{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:58:40Z","timestamp":1742918320462,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819970735"},{"type":"electronic","value":"9789819970742"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-7074-2_30","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T10:02:39Z","timestamp":1696672959000},"page":"387-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hist2Vec: Kernel-Based Embeddings for\u00a0Biological Sequence Classification"],"prefix":"10.1007","author":[{"given":"Sarwan","family":"Ali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haris","family":"Mansoor","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":[[2023,10,8]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Ali, S., Bello, B., Chourasia, P., et al.: Pwm2vec: an efficient embedding approach for viral host specification from coronavirus spike sequences. MDPI Biology (2022)","DOI":"10.3390\/biology11030418"},{"key":"30_CR2","unstructured":"Ali, S., Bello, B., Chourasia, P., et al.: Virus2vec: Viral sequence classification using machine learning. arXiv preprint arXiv:2304.12328 (2023)"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Ali, S., Patterson, M.: Spike2vec: An efficient and scalable embedding approach for covid-19 spike sequences. CoRR arXiv:2109.05019 (2021)","DOI":"10.1109\/BigData52589.2021.9671848"},{"key":"30_CR4","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. IEEE\/ACM Transactions on Computational Biology and Bioinformatics (2022)","DOI":"10.1109\/TCBB.2022.3206284"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Ali, S., Tamkanat-E-Ali, Khan, M.A., Khan, I., Patterson, M., et al.: Effective and scalable clustering of sars-cov-2 sequences. Accepted for publication at \u201cInternational Conference on Big Data Research (ICBDR)\u201d (2021)","DOI":"10.1145\/3505745.3505752"},{"issue":"3","key":"30_CR6","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul, S.F., Gish, W., Miller, W., Myers, E.W., Lipman, D.J.: Basic local alignment search tool. J. Mol. Biol. 215(3), 403\u2013410 (1990)","journal-title":"J. Mol. Biol."},{"issue":"1","key":"30_CR7","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s12859-023-05236-w","volume":"24","author":"B Bokharaeian","year":"2023","unstructured":"Bokharaeian, B., et al.: Automatic extraction of ranked snp-phenotype associations from text using a bert-lstm-based method. BMC Bioinform. 24(1), 144 (2023)","journal-title":"BMC Bioinform."},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Bonidia, R.P., Sampaio, L.D., et al.: Feature extraction approaches for biological sequences: a comparative study of mathematical features. Briefings in Bioinform. 22(5), bbab011 (2021)","DOI":"10.1093\/bib\/bbab011"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Brandes, N., Ofer, D., Peleg, Y., Rappoport, N., Linial, M.: Proteinbert: a universal deep-learning model of protein sequence and func. Bioinformatics 38(8) (2022)","DOI":"10.1093\/bioinformatics\/btac020"},{"issue":"8","key":"30_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3465398","volume":"54","author":"J Chen","year":"2021","unstructured":"Chen, J., Li, K., et al.: A survey on applications of artificial intelligence in fighting against covid-19. ACM Comput. Surv. (CSUR) 54(8), 1\u201332 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"4","key":"30_CR11","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1089\/cmb.2022.0424","volume":"30","author":"P Chourasia","year":"2023","unstructured":"Chourasia, P., Ali, S., Ciccolella, S., Vedova, G.D., Patterson, M.: Reads2vec: Efficient embedding of raw high-throughput sequencing reads data. J. Comput. Biol. 30(4), 469\u2013491 (2023)","journal-title":"J. Comput. Biol."},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Chourasia, P., Ali, S., et al.: Clustering sars-cov-2 variants from raw high-throughput sequencing reads data. In: International Conference on Computational Advances in Bio and Medical Sciences, pp. 133\u2013148. Springer (2021)","DOI":"10.1007\/978-3-031-17531-2_11"},{"key":"30_CR13","unstructured":"Corso, G., et al.: Neural distance embeddings for biological sequences. In: Advances in Neural Information Processing Systems, vol. 34, pp. 18539\u201318551 (2021)"},{"key":"30_CR14","unstructured":"Farhan, M., Tariq, J., Zaman, A., Shabbir, M., Khan, I.: Efficient approximation algorithms for strings kernel based sequence classification. In: Advances in neural information processing systems (NeurIPS), pp. 6935\u20136945 (2017)"},{"issue":"1","key":"30_CR15","doi-asserted-by":"publisher","DOI":"10.1002\/cpbi.108","volume":"72","author":"F Gabler","year":"2020","unstructured":"Gabler, F., Nam, S.Z., et al.: Protein sequence analysis using the mpi bioinformatics toolkit. Curr. Protoc. Bioinformatics 72(1), e108 (2020)","journal-title":"Curr. Protoc. Bioinformatics"},{"issue":"1","key":"30_CR16","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1080\/13102818.2017.1364977","volume":"32","author":"FS Golestan Hashemi","year":"2018","unstructured":"Golestan Hashemi, F.S., et al.: Intelligent mining of large-scale bio-data: bioinformatics applications. Biotech Biotechnol. Equipment 32(1), 10\u201329 (2018)","journal-title":"Biotech Biotechnol. Equipment"},{"issue":"10","key":"30_CR17","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.3390\/genes13101744","volume":"13","author":"M Guan","year":"2022","unstructured":"Guan, M., Zhao, L., Yau, S.S.T.: Classification of protein sequences by a novel alignment-free method on bacterial and virus families. Genes 13(10), 1744 (2022)","journal-title":"Genes"},{"issue":"1","key":"30_CR18","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 Bioinform. 20(1), 1\u201317 (2019)","journal-title":"BMC Bioinform."},{"key":"30_CR19","unstructured":"Hsu, C.W., et al.: A practical guide to support vector classification (2003)"},{"key":"30_CR20","unstructured":"Human DNA: https:\/\/www.kaggle.com\/code\/nageshsingh\/demystify-dna-sequencing-with-machine-learning\/data (2022). Accessed 10 Oct 2022"},{"issue":"11","key":"30_CR21","doi-asserted-by":"publisher","first-page":"4247","DOI":"10.1016\/j.jcp.2010.02.009","volume":"229","author":"A Khajeh-Saeed","year":"2010","unstructured":"Khajeh-Saeed, A., Poole, S., Perot, J.B.: Acceleration of the smith-waterman algorithm using single and multiple graphics processors. J. Comput. Phys. 229(11), 4247\u20134258 (2010)","journal-title":"J. Comput. Phys."},{"issue":"1","key":"30_CR22","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1093\/bfgp\/elac034","volume":"22","author":"M Khandelwal","year":"2023","unstructured":"Khandelwal, M., Kumar Rout, R., Umer, S., Mallik, S., Li, A.: Multifactorial feature extraction and site prognosis model for protein methylation data. Brief. Funct. Genomics 22(1), 20\u201330 (2023)","journal-title":"Brief. Funct. Genomics"},{"key":"30_CR23","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.bbrc.2020.09.010","volume":"533","author":"K Kuzmin","year":"2020","unstructured":"Kuzmin, K., et al.: Machine learning methods accurately predict host specificity of coronaviruses based on spike sequences alone. Biochem. Biophys. Res. Commun. 533, 553\u2013558 (2020)","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Leslie, C., Eskin, E., Noble, W.S.: The spectrum kernel: A string kernel for svm protein classification. In: Biocomputing, pp. 564\u2013575 (2001)","DOI":"10.1142\/9789812799623_0053"},{"issue":"4","key":"30_CR25","doi-asserted-by":"publisher","first-page":"1817","DOI":"10.1016\/j.eswa.2007.08.088","volume":"35","author":"SW Lin","year":"2008","unstructured":"Lin, S.W., Ying, K.C., Chen, S.C., Lee, Z.J.: Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Syst. Appl. 35(4), 1817\u20131824 (2008)","journal-title":"Expert Syst. Appl."},{"issue":"5","key":"30_CR26","doi-asserted-by":"publisher","first-page":"3171","DOI":"10.1109\/TIT.2019.2946846","volume":"66","author":"H Lou","year":"2019","unstructured":"Lou, H., Schwartz, M., Bruck, J., Farnoud, F.: Evolution of $$ k $$-mer frequencies and entropy in duplication and substitution mutation systems. IEEE Trans. Inf. Theory 66(5), 3171\u20133186 (2019)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"D1","key":"30_CR27","doi-asserted-by":"publisher","first-page":"D351","DOI":"10.1093\/nar\/gky1100","volume":"47","author":"AL Mitchell","year":"2019","unstructured":"Mitchell, A.L., Attwood, T.K., Babbitt, P.C., Blum, M., Bork, P., Bridge, A., Brown, S.D., Chang, H.Y., El-Gebali, S., Fraser, M.I., et al.: Interpro in 2019: improving coverage, classification and access to protein sequence annotations. Nucleic Acids Res. 47(D1), D351\u2013D360 (2019)","journal-title":"Nucleic Acids Res."},{"key":"30_CR28","unstructured":"Otto, M.P.: Scalable and interpretable kernel methods based on random fourier features (2023)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"P. Kuksa, P., Khan, I., Pavlovic, V.: Generalized similarity kernels for efficient sequence classification. In: Proceedings of the 2012 SIAM International Conference on Data Mining, pp. 873\u2013882. SIAM (2012)","DOI":"10.1137\/1.9781611972825.75"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Pickett, B.E., Sadat, E.L., Zhang, Y., Noronha, J.M., Squires, R.B., et al.: Vipr: an open bioinformatics database and analysis resource for virology research. Nucleic acids research, pp. D593\u2013D598 (2012)","DOI":"10.1093\/nar\/gkr859"},{"issue":"6","key":"30_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-1118-x","volume":"16","author":"R Qi","year":"2022","unstructured":"Qi, R., Guo, F., Zou, Q.: String kernels construction and fusion: a survey with bioinformatics application. Front. Comp. Sci. 16(6), 166904 (2022)","journal-title":"Front. Comp. Sci."},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Rao, R., Bhattacharya, N., et al.: Evaluating protein transfer learning with tape. Advances in neural information processing systems 32 (2019)","DOI":"10.1101\/676825"},{"issue":"12","key":"30_CR33","doi-asserted-by":"publisher","first-page":"6575","DOI":"10.1007\/s00521-020-05419-z","volume":"33","author":"I Roman","year":"2021","unstructured":"Roman, I., Santana, R., et al.: In-depth analysis of svm kernel learning and its components. Neural Comput. Appl. 33(12), 6575\u20136594 (2021)","journal-title":"Neural Comput. Appl."},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Saifuddin, K.M., et al.: Seq-hygan: Sequence classification via hypergraph attention network. arXiv preprint arXiv:2303.02393 (2023)","DOI":"10.1145\/3583780.3615057"},{"issue":"11","key":"30_CR35","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1109\/78.650102","volume":"45","author":"B Scholkopf","year":"1997","unstructured":"Scholkopf, B., Sung, K.K., et al.: Comparing support vector machines with gaussian kernels to radial basis function classifiers. IEEE Trans. Signal Process. 45(11), 2758\u20132765 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Shen, J., Qu, et al.: Wasserstein distance guided representation learning for domain adaptation. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11784"},{"issue":"1","key":"30_CR37","doi-asserted-by":"publisher","first-page":"5505","DOI":"10.1038\/s41598-022-09484-3","volume":"12","author":"R Sikander","year":"2022","unstructured":"Sikander, R., Ghulam, A., Ali, F.: Xgb-drugpred: computational prediction of druggable proteins using extreme gradient boosting and optimized features set. Sci. Rep. 12(1), 5505 (2022)","journal-title":"Sci. Rep."},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Solis-Reyes, S., Avino, M., Poon, A., Kari, L.: An open-source k-mer based machine learning tool for fast and accurate subtyping of hiv-1 genomes. Plos One (2018)","DOI":"10.1101\/362780"},{"key":"30_CR39","unstructured":"Sun, C., Ai, X., Zhang, Z., Hancock, E.R.: Labeled subgraph entropy kernel. arXiv preprint arXiv:2303.13543 (2023)"},{"key":"30_CR40","unstructured":"Taslim, M., Prakash, C., et al.: Hashing2vec: Fast embedding generation for sars-cov-2 spike sequence classification. In: ACML, pp. 754\u2013769. PMLR (2023)"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Vamathevan, J., Clark, et al.: Applications of machine learning in drug discovery and development. Nature Rev. Drug Discovery 18(6), 463\u2013477 (2019)","DOI":"10.1038\/s41573-019-0024-5"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Wood, D., Salzberg, S.: Kraken: ultrafast metagenomic sequence classification using exact alignments. Genome Biol. 15 (2014)","DOI":"10.1186\/gb-2014-15-3-r46"},{"key":"30_CR43","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp. 478\u2013487 (2016)"}],"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\/978-981-99-7074-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T14:04:14Z","timestamp":1703340254000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-7074-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819970735","9789819970742"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-7074-2_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","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":"Wroc\u0142aw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isbra2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mangul-lab-usc.github.io\/ISBRA23\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"89","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}