3","author":"M Vijaymeena","year":"2016","unstructured":"Vijaymeena, M., Kavitha, K.: A survey on similarity measures in text mining. Mach. Learn. Appl. Int. J. 3(2), 19\u201328 (2016)","journal-title":"Mach. Learn. Appl. Int. J."},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Villegas-Morcillo, A., Gomez, A.M., Sanchez, V.: An analysis of protein language model embeddings for fold prediction. Briefings Bioinform. 23(3), bbac142 (2022)","DOI":"10.1093\/bib\/bbac142"},{"key":"15_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmds.2022.100044","volume":"3","author":"P V\u00e4th","year":"2022","unstructured":"V\u00e4th, P., et al.: PROVAL: a framework for comparison of protein sequence embeddings. J. Comput. Math. Data Sci. 3, 100044 (2022)","journal-title":"J. Comput. Math. Data Sci."},{"key":"15_CR45","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.7126","volume":"7","author":"Y Yao","year":"2019","unstructured":"Yao, Y., et al.: An integration of deep learning with feature embedding for protein-protein interaction prediction. PeerJ 7, e7126 (2019)","journal-title":"PeerJ"}],"container-title":["Lecture Notes in Computer Science","Computational Methods in Systems Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-71671-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T22:47:21Z","timestamp":1726786041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-71671-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031716706","9783031716713"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-71671-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"19 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CMSB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Methods in Systems Biology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pisa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmsb2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cmsb.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}