{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:55:17Z","timestamp":1757620517664,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819506972"},{"type":"electronic","value":"9789819506989"}],"license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-0698-9_27","type":"book-chapter","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T07:27:52Z","timestamp":1753946872000},"page":"325-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TREPP: Tandem Repeat Expansion Pathogenicity Predicting Approach Using Stacked CatBoost Models and\u00a0Multiple Features"],"prefix":"10.1007","author":[{"given":"Minghua","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,1]]},"reference":[{"issue":"2","key":"27_CR1","doi-asserted-by":"publisher","first-page":"R13","DOI":"10.1186\/gb-2003-4-2-r13","volume":"4","author":"S Subramanian","year":"2003","unstructured":"Subramanian, S., Mishra, R.K., Singh, L.: Genome-wide analysis of microsatellite repeats in humans: their abundance and density in specific genomic regions. Genome Biol. 4(2), R13 (2003)","journal-title":"Genome Biol."},{"key":"27_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13100-020-00206-y","volume":"11","author":"JA Shortt","year":"2020","unstructured":"Shortt, J.A., Ruggiero, R.P., Cox, C., et al.: Finding and extending ancient simple sequence repeat-derived regions in the human genome. Mob. DNA 11, 11 (2020)","journal-title":"Mob. DNA"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"International Human Genome Sequencing Consortium: Initial sequencing and analysis of the human genome. Nature 409(6822), 860\u2013921 (2001)","DOI":"10.1038\/35057062"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Genome analysis of the platypus reveals unique signatures of evolution. Nature 453(7192), 175\u2013183 (2008)","DOI":"10.1038\/nature06936"},{"issue":"7147","key":"27_CR5","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/nature05977","volume":"447","author":"SM Mirkin","year":"2007","unstructured":"Mirkin, S.M.: Expandable DNA repeats and human disease. Nature 447(7147), 932\u201340 (2007)","journal-title":"Nature"},{"issue":"6","key":"27_CR6","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1038\/nrg1348","volume":"5","author":"H Ellegren","year":"2004","unstructured":"Ellegren, H.: Microsatellites: simple sequences with complex evolution. Nat. Rev. Genet. 5(6), 435\u201345 (2004)","journal-title":"Nat. Rev. Genet."},{"issue":"5","key":"27_CR7","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1038\/nrg.2017.115","volume":"19","author":"AJ Hannan","year":"2018","unstructured":"Hannan, A.J.: Tandem repeats mediating genetic plasticity in health and disease. Nat. Rev. Genet. 19(5), 286\u2013298 (2018)","journal-title":"Nat. Rev. Genet."},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Zhou, Z.D., et al.: Neurodegenerative diseases associated with non-coding CGG tandem repeat expansions. Nat. Rev. Neurol. 18(3), 145\u2013157 (2022)","DOI":"10.1038\/s41582-021-00612-7"},{"issue":"1","key":"27_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s40478-021-01201-x","volume":"9","author":"SR Chintalaphani","year":"2021","unstructured":"Chintalaphani, S.R., Pineda, S.S., Deveson, I.W., Kumar, K.R.: An update on the neurological short tandem repeat expansion disorders and the emergence of long-read sequencing diagnostics. Acta Neuropathol. Commun. 9(1), 98 (2021)","journal-title":"Acta Neuropathol. Commun."},{"issue":"7","key":"27_CR10","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1038\/s41576-024-00696-z","volume":"25","author":"IS Rajan-Babu","year":"2024","unstructured":"Rajan-Babu, I.S., Dolzhenko, E., Eberle, M.A., Friedman, J.M.: Sequence composition changes in short tandem repeats: heterogeneity, detection, mechanisms and clinical implications. Nat. Rev. Genet. 25(7), 476\u2013499 (2024)","journal-title":"Nat. Rev. Genet."},{"issue":"9","key":"27_CR11","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1016\/j.cell.2024.03.004","volume":"187","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Ye, W., Li, J.S., et al.: A genome-wide spectrum of tandem repeat expansions in 338,963 humans. Cell 187(9), 2336\u20132341 (2024)","journal-title":"Cell"},{"issue":"10","key":"27_CR12","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1038\/s41587-023-02057-3","volume":"42","author":"E Dolzhenko","year":"2024","unstructured":"Dolzhenko, E., English, A., et al.: Characterization and visualization of tandem repeats at genome scale. Nat. Biotechnol. 42(10), 1606\u20131614 (2024)","journal-title":"Nat. Biotechnol."},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hiatt, L., Weisburd, B., Dolzhenko, E., et\u00a0al.: Strchive: a dynamic resource detailing population-level and locus-specific insights at tandem repeat disease loci. medRxiv (2024)","DOI":"10.1101\/2024.05.21.24307682"},{"issue":"1","key":"27_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GE Batista","year":"2004","unstructured":"Batista, G.E., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explorations Newsl 6(1), 20\u201329 (2004)","journal-title":"ACM SIGKDD Explorations Newsl"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Ferreira, A.J., Figueiredo, M.A.: Boosting algorithms: a review of methods, theory, and applications. In: Ensemble Machine Learning: Methods and Applications, pp. 35\u201385 (2012)","DOI":"10.1007\/978-1-4419-9326-7_2"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"27_CR17","unstructured":"Ke, G., Meng, Q., Finley, T., et\u00a0al.: Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR18","unstructured":"Prokhorenkova, L., Gusev, G., et\u00a0al.: Catboost: unbiased boosting with categorical features. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.jare.2020.11.006","volume":"30","author":"YW Hsiao","year":"2021","unstructured":"Hsiao, Y.W., Tao, C.L., et al.: A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models. J. Adv. Res. 30, 113\u2013122 (2021)","journal-title":"J. Adv. Res."},{"issue":"5","key":"27_CR20","doi-asserted-by":"publisher","first-page":"3301","DOI":"10.1007\/s11831-023-09904-1","volume":"30","author":"N Chaplot","year":"2023","unstructured":"Chaplot, N., Pandey, D., Kumar, Y., et al.: A comprehensive analysis of artificial intelligence techniques for the prediction and prognosis of genetic disorders using various gene disorders. Arch. Comput. Methods Eng. 30(5), 3301\u20133323 (2023)","journal-title":"Arch. Comput. Methods Eng."},{"issue":"1","key":"27_CR21","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s13059-024-03171-4","volume":"25","author":"S Fazal","year":"2024","unstructured":"Fazal, S., Danzi, M.C., Xu, I., et al.: Rexprt: a machine learning tool to predict pathogenicity of tandem repeat loci. Genome Biol. 25(1), 39 (2024)","journal-title":"Genome Biol."},{"issue":"D1","key":"27_CR22","doi-asserted-by":"publisher","first-page":"D966","DOI":"10.1093\/nar\/gkae1078","volume":"53","author":"JM Mudge","year":"2025","unstructured":"Mudge, J.M., Carbonell-Sala, S., et al.: Gencode 2025: reference gene annotation for human and mouse. Nucleic Acids Res. 53(D1), D966\u2013D975 (2025)","journal-title":"Nucleic Acids Res."},{"issue":"2","key":"27_CR23","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1093\/nar\/27.2.573","volume":"27","author":"G Benson","year":"1999","unstructured":"Benson, G.: Tandem repeats finder: a program to analyze DNA sequences. Nucleic Acids Res. 27(2), 573\u2013580 (1999)","journal-title":"Nucleic Acids Res."},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, et\u00a0al.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623\u20132631 (2019)","DOI":"10.1145\/3292500.3330701"},{"issue":"1","key":"27_CR25","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1038\/s41597-020-00633-9","volume":"7","author":"S Fazal","year":"2020","unstructured":"Fazal, S., Danzi, M.C., et al.: Large scale in silico characterization of repeat expansion variation in human genomes. Sci. Data 7(1), 294 (2020)","journal-title":"Sci. Data"},{"issue":"45","key":"27_CR26","doi-asserted-by":"publisher","first-page":"27014","DOI":"10.1074\/jbc.270.45.27014","volume":"270","author":"S Kang","year":"1995","unstructured":"Kang, S., Ohshima, K., Shimizu, M., et al.: Pausing of DNA synthesis in vitro at specific loci in CTG and CGG triplet repeats from human hereditary disease genes. J. Biol. Chem. 270(45), 27014\u201327021 (1995)","journal-title":"J. Biol. Chem."},{"issue":"4","key":"27_CR27","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1073\/pnas.96.4.1504","volume":"96","author":"H Moore","year":"1999","unstructured":"Moore, H., Greenwell, P.W., Liu, C.P., et al.: Triplet repeats form secondary structures that escape DNA repair in yeast. Proc. Natl. Acad. Sci. 96(4), 1504\u20131509 (1999)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"10","key":"27_CR28","doi-asserted-by":"publisher","first-page":"5623","DOI":"10.1093\/nar\/gkab371","volume":"49","author":"DA Kiktev","year":"2021","unstructured":"Kiktev, D.A., Dominska, M., et al.: The fidelity of DNA replication, particularly on GC-rich templates, is reduced by defects of the FE-S cluster in DNA polymerase $$\\delta $$. Nucleic Acids Res. 49(10), 5623\u20135636 (2021)","journal-title":"Nucleic Acids Res."},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Viguera, E., Canceill, D., Ehrlich, S.D.: Replication slippage involves DNA polymerase pausing and dissociation. EMBO J. (2001)","DOI":"10.1093\/emboj\/20.10.2587"},{"key":"27_CR30","unstructured":"Online mendelian inheritance in man omim\u00ae. mckusick-nathans institute of genetic medicine, johns hopkins university (baltimore md) (2022). https:\/\/omim.org\/"},{"key":"27_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcn.2021.103623","volume":"113","author":"CS Leblond","year":"2021","unstructured":"Leblond, C.S., Le, T.L., Malesys, S., et al.: Operative list of genes associated with autism and neurodevelopmental disorders based on database review. Mol. Cell. Neurosci. 113, 103623 (2021)","journal-title":"Mol. Cell. Neurosci."}],"container-title":["Lecture Notes in Computer Science","Bioinformatics Research and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0698-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T08:29:13Z","timestamp":1757320153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0698-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"ISBN":["9789819506972","9789819506989"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0698-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,1]]},"assertion":[{"value":"1 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISBRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Bioinformatics Research and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Helsinki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isbra2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.helsinki.fi\/en\/conferences\/isbra2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}