{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T11:46:46Z","timestamp":1747482406371,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819722402"},{"type":"electronic","value":"9789819722389"}],"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\/978-981-97-2238-9_15","type":"book-chapter","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T12:01:48Z","timestamp":1714478508000},"page":"194-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Universal Non-parametric Approach for\u00a0Improved Molecular Sequence Analysis"],"prefix":"10.1007","author":[{"given":"Sarwan","family":"Ali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamkanat E","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prakash","family":"Chourasia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murray","family":"Patterson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,1]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et\u00a0al.: Low-resource text classification: a parameter-free classification method with compressors. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 6810\u20136828 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.426"},{"issue":"17","key":"15_CR2","doi-asserted-by":"publisher","first-page":"3035","DOI":"10.1093\/bioinformatics\/bty222","volume":"34","author":"S Budach","year":"2018","unstructured":"Budach, S., Marsico, A.: Pysster: classification of biological sequences by learning sequence and structure motifs with convolutional neural networks. Bioinformatics 34(17), 3035\u20133037 (2018)","journal-title":"Bioinformatics"},{"key":"15_CR3","unstructured":"Burrows, M.: A block-sorting lossless data compression algorithm. In: SRS Research Report, vol. 124 (1994)"},{"issue":"17","key":"15_CR4","first-page":"6","volume":"6","author":"AS Shah","year":"2019","unstructured":"Shah, A.S., Sethi, M.A.J.: The improvised Gzip, a technique for real time lossless data compression. EAI Endorsed Trans. CASA 6(17), 6 (2019)","journal-title":"EAI Endorsed Trans. CASA"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Kryukov, K., Jin, L., Nakagawa, S.: Efficient compression of SARS-COV-2 genome data using nucleotide archival format. In: Patterns, vol.\u00a03, no.\u00a09 (2022)","DOI":"10.1016\/j.patter.2022.100562"},{"issue":"5","key":"15_CR6","doi-asserted-by":"publisher","first-page":"055002","DOI":"10.1088\/2399-6528\/acd2a3","volume":"7","author":"M Vedak","year":"2023","unstructured":"Vedak, M., Ackland, G.J.: Compression and information entropy of binary strings from the collision history of three hard balls. J. Phys. Commun. 7(5), 055002 (2023)","journal-title":"J. Phys. Commun."},{"issue":"1","key":"15_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-8-252","volume":"8","author":"P Ferragina","year":"2007","unstructured":"Ferragina, P., Giancarlo, R., Greco, V., Manzini, G., Valiente, G.: Compression-based classification of biological sequences and structures via the universal similarity metric: experimental assessment. BMC Bioinf. 8(1), 1\u201320 (2007)","journal-title":"BMC Bioinf."},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"4939","DOI":"10.1109\/ACCESS.2020.3048309","volume":"9","author":"R Wei","year":"2021","unstructured":"Wei, R., Mahmood, A.: Recent advances in variational autoencoders with representation learning for biomedical informatics: a survey. IEEE Access 9, 4939\u20134956 (2021)","journal-title":"IEEE Access"},{"key":"15_CR9","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)"},{"issue":"3","key":"15_CR10","doi-asserted-by":"publisher","first-page":"418","DOI":"10.3390\/biology11030418","volume":"11","author":"S Ali","year":"2022","unstructured":"Ali, S., et al.: PWM2Vec: an efficient embedding approach for viral host specification from coronavirus spike sequences. Biology 11(3), 418 (2022)","journal-title":"Biology"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Ali, S., Sahoo, B., Khan, M.A., Zelikovsky, A., Khan, I.U., Patterson, M.: Efficient approximate kernel based spike sequence classification. In: IEEE\/ACM Transactions on Computational Biology and Bioinformatics (2022)","DOI":"10.1109\/TCBB.2022.3206284"},{"issue":"1","key":"15_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-019-3220-8","volume":"20","author":"M Heinzinger","year":"2019","unstructured":"Heinzinger, M., et al.: Modeling aspects of the language of life through transfer-learning protein sequences. BMC Bioinf. 20(1), 1\u201317 (2019)","journal-title":"BMC Bioinf."},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Yang, K.K., Fusi, N., Lu, A.X.: Convolutions are competitive with transformers for protein sequence pretraining, bioRxiv, pp. 2022\u201305 (2022)","DOI":"10.1101\/2022.05.19.492714"},{"key":"15_CR14","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.ab.2019.02.017","volume":"571","author":"NQK Le","year":"2019","unstructured":"Le, N.Q.K., et al.: ienhancer-5step: identifying enhancers using hidden information of DNA sequences via chou\u2019s 5-step rule and word embedding. Anal. Biochem. 571, 53\u201361 (2019)","journal-title":"Anal. Biochem."},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Shen, J., Qu, Y., Zhang, W., Yu, Y.: Wasserstein distance guided representation learning for domain adaptation. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"1069558","DOI":"10.3389\/fgene.2022.1069558","volume":"13","author":"B Dong","year":"2022","unstructured":"Dong, B., et al.: Antimicrobial peptides prediction method based on sequence multidimensional feature embedding. Front. Genet. 13, 1069558 (2022)","journal-title":"Front. Genet."},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Gemci, F., Ibrikci, T., Cevik, U.: Deep learning algorithm for detection of protein remote homology. Comput. Syst. Sci. Eng. 46(3) (2023)","DOI":"10.32604\/csse.2023.032706"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ghandi, M., et\u00a0al.: Enhanced regulatory sequence prediction using gapped k-mer features. In: PLoS Computational Biology, vol.\u00a010, no.\u00a07 (2014)","DOI":"10.1371\/journal.pcbi.1003711"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Ali, S., Sardar, U., Patterson, M., Khan, I.U.: Biosequence2vec: efficient embedding generation for biological sequences. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 173\u2013185 (2023)","DOI":"10.1007\/978-3-031-33377-4_14"},{"issue":"3","key":"15_CR20","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.3390\/s23031219","volume":"23","author":"D Azevedo","year":"2023","unstructured":"Azevedo, D., Rodrigues, A.M., Canh\u00e3o, H., Carvalho, A.M., Souto, A.: Zgli: a pipeline for clustering by compression with application to patient stratification in spondyloarthritis. Sensors 23(3), 1219 (2023)","journal-title":"Sensors"},{"key":"15_CR21","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.ijar.2007.03.011","volume":"47","author":"S Mantaci","year":"2008","unstructured":"Mantaci, S., Restivo, A., Sciortino, M.: Distance measures for biological sequences: some recent approaches. J. Approximate Reasoning 47, 109\u2013124 (2008)","journal-title":"J. Approximate Reasoning"},{"key":"15_CR22","unstructured":"Kolmogorov, A.N.: On tables of random numbers. Sankhy\u0101: Indian J. Stat. Ser. A 25, 369\u2013376 (1963)"},{"issue":"6","key":"15_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.3390\/a13060151","volume":"13","author":"B Carpentieri","year":"2020","unstructured":"Carpentieri, B.: Compression of next-generation sequencing data and of DNA digital files. Algorithms 13(6), 151 (2020)","journal-title":"Algorithms"},{"issue":"3","key":"15_CR24","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"23","author":"J Ziv","year":"1977","unstructured":"Ziv, J., Lempel, A.: A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 23(3), 337\u2013343 (1977)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Yergeau, F.: UTF-8, a transformation format of unicode and ISO 10646, Technical Report (1996)","DOI":"10.17487\/rfc2044"},{"issue":"12","key":"15_CR26","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/TIT.2004.838101","volume":"50","author":"M Li","year":"2004","unstructured":"Li, M., Chen, X., Li, X., Ma, B., Vitanyi, P.: The similarity metric. IEEE Trans. Inf. Theory 50(12), 3250\u20133264 (2004)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"15_CR27","unstructured":"Human DNA. https:\/\/www.kaggle.com\/code\/nageshsingh\/demystify-dna-sequencing-with-machine-learning\/data Accessed 10 October 2022"},{"key":"15_CR28","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp. 478\u2013487 (2016)"},{"issue":"8","key":"15_CR29","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","volume":"38","author":"N Brandes","year":"2022","unstructured":"Brandes, N., Ofer, D., Peleg, Y., Rappoport, N., Linial, M.: ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics 38(8), 2102\u20132110 (2022)","journal-title":"Bioinformatics"},{"key":"15_CR30","unstructured":"Xu, J.-W., et\u00a0al.: An explicit construction of a reproducing gaussian kernel hilbert space. In: Conference on Acoustics Speech and Signal Processing Proceedings, vol.\u00a05, pp. V\u2013V (2006)"},{"key":"15_CR31","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1023\/A:1022936519097","volume":"17","author":"B Hammer","year":"2003","unstructured":"Hammer, B., Gersmann, K.: A note on the universal approximation capability of support vector machines. Neural Process. Lett. 17, 43\u201353 (2003)","journal-title":"Neural Process. Lett."},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Minh, H.Q., Niyogi, P., Yao, Y.: Mercer\u2019s theorem, feature maps, and smoothing. In: Conference on Learning Theory, pp. 154\u2013168 (2006)","DOI":"10.1007\/11776420_14"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2238-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T12:08:49Z","timestamp":1714478929000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2238-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722402","9789819722389"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2238-9_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":"1 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}