{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:40:59Z","timestamp":1757626859779,"version":"3.44.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031949272"},{"type":"electronic","value":"9783031949289"}],"license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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\/978-3-031-94928-9_15","type":"book-chapter","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T09:46:54Z","timestamp":1756633614000},"page":"202-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Position Specific Scoring Is All You Need? Revisiting Protein Sequence Classification Tasks"],"prefix":"10.1007","author":[{"given":"Sarwan","family":"Ali","sequence":"first","affiliation":[]},{"given":"Taslim","family":"Murad","sequence":"additional","affiliation":[]},{"given":"Prakash","family":"Chourasia","sequence":"additional","affiliation":[]},{"given":"Haris","family":"Mansoor","sequence":"additional","affiliation":[]},{"given":"Imdad Ullah","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Pin-Yu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Murray","family":"Patterson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Ali, S., Patterson, M.: Spike2Vec: an efficient and scalable embedding approach for COVID-19 spike sequences. In: IEEE International Conference on Big Data (Big Data), pp. 1533\u20131540 (2021)","DOI":"10.1109\/BigData52589.2021.9671848"},{"key":"15_CR2","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 Trans. Comput. Biol. Bioinform. (2022)","DOI":"10.1109\/TCBB.2022.3206284"},{"key":"15_CR3","doi-asserted-by":"publisher","unstructured":"Brandes, N., Ofer, D., Peleg, et\u00a0al.: ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics 38(8), 2102\u20132110 (2022). https:\/\/doi.org\/10.1093\/bioinformatics\/btac020","DOI":"10.1093\/bioinformatics\/btac020"},{"issue":"W1","key":"15_CR4","doi-asserted-by":"publisher","first-page":"W402","DOI":"10.1093\/nar\/gkz297","volume":"47","author":"DW Buchan","year":"2019","unstructured":"Buchan, D.W., Jones, D.T.: The PSIPRED protein analysis workbench: 20 years on. Nucleic Acids Res. 47(W1), W402\u2013W407 (2019)","journal-title":"Nucleic Acids Res."},{"issue":"7","key":"15_CR5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003711","volume":"10","author":"M Ghandi","year":"2014","unstructured":"Ghandi, M., Lee, D., et al.: Enhanced regulatory sequence prediction using gapped k-mer features. PLoS Comput. Biol. 10(7), e1003711 (2014)","journal-title":"PLoS Comput. Biol."},{"key":"15_CR6","unstructured":"GISAID Website (2022). https:\/\/www.gisaid.org\/. Accessed 17 Feb 2023"},{"key":"15_CR7","unstructured":"Grinsztajn, L., Oyallon, E., Varoquaux, G.: Why do tree-based models still outperform deep learning on tabular data? arXiv preprint arXiv:2207.08815 (2022)"},{"issue":"1","key":"15_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-019-3220-8","volume":"20","author":"M Heinzinger","year":"2019","unstructured":"Heinzinger, M., Elnaggar, A., Wang, Y., 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":"22","key":"15_CR9","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","volume":"89","author":"S Henikoff","year":"1992","unstructured":"Henikoff, S., Henikoff, J.G.: Amino acid substitution matrices from protein blocks. Proc. Natl. Acad. Sci. 89(22), 10915\u201310919 (1992)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"4","key":"15_CR10","first-page":"378","volume":"14","author":"T Hirokawa","year":"1998","unstructured":"Hirokawa, T., Boon-Chieng, S., Mitaku, S.: SOSUI: classification and secondary structure prediction system for membrane proteins. Bioinformatics (Oxford, England) 14(4), 378\u2013379 (1998)","journal-title":"Bioinformatics (Oxford, England)"},{"issue":"3","key":"15_CR11","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":"15_CR12","unstructured":"Joseph, M., Raj, H.: GATE: gated additive tree ensemble for tabular classification and regression. arXiv preprint arXiv:2207.08548 (2022)"},{"issue":"3","key":"15_CR13","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(3), 553\u2013558 (2020)","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"15_CR14","unstructured":"Leslie, C., Eskin, E., et\u00a0al.: Mismatch string kernels for SVM protein classification. In: Advances in Neural Information Processing Systems, pp. 1441\u20131448 (2003)"},{"key":"15_CR15","volume":"2022","author":"Z Lin","year":"2022","unstructured":"Lin, Z., et al.: Language models of protein sequences at the scale of evolution enable accurate structure prediction. BioRxiv 2022, 500902 (2022)","journal-title":"BioRxiv"},{"key":"15_CR16","unstructured":"Lodhi, H., Saunders, C., Shawe-Taylor, J., et\u00a0al.: Text classification using string kernels. J. Mach. Learn. Res. 2, 419\u2013444 (2002)"},{"issue":"2","key":"15_CR17","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/e22020255","volume":"22","author":"Y Ma","year":"2020","unstructured":"Ma, Y., Yu, Z., Tang, R., Xie, X., Han, G., Anh, V.V.: Phylogenetic analysis of HIV-1 genomes based on the position-weighted k-mers method. Entropy 22(2), 255 (2020)","journal-title":"Entropy"},{"key":"15_CR18","unstructured":"Malinin, A., Prokhorenkova, L., Ustimenko, A.: Uncertainty in gradient boosting via ensembles. In: International Conference on Learning Representations (ICLR) (2021)"},{"issue":"D1","key":"15_CR19","doi-asserted-by":"publisher","first-page":"D593","DOI":"10.1093\/nar\/gkr859","volume":"40","author":"BE Pickett","year":"2012","unstructured":"Pickett, B.E., et al.: VIPR: an open bioinformatics database and analysis resource for virology research. Nucleic Acids Res. 40(D1), D593\u2013D598 (2012)","journal-title":"Nucleic Acids Res."},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Rao, R., et al.: Evaluating protein transfer learning with tape. Adv. Neural Inf. Process. Syst. 32 (2019)","DOI":"10.1101\/676825"},{"issue":"1","key":"15_CR21","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/sj.bjp.0707307","volume":"152","author":"D Rognan","year":"2007","unstructured":"Rognan, D.: Chemogenomic approaches to rational drug design. Br. J. Pharmacol. 152(1), 38\u201352 (2007)","journal-title":"Br. J. Pharmacol."},{"key":"15_CR22","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"},{"issue":"14","key":"15_CR23","doi-asserted-by":"publisher","first-page":"i173","DOI":"10.1093\/bioinformatics\/btz322","volume":"35","author":"A Shrikumar","year":"2019","unstructured":"Shrikumar, A., Prakash, E., Kundaje, A.: GkmExplain: fast and accurate interpretation of nonlinear gapped k-mer SVMs. Bioinformatics 35(14), i173\u2013i182 (2019)","journal-title":"Bioinformatics"},{"issue":"8","key":"15_CR24","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.1093\/bioinformatics\/btaa003","volume":"36","author":"N Strodthoff","year":"2020","unstructured":"Strodthoff, N., Wagner, P., et al.: UDSMProt: universal deep sequence models for protein classification. Bioinformatics 36(8), 2401\u20132409 (2020)","journal-title":"Bioinformatics"},{"issue":"8","key":"15_CR25","first-page":"1","volume":"11","author":"NC Toussaint","year":"2010","unstructured":"Toussaint, N.C., Widmer, C., Kohlbacher, O., R\u00e4tsch, G.: Exploiting physico-chemical properties in string kernels. BMC Bioinform. 11(8), 1\u20139 (2010)","journal-title":"BMC Bioinform."},{"issue":"3","key":"15_CR26","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1017\/S0033583503003901","volume":"36","author":"JC Whisstock","year":"2003","unstructured":"Whisstock, J.C., Lesk, A.M.: Prediction of protein function from protein sequence and structure. Q. Rev. Biophys. 36(3), 307\u2013340 (2003)","journal-title":"Q. Rev. Biophys."},{"key":"15_CR27","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp. 478\u2013487 (2016)"},{"issue":"1","key":"15_CR28","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1882471.1882478","volume":"12","author":"Z Xing","year":"2010","unstructured":"Xing, Z., Pei, J., Keogh, E.: A brief survey on sequence classification. ACM SIGKDD Explor. Newsl. 12(1), 40\u201348 (2010)","journal-title":"ACM SIGKDD Explor. Newsl."}],"container-title":["Lecture Notes in Computer Science","Comparative Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-94928-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T23:41:53Z","timestamp":1757461313000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-94928-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"ISBN":["9783031949272","9783031949289"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-94928-9_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"1 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RECOMB-CG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"RECOMB International Workshop on Comparative Genomics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seoul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"24 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","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":"rcg2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/recomb-cg-2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}