{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:57:09Z","timestamp":1743033429836,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333767"},{"type":"electronic","value":"9783031333774"}],"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\/978-3-031-33377-4_14","type":"book-chapter","created":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T09:02:36Z","timestamp":1685178156000},"page":"173-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["BioSequence2Vec: Efficient Embedding Generation for\u00a0Biological Sequences"],"prefix":"10.1007","author":[{"given":"Sarwan","family":"Ali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Usama","family":"Sardar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murray","family":"Patterson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imdad Ullah","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,28]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Ali, S.: Evaluating covid-19 sequence data using nearest-neighbors based network model. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 5182\u20135188. Osaka, Japan (2022). https:\/\/doi.org\/10.1109\/BigData55660.2022.10020653","DOI":"10.1109\/BigData55660.2022.10020653"},{"issue":"3","key":"14_CR2","doi-asserted-by":"publisher","first-page":"418","DOI":"10.3390\/biology11030418","volume":"11","author":"S Ali","year":"2022","unstructured":"Ali, S., Bello, B., Chourasia, P., Punathil, R.T., Zhou, Y., Patterson, M.: PWM2Vec: an efficient embedding approach for viral host specification from coronavirus spike sequences. Biology 11(3), 418 (2022)","journal-title":"Biology"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Ali, S., Bello, B., Tayebi, Z., Patterson, M.: Characterizing sars-cov-2 spike sequences based on geographical location. J. Comput. Biol. 30, 0391 (2023)","DOI":"10.1089\/cmb.2022.0391"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Ali, S., Murad, T., Chourasia, P., Patterson, M.: Spike2signal: classifying coronavirus spike sequences with deep learning. In: 2022 IEEE Eighth International Conference on Big Data Computing Service and Applications (BigDataService), pp. 81\u201388 (2022)","DOI":"10.1109\/BigDataService55688.2022.00020"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Ali, S., Patterson, M.: Spike2vec: an efficient and scalable embedding approach for COVID-19 spike sequences. In: IEEE Big Data, pp. 1533\u20131540 (2021)","DOI":"10.1109\/BigData52589.2021.9671848"},{"key":"14_CR6","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":"14_CR7","doi-asserted-by":"crossref","unstructured":"Ali, S., Sahoo, B., Ullah, N., Zelikovskiy, A., Patterson, M., Khan, I.: A k-mer based approach for sars-cov-2 variant identification. In: International Symposium on Bioinformatics Research and Applications, pp. 153\u2013164 (2021)","DOI":"10.1007\/978-3-030-91415-8_14"},{"issue":"1","key":"14_CR8","doi-asserted-by":"publisher","first-page":"4154","DOI":"10.1038\/s41598-023-31368-3","volume":"13","author":"S Ali","year":"2023","unstructured":"Ali, S., Sahoo, B., Zelikovsky, A., Chen, P.Y., Patterson, M.: Benchmarking machine learning robustness in COVID-19 genome sequence classification. Sci. Rep. 13(1), 4154 (2023)","journal-title":"Sci. Rep."},{"issue":"7","key":"14_CR9","doi-asserted-by":"publisher","first-page":"1881","DOI":"10.1007\/s11517-022-02570-8","volume":"60","author":"S Ali","year":"2022","unstructured":"Ali, S., Zhou, Y., Patterson, M.: Efficient analysis of COVID-19 clinical data using machine learning models. Med. Biol. Eng. Comput. 60(7), 1881\u20131896 (2022)","journal-title":"Med. Biol. Eng. Comput."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Alon, N., Matias, Y., Szegedy, M.: The space complexity of approximating the frequency moments. In: Symposium on Theory of computing, pp. 20\u201329 (1996)","DOI":"10.1145\/237814.237823"},{"key":"14_CR11","doi-asserted-by":"publisher","first-page":"5155","DOI":"10.1073\/pnas.83.14.5155","volume":"83","author":"B Blaisdell","year":"1986","unstructured":"Blaisdell, B.: A measure of the similarity of sets of sequences not requiring sequence alignment. Proc. Natl. Acad. Sci. 83, 5155\u20135159 (1986)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Borisov, V., et al.: Deep neural networks and tabular data: a survey. arXiv preprint arXiv:2110.01889 (2021)","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"14_CR13","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 function. Bioinformatics 38(8), 2102\u20132110 (2022)","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Carter, J.L., Wegman, M.N.: Universal classes of hash functions. In: ACM symposium on Theory of computing, pp. 106\u2013112 (1979)","DOI":"10.1145\/800105.803400"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Chourasia, P., Ali, S., Ciccolella, S., Della Vedova, G., Patterson, M.: Clustering sars-cov-2 variants from raw high-throughput sequencing reads data. In: Computational Advances in Bio and Medical Sciences (ICCABS), pp. 133\u2013148 (2022)","DOI":"10.1007\/978-3-031-17531-2_11"},{"key":"14_CR16","doi-asserted-by":"publisher","unstructured":"Chourasia, P., Ali, S., Patterson, M.: Informative initialization and kernel selection improves t-SNE for biological sequences. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 101\u2013106. Osaka, Japan (2022). https:\/\/doi.org\/10.1109\/BigData55660.2022.10020217","DOI":"10.1109\/BigData55660.2022.10020217"},{"issue":"5\u20136","key":"14_CR17","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.ygeno.2017.06.007","volume":"109","author":"B Chowdhury","year":"2017","unstructured":"Chowdhury, B., Garai, G.: A review on multiple sequence alignment from the perspective of genetic algorithm. Genomics 109(5\u20136), 419\u2013431 (2017)","journal-title":"Genomics"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Cristianini, N., Shawe-Taylor, J., et al.: An introduction to support vector machines and other Kernel-based learning methods. Cambridge University Press (2000)","DOI":"10.1017\/CBO9780511801389"},{"key":"14_CR19","unstructured":"Farhan, M., Tariq, J., Zaman, A., Shabbir, M., Khan, I.U.: Efficient approximation algorithms for strings Kernel based sequence classification. In: NeurIPS, pp. 6935\u20136945 (2017)"},{"issue":"2","key":"14_CR20","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/s00285-013-0705-3","volume":"69","author":"M Ghandi","year":"2014","unstructured":"Ghandi, M., Noori, M., Beer, M.: Robust k k-mer frequency estimation using gapped k-mers. J. Math. Biol. 69(2), 469\u2013500 (2014)","journal-title":"J. Math. Biol."},{"key":"14_CR21","unstructured":"GISAID. https:\/\/www.gisaid.org\/ (2022). Accessed 04 Dec 2022"},{"issue":"1","key":"14_CR22","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."},{"issue":"3","key":"14_CR23","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1016\/j.patcog.2006.07.009","volume":"40","author":"H Hoffmann","year":"2007","unstructured":"Hoffmann, H.: Kernel PCA for novelty detection. Pattern Recogn. 40(3), 863\u2013874 (2007)","journal-title":"Pattern Recogn."},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Hu, W., Bansal, R., Cao, K., Rao, N., Subbian, K., Leskovec, J.: Learning backward compatible embeddings. arXiv preprint arXiv:2206.03040 (2022)","DOI":"10.1145\/3534678.3539194"},{"key":"14_CR25","unstructured":"Human DNA. https:\/\/www.kaggle.com\/code\/nageshsingh\/demystify-dna-sequencing-with-machine-learning\/data. Accessed 10 Oct 2022"},{"issue":"7873","key":"14_CR26","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper, J., et al.: Highly accurate protein structure prediction with AlphaFold. Nature 596(7873), 583\u2013589 (2021)","journal-title":"Nature"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Kuzmin, K., et al.: Machine learning methods accurately predict host specificity of coronaviruses based on spike sequences alone. Biochem. Biophys. Res. Comm. 533(3), 553\u2013558 (2020)","DOI":"10.1016\/j.bbrc.2020.09.010"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"O\u2019Toole, A., et al.: Assignment of epidemiological lineages in an emerging pandemic using the pangolin tool. Virus Evol. 7(2), veab064 (2021)","DOI":"10.1093\/ve\/veab064"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Rambaut, A., et al.: A dynamic nomenclature proposal for SARS-CoV-2 lineages to assist genomic epidemiology. Nature Microbiol. 5, 1403\u20131407 (2020)","DOI":"10.1038\/s41564-020-0770-5"},{"key":"14_CR30","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 A.I (2018)","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"14_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","volume":"81","author":"R Shwartz-Ziv","year":"2022","unstructured":"Shwartz-Ziv, R., Armon, A.: Tabular data: deep learning is not all you need. Inf. Fusion 81, 84\u201390 (2022)","journal-title":"Inf. Fusion"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Singh, R., Sekhon, A., et al.: GakCo: a fast gapped k-mer string kernel using counting. In: Joint ECML and Knowledge Discovery in Databases, pp. 356\u2013373 (2017)","DOI":"10.1007\/978-3-319-71249-9_22"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Stephens, Z.D., et al.: Big data: astronomical or genomical? PLoS Biol. 13, e1002195 (2015)","DOI":"10.1371\/journal.pbio.1002195"},{"issue":"12","key":"14_CR34","doi-asserted-by":"publisher","first-page":"348","DOI":"10.3390\/a14120348","volume":"14","author":"Z Tayebi","year":"2021","unstructured":"Tayebi, Z., Ali, S., Patterson, M.: Robust representation and efficient feature selection allows for effective clustering of SARS-CoV-2 variants. Algorithms 14(12), 348 (2021)","journal-title":"Algorithms"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Ullah, A., Ali, S., Khan, I., Khan, M.A., Faizullah, S.: Effect of analysis window and feature selection on classification of hand movements using EMG signal. In: SAI Intelligent Systems Conference (IntelliSys), pp. 400\u2013415 (2020)","DOI":"10.1007\/978-3-030-55190-2_30"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: IJCNN, pp. 1578\u20131585 (2017)","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"14_CR37","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","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33377-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T06:17:05Z","timestamp":1729491425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33377-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333767","9783031333774"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33377-4_14","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":"28 May 2023","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":"Osaka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","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":"143","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":"0","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":"18% - 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":"3.5","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":"10","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}